Home

Awesome

Time Series AI Papers

A list of up-to-date time-series papers in AI venues, tracking the following conferences: WSDM, AAAI, ICLR, AISTATS, ICASSP, SDM, WWW, IJCAI, ICML, KDD, NeurIPS, CIKM, ICDM

<p align="center"> <img width="700" src="word-cloud.png" alt="overview" /> </p>

2024

ICML 2024

Multi-Patch Prediction: Adapting LLMs for Time Series Representation Learning

Graph-based Time Series Clustering for End-to-End Hierarchical Forecasting

MF-CLR: Multi-Frequency Contrastive Learning Representation for Time Series

Transformers with Loss Shaping Constraints for Long-Term Time Series Forecasting

CauDiTS: Causal Disentangled Domain Adaptation of Multivariate Time Series

A Vector Quantization Pretraining Method for EEG Time Series with Random Projection and Phase Alignment

SparseTSF: Modeling Long-term Time Series Forecasting with 1k Parameters

Learning Optimal Projection for Forecast Reconciliation of Hierarchical Time Series

Revitalizing Multivariate Time Series Forecasting: Learnable Decomposition with Inter-Series Dependencies and Intra-Series Variations Modeling

Bayesian Online Multivariate Time Series Imputation with Functional Decomposition

CATS: Enhancing Multivariate Time Series Forecasting by Constructing Auxiliary Time Series as Exogenous Variables

Position Paper: What Can Large Language Models Tell Us about Time Series Analysis

Deep Functional Factor Models: Forecasting High-Dimensional Functional Time Series via Bayesian Nonparametric Factorization

UP2ME: Univariate Pre-training to Multivariate Fine-tuning as a General-purpose Framework for Multivariate Time Series Analysis

Position Paper: Quo Vadis, Unsupervised Time Series Anomaly Detection?

Discovering Mixtures of Structural Causal Models from Time Series Data

Unlocking the Potential of Transformers in Time Series Forecasting with Sharpness-Aware Minimization and Channel-Wise Attention

An Analysis of Linear Time Series Forecasting Models

TimeMIL: Advancing Multivariate Time Series Classification via a Time-aware Multiple Instance Learning

TSLANet: Rethinking Transformers for Time Series Representation Learning

An Empirical Examination of Balancing Strategy for Counterfactual Estimation on Time Series

Timer: Transformers for Time Series at Scale

Time Weaver: A Conditional Time Series Generation Model

SIN: Selective and Interpretable Normalization for Long-Term Time Series Forecasting

Unified Training of Universal Time Series Forecasting Transformers

Time Series Diffusion in the Frequency Domain

Reservoir Computing for Short High-Dimensional Time Series: an Application to SARS-CoV-2 Hospitalization Forecast

Irregular Multivariate Time Series Forecasting: A Transformable Patching Graph Neural Networks Approach

Learning Causal Relations from Subsampled Time Series with Two Time-Slices

$S^2$IP-LLM: Semantic Space Informed Prompt Learning with LLM for Time Series Forecasting

Probabilistic time series modeling with decomposable denoising diffusion model

MOMENT: A Family of Open Time-series Foundation Models

TimeX++: Learning Time-Series Explanations with Information Bottleneck

A decoder-only foundation model for time-series forecasting

Time-Series Forecasting for Out-of-Distribution Generalization Using Invariant Learning

Conformal prediction for multi-dimensional time-series

TimeSiam: A Pre-Training Framework for Siamese Time-Series Modeling

Efficient and Effective Time-Series Forecasting with Spiking Neural Networks

IJCAI 2024

Large Language Models for Time Series: A Survey

Sub-Adjacent Transformer: Improving Time Series Anomaly Detection with Reconstruction Error from Sub-Adjacent Neighborhoods

An NCDE-based Framework for Universal Representation Learning of Time Series

Self-adaptive Extreme Penalized Loss for Imbalanced Time Series Prediction

SDformer: Transformer with Spectral Filter and Dynamic Attention for Multivariate Time Series Long-term Forecasting

Score-CDM: Score-Weighted Convolutional Diffusion Model for Multivariate Time Series Imputation

SCAT: A Time Series Forecasting with Spectral Central Alternating Transformers

Large Language Model Guided Knowledge Distillation for Time Series Anomaly Detection

SaSDim:Self-Adaptive Noise Scaling Diffusion Model for Spatial Time Series Imputation

Decoupled Invariant Attention Network for Multivariate Time-series Forecasting

Denoising-Aware Contrastive Learning for Noisy Time Series

Contrastive Learning Is Not Optimal for Quasiperiodic Time Series

Deep Frequency Derivative Learning for Non-stationary Time Series Forecasting

VCformer: Variable Correlation Transformer with Inherent Lagged Correlation for Multivariate Time Series Forecasting

Skip-Timeformer: Skip-Time Interaction Transformer for Long Sequence Time-Series Forecasting

Temporal Graph ODEs for Irregularly-Sampled Time Series

LeRet: Language-Empowered Retentive Network for Time Series Forecasting

Reconstructing Missing Variables for Multivariate Time Series Forecasting via Conditional Generative Flows

SpecAR-Net: Spectrogram Analysis and Representation Network for Time Series

Perturbation Guiding Contrastive Representation Learning for Time Series Anomaly Detection

Disentangling Domain and General Representations for Time Series Classification

WWW 2024

UniTime: A Language-Empowered Unified Model for Cross-Domain Time Series Forecasting

Dynamic Multi-Network Mining of Tensor Time Series

LARA: A Light and Anti-overfitting Retraining Approach for Unsupervised Time Series Anomaly Detection

Breaking the Time-Frequency Granularity Discrepancy in Time-Series Anomaly Detection

E2USD: Efficient-yet-effective Unsupervised State Detection for Multivariate Time Series

Revisiting VAE for Unsupervised Time Series Anomaly Detection: A Frequency Perspective

SDM 2024

Pupae: Intuitive and Actionable Explanations for Time Series Anomalies

Pattern-Based Time Series Semantic Segmentation with Gradual State Transitions

Towards Entity-Aware Conditional Variational Inference for Heterogeneous Time-Series Prediction: An Application to Hydrology

EBV: Electronic Bee-Veterinarian for Principled Mining and Forecasting of Honeybee Time Series

Time-Transformer: Integrating Local and Global Features for Better Time Series Generation

Message Propagation Through Time: An Algorithm for Sequence Dependency Retention in Time Series Modeling

Analysis of Causal and Non-Causal Convolution Networks for Time Series Classification

AISTATS 2024

Better Batch for Deep Probabilistic Time Series Forecasting

Fitting ARMA Time Series Models without Identification: A Proximal Approach

Multivariate Time Series Forecasting By Graph Attention Networks With Theoretical Guarantees

An Online Bootstrap for Time Series

Extended Deep Adaptive Input Normalization for Preprocessing Time Series Data for Neural Networks

Mixture-of-Linear-Experts for Long-term Time Series Forecasting

Unsupervised Change Point Detection in Multivariate Time Series

Multi-resolution Time-Series Transformer for Long-term Forecasting

Random Oscillators Network for Time Series Processing

ICLR 2024

Latent Trajectory Learning for Limited Timestamps under Distribution Shift over Time

ClimODE: Climate Forecasting With Physics-informed Neural ODEs

Soft Contrastive Learning for Time Series

FITS: Modeling Time Series with 10k Parameters

ModernTCN: A Modern Pure Convolution Structure for General Time Series Analysis

iTransformer: Inverted Transformers Are Effective for Time Series Forecasting

Inherently Interpretable Time Series Classification via Multiple Instance Learning

Generative Learning for Financial Time Series with Irregular and Scale-Invariant Patterns

Stable Neural Stochastic Differential Equations in Analyzing Irregular Time Series Data

SocioDojo: Building Lifelong Analytical Agents with Real-world Text and Time Series

Towards Transparent Time Series Forecasting

Multi-Resolution Diffusion Models for Time Series Forecasting

Diffusion-TS: Interpretable Diffusion for General Time Series Generation

Explaining Time Series via Contrastive and Locally Sparse Perturbations

Multi-scale Transformers with Adaptive Pathways for Time Series Forecasting

Copula Conformal prediction for multi-step time series prediction

CausalTime: Realistically Generated Time-series for Benchmarking of Causal Discovery

Interpretable Sparse System Identification: Beyond Recent Deep Learning Techniques on Time-Series Prediction

Time-LLM: Time Series Forecasting by Reprogramming Large Language Models

Learning to Embed Time Series Patches Independently

TACTiS-2: Better, Faster, Simpler Attentional Copulas for Multivariate Time Series

T-Rep: Representation Learning for Time Series using Time-Embeddings

Parametric Augmentation for Time Series Contrastive Learning

Conditional Information Bottleneck Approach for Time Series Imputation

TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting

TEST: Text Prototype Aligned Embedding to Activate LLM's Ability for Time Series

TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting

CARD: Channel Aligned Robust Blend Transformer for Time Series Forecasting

VQ-TR: Vector Quantized Attention for Time Series Forecasting

Disentangling Time Series Representations via Contrastive based l-Variational Inference

Retrieval-Based Reconstruction For Time-series Contrastive Learning

RobustTSF: Towards Theory and Design of Robust Time Series Forecasting with Anomalies

Transformer-Modulated Diffusion Models for Probabilistic Multivariate Time Series Forecasting

Generative Modeling of Regular and Irregular Time Series Data via Koopman VAEs

MG-TSD: Multi-Granularity Time Series Diffusion Models with Guided Learning Process

Towards Enhancing Time Series Contrastive Learning: A Dynamic Bad Pair Mining Approach

Rethinking Channel Dependence for Multivariate Time Series Forecasting: Learning from Leading Indicators

STanHop: Sparse Tandem Hopfield Model for Memory-Enhanced Time Series Prediction

Periodicity Decoupling Framework for Long-term Series Forecasting

Biased Temporal Convolution Graph Network for Time Series Forecasting with Missing Values

DAM: A Foundation Model for Forecasting

Leveraging Generative Models for Unsupervised Alignment of Neural Time Series Data

ARM: Refining Multivariate Forecasting with Adaptive Temporal-Contextual Learning

Language Models Represent Space and Time

Self-Supervised Contrastive Forecasting

AAAI 2024

HDMixer: Hierarchical Dependency with Extendable Patch for Multivariate Time Series Forecasting

Latent Diffusion Transformer for Probabilistic Time Series Forecasting

Learning from Polar Representation: An Extreme-Adaptive Model for Long-Term Time Series Forecasting

Diffusion Language-Shapelets for Semi-supervised Time-Series Classification

U-mixer: An Unet-Mixer Architecture with Stationarity Correction for Time Series Forecasting

Fully-Connected Spatial-Temporal Graph for Multivariate Time-Series Data

Considering Nonstationary within Multivariate Time Series with Variational Hierarchical Transformer for Forecasting

Cross-Domain Contrastive Learning for Time Series Clustering

When Model Meets New Normals: Test-Time Adaptation for Unsupervised Time-Series Anomaly Detection

GraFITi: Graphs for Forecasting Irregularly Sampled Time Series

MSGNet: Learning Multi-Scale Inter-series Correlations for Multivariate Time Series Forecasting

Graph-Aware Contrasting for Multivariate Time-Series Classification

Energy-Efficient Streaming Time Series Classification with Attentive Power Iteration

Cumulative Difference Learning VAE for Time-Series with Temporally Correlated Inflow-Outflow

IVP-VAE: Modeling EHR Time Series with Initial Value Problem Solvers

CUTS+: High-Dimensional Causal Discovery from Irregular Time-Series

Efficient Representation Learning of Satellite Image Time Series and Their Fusion for Spatiotemporal Applications

TimesURL: Self-Supervised Contrastive Learning for Universal Time Series Representation Learning

SimPSI: A Simple Strategy to Preserve Spectral Information in Time Series Data Augmentation

CGS-Mask: Making Time Series Predictions Intuitive for All

Time-Aware Knowledge Representations of Dynamic Objects with Multidimensional Persistence

Spatio-Temporal Pivotal Graph Neural Networks for Traffic Flow Forecasting

Towards Dynamic Spatial-Temporal Graph Learning: A Decoupled Perspective

ModWaveMLP: MLP-Based Mode Decomposition and Wavelet Denoising Model to Defeat Complex Structures in Traffic Forecasting

Adaptive Meta-Learning Probabilistic Inference Framework for Long Sequence Prediction

WSDM 2024

Cross-modal Self-Supervised Learning for Time-series through Latent Masking

NeuralReconciler for Hierarchical Time Series Forecasting

Continuous-time Autoencoders for Regular and Irregular Time Series Imputation

CreST: A Credible Spatiotemporal Learning Framework for Uncertainty-aware Traffic Forecasting

CityCAN: Causal Attention Network for Citywide Spatio-Temporal Forecasting

MultiSPANS: A Multi-range Spatial-Temporal Transformer Network for Traffic Forecast via Structural Entropy Optimization

2023

ICDM 2023

PatternRCA: A Pattern-aware Root Cause Analysis Framework For Multi-Dimensional Time Series

MTT-DynGL: Towards Multidimensional Topology-Oriented Time-Series Dynamic Graphs Learning Model

Rethinking Temporal Dependencies in Multiple Time Series: A Use Case in Financial Data

Koopman Invertible Autoencoder: Leveraging Forward and Backward Dynamics for Temporal Modeling

Self-supervised Pre-Training for Robust and Generic Spatial-Temporal Representations

Compatible Transformer for Irregularly Sampled Multivariate Time Series

Explainable Adaptive Tree-Based Model Selection for Time-Series Forecasting

Boosting Urban Prediction via Addressing Spatial-Temporal Distribution Shift

GAFNO: Gated Adaptive Fourier Neural Operator for Task-Agnostic Time Series Modeling

A Symbolic Representation of Two-Dimensional Time Series for Arbitrary Length DTW Motif

Counterfactual Explanations for Time Series Forecasting

CIKM 2023

ST-MoE: Spatio-Temporal Mixture-of-Experts for Debiasing in Traffic Prediction

Spatio-Temporal Meta Contrastive Learning

Spatial-Temporal Graph Boosting Networks: Enhancing Spatial-Temporal Graph Neural Networks via Gradient Boosting

MadSGM: Multivariate Anomaly Detection with Score-based Generative Models

Monotonic Neural Ordinary Differential Equation: Time-series Forecasting for Cumulative Data

Adaptive Graph Neural Diffusion for Traffic Demand Forecasting

CARPG: Cross-City Knowledge Transfer for Traffic Accident Prediction via Attentive Region-Level Parameter Generation

GBTTE: Graph Attention Network Based Bus Travel Time Estimation

Cross-city Few-Shot Traffic Forecasting via Traffic Pattern Bank

Follow the Will of the Market: A Context-Informed Drift-Aware Method for Stock Prediction

Diffusion Variational Autoencoder for Tackling Stochasticity in Multi-Step Regression Stock Price Prediction

Uncertainty Quantification via Spatial-Temporal Tweedie Model for Zero-inflated and Long-tail Travel Demand Prediction

Enhancing the Robustness via Adversarial Learning and Joint Spatial-Temporal Embeddings in Traffic Forecasting

Enhancing Spatio-temporal Traffic Prediction through Urban Human Activity Analysis

HST-GT: Heterogeneous Spatial-Temporal Graph Transformer for Delivery Time Estimation in Warehouse-Distribution Integration E-Commerce

Spatio-Temporal Adaptive Embedding Makes Vanilla Transformer SOTA for Traffic Forecasting

MLPST: MLP is All You Need for Spatio-Temporal Prediction

Mask- and Contrast-Enhanced Spatio-Temporal Learning for Urban Flow Prediction

Region Profile Enhanced Urban Spatio-Temporal Prediction via Adaptive Meta-Learning

PromptST: Prompt-Enhanced Spatio-Temporal Multi-Attribute Prediction

GCformer: An Efficient Solution for Accurate and Scalable Long-Term Multivariate Time Series Forecasting

MemDA: Forecasting Urban Time Series with Memory-based Drift Adaptation

Meta-Transfer-Learning for Time Series Data with Extreme Events: An Application to Water Temperature Prediction

Temporal Convolutional Explorer Helps Understand 1D-CNN's Learning Behavior in Time Series Classification from Frequency Domain

DSformer: A Double Sampling Transformer for Multivariate Time Series Long-term Prediction

TriD-MAE: A Generic Pre-trained Model for Multivariate Time Series with Missing Values

FAMC-Net: Frequency Domain Parity Correction Attention and Multi-Scale Dilated Convolution for Time Series Forecasting

DuoGAT: Dual Time-oriented Graph Attention Networks for Accurate, Efficient and Explainable Anomaly Detection on Time-series

Khronos: A Real-Time Indexing Framework for Time Series Databases on Large-Scale Performance Monitoring Systems

Density-Aware Temporal Attentive Step-wise Diffusion Model For Medical Time Series Imputation

A Co-training Approach for Noisy Time Series Learning

Time-series Shapelets with Learnable Lengths

Toward a Foundation Model for Time Series Data

Unlocking the Potential of Deep Learning in Peak-Hour Series Forecasting

TemDep: Temporal Dependency Priority for Multivariate Time Series Prediction

Clustering-property Matters: A Cluster-aware Network for Large Scale Multivariate Time Series Forecasting

Learning Visibility Attention Graph Representation for Time Series Forecasting

Rethinking Sensors Modeling: Hierarchical Information Enhanced Traffic Forecasting

Unleashing the Power of Shared Label Structures for Human Activity Recognition

NeurIPS 2023

One Fits All: Power General Time Series Analysis by Pretrained LM

MEMTO: Memory-guided Transformer for Multivariate Time Series Anomaly Detection

OneNet: Enhancing Time Series Forecasting Models under Concept Drift by Online Ensembling

Scale-teaching: Robust Multi-scale Training for Time Series Classification with Noisy Labels

Adaptive Normalization for Non-stationary Time Series Forecasting: A Temporal Slice Perspective

Causal Discovery from Subsampled Time Series with Proxy Variables

Predict, Refine, Synthesize: Self-Guiding Diffusion Models for Probabilistic Time Series Forecasting

Improving Day-Ahead Solar Irradiance Time Series Forecasting by Leveraging Spatio-Temporal Context

CrossGNN: Confronting Noisy Multivariate Time Series Via Cross Interaction Refinement

Time Series Kernels based on Nonlinear Vector AutoRegressive Delay Embeddings

WildfireSpreadTS: A dataset of multi-modal time series for wildfire spread prediction

Frequency-domain MLPs are More Effective Learners in Time Series Forecasting

ContiFormer: Continuous-Time Transformer for Irregular Time Series Modeling

Koopa: Learning Non-stationary Time Series Dynamics with Koopman Predictors

Conformal PID Control for Time Series Prediction

Drift doesn't Matter: Dynamic Decomposition with Diffusion Reconstruction for Unstable Multivariate Time Series Anomaly Detection

Sparse Deep Learning for Time Series Data: Theory and Applications

Large Language Models Are Zero Shot Time Series Forecasters

Sparse Graph Learning from Spatiotemporal Time Series

BasisFormer: Attention-based Time Series Forecasting with Learnable and Interpretable Basis

WITRAN: Water-wave Information Transmission and Recurrent Acceleration Network for Long-range Time Series Forecasting

Nominality Score Conditioned Time Series Anomaly Detection by Point/Sequential Reconstruction

Causal Discovery in Semi-Stationary Time Series

Conformal Prediction for Time Series with Modern Hopfield Networks

Time Series as Images: Vision Transformer for Irregularly Sampled Time Series

FourierGNN: Rethinking Multivariate Time Series Forecasting from a Pure Graph Perspective

Finding Order in Chaos: A Novel Data Augmentation Method for Time Series in Contrastive Learning

BioMassters: A Benchmark Dataset for Forest Biomass Estimation using Multi-modal Satellite Time-series

SimMTM: A Simple Pre-Training Framework for Masked Time-Series Modeling

Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistency

FOCAL: Contrastive Learning for Multimodal Time-Series Sensing Signals in Factorized Orthogonal Latent Space

On the Constrained Time-Series Generation Problem

Contrast Everything: A Hierarchical Contrastive Framework for Medical Time-Series

ForecastPFN: Synthetically-Trained Zero-Shot Forecasting

Neural Lad: A Neural Latent Dynamics Framework for Times Series Modeling

Taming Local Effects in Graph-based Spatiotemporal Forecasting

Deciphering Spatio-Temporal Graph Forecasting: A Causal Lens and Treatment

GPT-ST: Generative Pre-Training of Spatio-Temporal Graph Neural Networks

KDD 2023

Generative Causal Interpretation Model for Spatio-Temporal Representation Learning

Localised Adaptive Spatial-Temporal Graph Neural Network

Maintaining the status quo-Capturing invariant relations for OOD spatiotemporal learning

Pattern Expansion and Consolidation on Evolving Graphs for Continual Traffic Prediction

DCdetector: Dual Attention Contrastive Representation Learning for Time Series Anomaly Detection

Precursor-of-Anomaly Detection for Irregular Time Series

Transferable Graph Structure Learning for Graph-Based Traffic Forecasting Across Cities

TSMixer: Lightweight MLP-Mixer Model for Multivariate Time Series Forecasting

Hierarchical Proxy Modeling for Improved HPO in Time Series Forecasting

FLAMES2Graph: An Interpretable Federated Multivariate Time Series Classification Framework

When Rigidity Hurts: Soft Consistency Regularization for Probabilistic Hierarchical Time Series Forecasting

Warpformer: A Multi-Scale Modeling Approach for Irregular Clinical Time Series

WHEN: A Wavelet-DTW Hybrid Attention Network for Heterogeneous Time Series Analysis

Source-Free Domain Adaptation with Temporal Imputation for Time Series Data

Networked Time Series Imputation via Position-aware Graph Enhanced Variational Autoencoders

Sparse Binary Transformers for Multivariate Time Series Modeling

Imputation-based Time-Series Anomaly Detection with Conditional Weight-Incremental Diffusion Models

An Observed Value Consistent Diffusion Model for Imputing Missing Values in Multivariate Time Series

Parameter-free Spikelet: Discovering Different Length and Warped Time Series Motifs using an Adaptive Time Series Representation

DoubleAdapt: A Meta-Learning Approach to Incremental Learning for Stock Trend Forecasting

Web-Based Long-Term Spine Treatment Outcome Forecasting

ICML 2023

Domain Adaptation for Time Series Under Feature and Label Shifts

Learning Perturbations to Explain Time Series Predictions

Non-autoregressive Conditional Diffusion Models for Time Series Prediction

Probabilistic Imputation for Time-series Classification with Missing Data

Provably Convergent Schrödinger Bridge with Applications to Probabilistic Time Series Imputation

Learning Deep Time-index Models for Time Series Forecasting

Self-Interpretable Time Series Prediction with Counterfactual Explanations

Neural Continuous-Discrete State Space Models for Irregularly-Sampled Time Series

Neural Stochastic Differential Games for Time-series Analysis

Theoretical Guarantees of Learning Ensembling Strategies with Applications to Time Series Forecasting

Prototype-oriented unsupervised anomaly detection for multivariate time series

Sequential Monte Carlo Learning for Time Series Structure Discovery

Sequential Multi-Dimensional Self-Supervised Learning for Clinical Time Series

Feature Programming for Multivariate Time Series Prediction

SOM-CPC: Unsupervised Contrastive Learning with Self-Organizing Maps for Structured Representations of High-Rate Time Series

Deep Latent State Space Models for Time-Series Generation

Context Consistency Regularization for Label Sparsity in Time Series

Sequential Predictive Conformal Inference for Time Series

Regions of Reliability in the Evaluation of Multivariate Probabilistic Forecasts

Regression with Sensor Data Containing Incomplete Observations

Spatial-Temporal Graph Learning with Adversarial Contrastive Adaptation

IJCAI 2023

CTW: Confident Time-Warping for Time-Series Label-Noise Learning

Latent Processes Identification From Multi-View Time Series

SMARTformer: Semi-Autoregressive Transformer with Efficient Integrated Window Attention for Long Time Series Forecasting

DeLELSTM: Decomposition-based Linear Explainable LSTM to Capture Instantaneous and Long-term Effects in Time Series

Learning Gaussian Mixture Representations for Tensor Time Series Forecasting

pTSE: A Multi-model Ensemble Method for Probabilistic Time Series Forecasting

Distilling Universal and Joint Knowledge for Cross-Domain Model Compression on Time Series Data

Not Only Pairwise Relationships: Fine-Grained Relational Modeling for Multivariate Time Series Forecasting

Self-Recover: Forecasting Block Maxima in Time Series from Predictors with Disparate Temporal Coverage Using Self-Supervised Learning

Prompt Federated Learning for Weather Forecasting: Toward Foundation Models on Meteorological Data

WWW 2023

FormerTime: Hierarchical Multi-Scale Representations for Multivariate Time Series Classification

TFE-GNN: A Temporal Fusion Encoder Using Graph Neural Networks for Fine-grained Encrypted Traffic Classification

INCREASE: Inductive Graph Representation Learning for Spatio-Temporal Kriging

SDM 2023

Attention-Based Multi-modal Missing Value Imputation for Time Series Data with High Missing Rate

Probabilistic Decomposition Transformer for Time Series Forecasting

PMP: Privacy-Aware Matrix Profile against Sensitive Pattern Inference for Time Series

Context-aware Domain Adaptation for Time Series Anomaly Detection

GIST: Graph Inference for Structured Time Series

Discovering Multi-Dimensional Time Series Anomalies with K of N Anomaly Detection

Time-delayed Multivariate Time Series Predictions

Deep Contrastive One-Class Time Series Anomaly Detection

Exact and Heuristic Approaches to Speeding Up the MSM Time Series Distance Computation

Towards Learning in Grey Spatiotemporal Systems: A Prophet to Non-consecutive Spatiotemporal Dynamics

StAGN: Spatial-Temporal Adaptive Graph Network via Constranstive Learning for Sleep Stage Classification

STM-GAIL: Spatial-Temporal Meta-GAIL for Learning Diverse Human Driving Strategies

Mini-Batch Learning Strategies for modeling long term temporal dependencies: A study in environmental applications

A Two-View EEG Representation for Brain Cognition by Composite Temporal-Spatial Contrastive Learning

Spatiotemporal Classification with limited labels using Constrained Clustering for large datasets

AISTATS 2023

Vector Quantized Time Series Modeling with a Bidirectional Prior Model

Root Cause Identification for Collective Anomalies given a Summary Causal Graph and Time Series

Weather2K: A Multivariate Spatio-Temporal Benchmark Dataset for Meteorological Forecasting Based on Real-Time Observation Data from Ground Weather Stations

T-Phenotype: Discovering Phenotypes of Predictive Temporal Patterns in Disease Progression

Coherent Probabilistic Forecasting of Temporal Hierarchies

ICLR 2023

Crossformer: Transformer Utilizing Cross-Dimension Dependency for Multivariate Time Series Forecasting

MICN: Multi-scale Local and Global Context Modeling for Long-term Series Forecasting

Unsupervised Model Selection for Time Series Anomaly Detection

Sequential Latent Variable Models for Few-Shot High-Dimensional Time-Series Forecasting

Dynamical systems embedding with a physics-informed convolutional network

Contrastive Learning for Unsupervised Domain Adaptation of Time Series

Out-of-distribution Representation Learning for Time Series Classification

A Time Series is Worth 64 Words: Long-term Forecasting with Transformers

Scaleformer: Iterative Multi-scale Refining Transformers for Time Series Forecasting

Multivariate Time-series Imputation with Disentangled Temporal Representations

CUTS: Neural Causal Discovery from Unstructured Time-Series Data

TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis

Temporal Dependencies in Feature Importance for Time Series Prediction

Effectively Modeling Time Series with Simple Discrete State Spaces

Learning Fast and Slow for Time Series Forecasting

Recursive Time Series Data Augmentation

Koopman Neural Operator Forecaster for Time-series with Temporal Distributional Shifts

Robust Multivariate Time-Series Forecasting: Adversarial Attacks and Defense Mechanisms

Deep Declarative Dynamic Time Warping for End-to-End Learning of Alignment Paths

AAAI 2023

Spatio-Temporal Graph Neural Point Process for Traffic Congestion Event Prediction

Causal Conditional Hidden Markov Model for Multimodal Traffic Prediction

Automated Spatio-Temporal Multi-Task Learning

Learning Decomposed Spatial Relations for Multi-Variate Time-Series Modeling

Scalable Spatiotemporal Graph Neural Networks

Unifying Electricity Forecasting with Robust, Flexible, and Explainable Machine Learning Algorithms

Easy Begun Is Half Done: Spatial-Temporal Graph Modeling with ST-Curriculum Dropout

Spatio-Temporal Neural Structural Causal Models for Bike Flow Prediction

Spatio-Temporal Self-Supervised Learning for Traffic Flow Prediction

WaveForM: Graph Enhanced Wavelet Learning for Long Sequence Forecasting of Multivariate Time Series

Temporal-Frequency Co-Training for Time Series Semi-Supervised Learning

SEnsor Alignment for Multivariate Time-Series Unsupervised Domain Adaptation

Forecasting with Sparse but Informative Variables: A Case Study in Predicting Blood Glucose

Causal Recurrent Variational Autoencoder for Medical Time Series Generation

AEC-GAN: Adversarial Error Correction GANs for Auto-Regressive Long Time-series Generation

An Extreme-Adaptive Time Series Prediction Model Based on Probability-Enhanced LSTM Neural Networks

Are Transformers Effective for Time Series Forecasting?

Supervised Contrastive Few-shot Learning for High-frequency Time Series

Hierarchical Contrastive Learning for Temporal Point Processes

Self-Supervised Learning for Anomalous Channel Detection in EEG Graphs: Application to Seizure Analysis

SVP-T: A Shape-Level Variable-Position Transformer for Multivariate Time Series Classification

Dish-TS: A General Paradigm for Alleviating Distribution Shift in Time Series Forecasting

Spatio-Temporal Meta-Graph Learning for Traffic Forecasting

WSiP: Wave Superposition Inspired Pooling for Dynamic Interactions-Aware Trajectory Prediction

PEN: Prediction-Explanation Network to Forecast Stock Price Movement with Better Explainability

N-HiTS: Neural Hierarchical Interpolation for Time Series Forecasting

Detecting Multivariate Time Series Anomalies with Zero Known Label

Learning Dynamic Temporal Relations with Continuous Graph for Multivariate Time Series Forecasting

DyCVAE: Learning Dynamic Causal Factors for Non-stationary Series Domain Generalization

InParformer: Evolutionary Decomposition Transformers with Interactive Parallel Attention for Long-Term Time Series Forecasting

SLOTH: Structured Learning and Task-based Optimization for Time Series Forecasting on Hierarchies

Estimating Treatment Effects from Irregular Time Series Observations with Hidden Confounders

PrimeNet: Pre-Training for Irregular Multivariate Time Series

Time Series Contrastive Learning with Information-Aware Augmentations

Black-box Adversarial Attack on Time Series Classification

WSDM 2023

A Multi-graph Fusion Based Spatiotemporal Dynamic Learning Framework

Telecommunication Traffic Forecasting via Multi-task Learning

Adversarial Autoencoder for Unsupervised Time Series Anomaly Detection and Interpretation

Ask “Who”, Not “What”: Bitcoin Volatility Forecasting with Twitter Data

DIGMN: Dynamic Intent Guided Meta Network for Differentiated User Engagement Forecasting in Online Professional Social Platforms

Efficient Integration of Multi-Order Dynamics and Internal Dynamics in Stock Movement Prediction

2022

ICDM 2022

Matrix Profile XXV: Introducing Novelets: A Primitive that Allows Online Detection of Emerging Behaviors in Time Series

Neuro-symbolic Models for Interpretable Time Series Classification using Temporal Logic Description

Class-Specific Explainability for Deep Time Series Classifiers

Matrix Profile XXVI: Mplots: Scaling Time Series Similarity Matrices to Massive Data

Robust Time Series Chain Discovery with Incremental Nearest Neighbors

Self-explaining Hierarchical Model for Intraoperative Time Series

MRM2: Multi-Relationship Modeling Module for Multivariate Time Series Classification

Temporal Knowledge Graph Reasoning via Time- Distributed Representation Learning

Text-enhanced Multi-Granularity Temporal Graph Learning for Event Prediction

Mest-GAN: Cross-City Urban Traffic Estimation with Meta Spatial-Temporal Generative Adversarial Network

STORM-GAN: Spatio-Temporal Meta-GAN for Cross-City Estimation of Human Mobility Responses to COVID-19

Spatiotemporal Contextual Consistency Network for Precipitation Nowcasting

CIKM 2022

AutoForecast: Automatic Time-Series Forecasting Model Selection

Deep Extreme Mixture Model for Time Series Forecasting

MARINA: An MLP-Attention Model for Multivariate Time-Series Analysis

Stop&Hop: Early Classification of Irregular Time Series

TFAD: A Decomposition Time Series Anomaly Detection Architecture with Time-Freq Analysis

Domain Adversarial Spatial-Temporal Network: A Transferable Framework for Short-term Traffic Forecasting across Cities

Residual Correction in Real-Time Traffic Forecasting

Bridging Self-Attention and Time Series Decomposition for Periodic Forecasting

NeurIPS 2022

Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistency

Causal Disentanglement for Time Series

BILCO: An Efficient Algorithm for Joint Alignment of Time Series

Non-stationary Transformers: Rethinking the Stationarity in Time Series Forecasting

GT-GAN: General Purpose Time Series Synthesis with Generative Adversarial Networks

Generative Time Series Forecasting with Diffusion, Denoise and Disentanglement

Efficient learning of nonlinear prediction models with time-series privileged information

Time Dimension Dances with Simplicial Complexes: Zigzag Filtration Curve based Supra-Hodge Convolution Networks for Time-series Forecasting

WaveBound: Dynamically Bounding Error for Stable Time Series Forecasting

SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction

FiLM: Frequency improved Legendre Memory Model for Long-term Time Series Forecasting

Dynamic Sparse Network for Time Series Classification: Learning What to “See”

Learning Latent Seasonal-Trend Representations for Time Series Forecasting

Multivariate Time-Series Forecasting with Temporal Polynomial Graph Neural Networks

Earthformer: Exploring Space-Time Transformers for Earth System Forecasting

C2FAR: Coarse-to-Fine Autoregressive Networks for Precise Probabilistic Forecasting

Meta-Learning Dynamics Forecasting Using Task Inference

AutoST: Towards the Universal Modeling of Spatio-temporal Sequences

KDD 2022

Learning the Evolutionary and Multi-scale Graph Structure for Multivariate Time Series Forecasting

Task-Aware Reconstruction for Time-Series Transformer

Multi-Variate Time Series Forecasting on Variable Subsets

ProActive: Self-Attentive Temporal Point Process Flows for Activity Sequences

MSDR: Multi-Step Dependency Relation Networks for Spatial Temporal Forecasting

Mining Spatio-Temporal Relations via Self-Paced Graph Contrastive Learning

Beyond Point Prediction: Capturing Zero-Inflated & Heavy-Tailed Spatiotemporal Data with Deep Extreme Mixture Models

Scaling Time Series Anomaly Detection to Trillions of Datapoints and Ultra-fast Arriving Data Streams

Local Evaluation of Time Series Anomaly Detection Algorithms

Learning to Rotate: Quaternion Transformer for Complicated Periodical Time Series Forecasting

Learning Differential Operators for Interpretable Time Series Modeling

Non-stationary Time-aware Kernelized Attention for Temporal Event Prediction

Pre-training Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series Forecasting

Scaling Time Series Anomaly Detection to Trillions of Datapoints and Ultra-fast Arriving Data Streams

Robust Event Forecasting with Spatiotemporal Confounder Learning

Spatio-Temporal Graph Few-Shot Learning with Cross-City Knowledge Transfer

Spatio-Temporal Trajectory Similarity Learning in Road Networks

Selective Cross-city Transfer Learning for Traffic Prediction via Source City Region Re-weighting

MetaPTP: An Adaptive Meta-optimized Model for Personalized Spatial Trajectory Prediction

Human mobility prediction with causal and spatial-constrained multi-task network

ICML 2022

Closed-Form Diffeomorphic Transformations for Time Series Alignment

FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting

Deep Variational Graph Convolutional Recurrent Network for Multivariate Time Series Anomaly Detection

Learning of Cluster-based Feature Importance for Electronic Health Record Time-series

Modeling Irregular Time Series with Continuous Recurrent Units

Domain Adaptation for Time Series Forecasting via Attention Sharing

Utilizing Expert Features for Contrastive Learning of Time-Series Representations

Reconstructing nonlinear dynamical systems from multi-modal time series

Adaptive Conformal Predictions for Time Series

TACTiS: Transformer-Attentional Copulas for Time Series

Unsupervised Time-Series Representation Learning with Iterative Bilinear Temporal-Spectral Fusion

DSTAGNN: Dynamic Spatial-Temporal Aware Graph Neural Network for Traffic Flow Forecasting

The Transfo-k-mer: protein fitness prediction with auto-regressive transformers and inference-time retrieval

IJCAI 2022

Triformer: Triangular, Variable-Specific Attentions for Long Sequence Multivariate Time Series Forecasting

GRELEN: Multivariate Time Series Anomaly Detection from the Perspective of Graph Relational Learning

T-SMOTE: Temporal-oriented Synthetic Minority Oversampling Technique for Imbalanced Time Series Classification

Neural Contextual Anomaly Detection for Time Series

Memory Augmented State Space Model for Time Series Forecasting

DeepExtrema: A Deep Learning Approach for Forecasting Block Maxima in Time Series Data

A Reinforcement Learning-Informed Pattern Mining Framework for Multivariate Time Series Classification

Regularized Graph Structure Learning with Semantic Knowledge for Multi-variates Time-Series Forecasting

Long-term Spatio-Temporal Forecasting via Dynamic Multiple-Graph Attention

When Transfer Learning Meets Cross-City Urban Flow Prediction: Spatio-Temporal Adaptation Matters

Physics-Informed Long-Sequence Forecasting From Multi-Resolution Spatiotemporal Data

FOGS: First-Order Gradient Supervision with Learning-based Graph for Traffic Flow Forecasting

WWW 2022

Knowledge Enhanced GAN for IoT Traffic Generation

Multi-Granularity Residual Learning with Confidence Estimation for Time Series Prediction

CAMul: Calibrated and Accurate Multi-view Time-Series Forecasting

EXIT: Extrapolation and Interpolation-based Neural Controlled Differential Equations for Time-series Classification and Forecasting

SDM 2022

Error-Bounded Approximate Time Series Joins Using Compact Dictionary Representations of Time Series

Learning Time-Series Shapelets Enhancing Discriminability

Towards Similarity-Aware Time-Series Classification

Joint Time Series Chain: Detecting Unusual Evolving Trend Across Time Series

Ib-Gan: A Unified Approach for Multivariate Time Series Classification under Class Imbalance

Collaborative Attention Mechanism for Multi-Modal Time Series Classification

Leveraging Dependencies among Learned Temporal Subsequences

Measuring Disentangled Generative Spatio-Temporal Representation

ICASSP 2022

Attentional Gated Res2Net for Multivariate Time Series Classification

Bayesian Continual Imputation and Prediction for Irregularly Sampled Time Series Data

CDX-Net: Cross-Domain Multi-Feature Fusion Modeling via Deep Neural Networks for Multivariate Time Series Forecasting in AIOps

Convex Clustering for Autocorrelated Time Series

Graph Learning from Multivariate Dependent Time Series via a Multi-Attribute Formulation

Multiple Temporal Context Embedding Networks for Unsupervised Time Series Anomaly Detection

On Mini-Batch Training with Varying Length Time Series

Sparse-Group Log-Sum Penalized Graphical Model Learning For Time Series

STGAT-MAD : Spatial-Temporal Graph Attention Network for Multivariate Time Series Anomaly Detection

AISTATS 2022

Robust Probabilistic Time Series Forecasting

Deep Generative model with Hierarchical Latent Factors for Time Series Anomaly Detection

LIMESegment: Meaningful, Realistic Time Series Explanations

Using time-series privileged information for provably efficient learning of prediction models

Learning Quantile Functions without Quantile Crossing for Distribution-free Time Series Forecasting

Decoupling Local and Global Representations of Time Series

Amortised Likelihood-free Inference for Expensive Time-series Simulators with Signatured Ratio Estimation

Increasing the accuracy and resolution of precipitation forecasts using deep generative models

Multivariate Quantile Function Forecaster

ICLR 2022

Pyraformer: Low-Complexity Pyramidal Attention for Long-Range Time Series Modeling and Forecasting

Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy

Graph-Augmented Normalizing Flows for Anomaly Detection of Multiple Time Series

DEPTS: Deep Expansion Learning for Periodic Time Series Forecasting

TAMP-S2GCNets: Coupling Time-Aware Multipersistence Knowledge Representation with Spatio-Supra Graph Convolutional Networks for Time-Series Forecasting

PSA-GAN: Progressive Self Attention GANs for Synthetic Time Series

Coherence-based Label Propagation over Time Series for Accelerated Active Learning

Huber Additive Models for Non-stationary Time Series Analysis

Reversible Instance Normalization for Accurate Time-Series Forecasting against Distribution Shift

CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecasting

Guided Network for Irregularly Sampled Multivariate Time Series

Heteroscedastic Temporal Variational Autoencoder For Irregularly Sampled Time Series

Omni-Scale CNNs: a simple and effective kernel size configuration for time series classification

Filling the G_ap_s: Multivariate Time Series Imputation by Graph Neural Networks

T-WaveNet: A Tree-Structured Wavelet Neural Network for Time Series Signal Analysis

Temporal Alignment Prediction for Supervised Representation Learning and Few-Shot Sequence Classification

Learning to Remember Patterns: Pattern Matching Memory Networks for Traffic Forecasting

On the benefits of maximum likelihood estimation for Regression and Forecasting

Back2Future: Leveraging Backfill Dynamics for Improving Real-time Predictions in Future

UniFormer: Unified Transformer for Efficient Spatial-Temporal Representation Learning

AAAI 2022

Towards a Rigorous Evaluation of Time-Series Anomaly Detection

Training Robust Deep Models for Time-Series Domain: Novel Algorithms and Theoretical Analysis

CATN: Cross Attentive Tree-Aware Network for Multivariate Time Series Forecasting

Reinforcement Learning based Dynamic Model Combination for Time Series Forecasting

TS2Vec: Towards Universal Representation of Time Series

I-SEA: Importance Sampling and Expected Alignment-Based Deep Distance Metric Learning for Time Series Analysis and Embedding

Clustering Interval-Censored Time-Series for Disease Phenotyping

Conditional Loss and Deep Euler Scheme for Time Series Generation

Conditional Local Convolution for Spatio-Temporal Meteorological Forecasting

Learning and Dynamical Models for Sub-Seasonal Climate Forecasting: Comparison and Collaboration

Graph Neural Controlled Differential Equations for Traffic Forecasting

Dynamic Manifold Learning for Land Deformation Forecasting

HAGEN: Homophily-Aware Graph Convolutional Recurrent Network for Crime Forecasting

PrEF: Probabilistic Electricity Forecasting via Copula-Augmented State Space Model

LIMREF: Local Interpretable Model Agnostic Rule-Based Explanations for Forecasting, with an Application to Electricity Smart Meter Data

NumHTML: Numeric-Oriented Hierarchical Transformer Model for Multi-Task Financial Forecasting

CausalGNN: Causal-Based Graph Neural Networks for Spatio-Temporal Epidemic Forecasting

AGNN-RNNApproach for Harnessing Geospatial and Temporal Information: Application to Crop Yield Prediction

SPATE-GAN: Improved Generative Modeling of Dynamic Spatio-Temporal Patterns with an Autoregressive Embedding Loss

Feature Importance Explanations for Temporal Black-Box Models

MuMu:Cooperative Multitask Learning-based Guided Multimodal Fusion

WSDM 2022

ESC-GAN: Extending Spatial Coverage of Physical Sensors

ST-GSP: Spatial-Temporal Global Semantic Representation Learning for Urban Flow Prediction

Translating Human Mobility Forecasting through Natural Language Generation

A New Class of Polynomial Activation Functions of Deep Learning for Precipitation Forecasting

CMT-Net: A Mutual Transition Aware Framework for Taxicab Pick-ups and Drop-offs Co-Prediction

Predicting Human Mobility via Graph Convolutional Dual-attentive Networks

RLMob: Deep Reinforcement Learning for Successive Mobility Prediction

2021

ICDM 2021

Towards Interpretability and Personalization: A Predictive Framework for Clinical Time-series Analysis

Towards Generating Real-World Time Series Data

Continual Learning for Multivariate Time Series Tasks with Variable Input Dimensions

CASPITA: Mining Statistically Significant Paths in Time Series Data from an Unknown Network

Multi-way Time Series Join on Multi-length Patterns

Ultra fast warping window optimization for Dynamic Time Warping

Disentangled Deep Multivariate Hawkes Process for Learning Event Sequences

Attentive Neural Controlled Differential Equations for Time-series Classification and Forecasting

SSDNet: State Space Decomposition Neural Network for Time Series Forecasting

Space Meets Time: Local Spacetime Neural Network For Traffic Flow Forecasting

DAC-ML: Domain Adaptable Continuous Meta-Learning for Urban Dynamics Prediction

Sequential Diagnosis Prediction with Transformer and Ontological Representation

Partial Differential Equation Driven Dynamic Graph Networks for Predicting Stream Water Temperature

Label Dependent Attention Model for Disease Risk Prediction Using Multimodal Electronic Health Records

SCEHR: Supervised Contrastive Learning for Clinical Risk Predictions with Electronic Health Records

LIFE: Learning Individual Features for Multivariate Time Series Prediction with Missing Values

MERITS: Medication Recommendation for Chronic Disease with Irregular Time-Series

PIETS: Parallelised Irregularity Encoders for Forecasting with Heterogeneous Time-Series

Matrix Profile XXIII: Contrast Profile: A Novel Time Series Primitive that Allows Real World Classification

LOGIC: Probabilistic Machine Learning for Time Series Classification

SMATE: Semi-Supervised Spatio-Temporal Representation Learning on Multivariate Time Series

STING: Self-attention based Time-series Imputation Networks using GAN

Spikelet: An Adaptive Symbolic Approximation for Finding Higher-Level Structure in Time Series

Streaming Dynamic Graph Neural Networks for Continuous-Time Temporal Graph Modeling

TCube: Domain-Agnostic Neural Time-series Narration

TEST-GCN: Topologically Enhanced Spatial-Temporal Graph Convolutional Networks for Traffic Forecasting

CIKM 2021

ClaSP - Time Series Segmentation

Learning to Learn the Future: Modeling Concept Drifts in Time Series Prediction

AdaRNN: Adaptive Learning and Forecasting of Time Series

Learning Saliency Maps to Explain Deep Time Series Classifiers

Actionable Insights in Urban Multivariate Time-series

Integrating Static and Time-Series Data in Deep Recurrent Models for Oncology Early Warning Systems

Hierarchical Semantics Matching For Heterogeneous Spatio-temporal Sources

HASTE: A Distributed System for Hybrid and Adaptive Processing on Streaming Spatial-Textual Data

Spatio-Temporal-Categorical Graph Neural Networks for Fine-Grained Multi-Incident Co-Prediction

Spatio-Temporal-Social Multi-Feature-based Fine-Grained Hot Spots Prediction for Content Delivery Services in 5G Era

Into the Unobservables: A Multi-range Encoder-decoder Framework for COVID-19 Prediction

What is Next when Sequential Prediction Meets Implicitly Hard Interaction?

Stock Trend Prediction with Multi-granularity Data: A Contrastive Learning Approach with Adaptive Fusion

NeurIPS 2021

Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting

Dynamical Wasserstein Barycenters for Time-series Modeling

CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation

Conformal Time-series Forecasting

Coresets for Time Series Clustering

MixSeq: Connecting Macroscopic Time Series Forecasting with Microscopic Time Series Data

Adjusting for Autocorrelated Errors in Neural Networks for Time Series

Deep Explicit Duration Switching Models for Time Series

Online false discovery rate control for anomaly detection in time series

Topological Attention for Time Series Forecasting

Time-series Generation by Contrastive Imitation

Probabilistic Transformer For Time Series Analysis

Spatial-Temporal Super-Resolution of Satellite Imagery via Conditional Pixel Synthesis

KDD 2021

MiniRocket: A Fast (Almost) Deterministic Transform for Time Series Classification

Deep Learning Embeddings for Data Series Similarity Search

Fast and Accurate Partial Fourier Transform for Time Series Data

Representation Learning of Multivariate Time Series using a Transformer Framework

ST-Norm: Spatial and Temporal Normalization for Multi-variate Time Series Forecasting

Statistical models coupling allows for complex localmultivariate time series analysis

Cross-Node Federated Graph Neural Network for Spatio-Temporal Data Modeling

Dynamic and Multi-faceted Spatio-temporal Deep Learning for Traffic Speed Forecasting

Quantifying Uncertainty in Deep Spatiotemporal Forecasting

Spatial-Temporal Graph ODE Networks for Traffic Flow Forecasting

Weakly Supervised Spatial Deep Learning based on Imperfect Training Labels with Location Errors

A PLAN for Tackling the Locust Crisis in East Africa: Harnessing Spatiotemporal Deep Models for Locust Movement Forecasting

Graph Deep Factor Model for Cloud Utilization Forecasting

JOHAN: A Joint Online Hurricane Trajectory and Intensity Forecasting Framework

Accurate Multivariate Stock Movement Prediction via Data-Axis Transformer with Multi-Level Contexts

Attentive Heterogeneous Graph Embedding for Job Mobility Prediction

TrajNet: A Trajectory-Based Deep Learning Model for Traffic Prediction

ICML 2021

End-to-End Learning of Coherent Probabilistic Forecasts for Hierarchical Time Series

Neural Rough Differential Equations for Long Time Series

Voice2Series: Reprogramming Acoustic Models for Time Series Classification

Whittle Networks: A Deep Likelihood Model for Time Series

Necessary and sufficient conditions for causal feature selection in time series with latent common causes

Explaining Time Series Predictions with Dynamic Masks

Z-GCNETs: Time Zigzags at Graph Convolutional Networks for Time Series Forecasting

Conformal prediction interval for dynamic time-series

Approximation Theory of Convolutional Architectures for Time Series Modelling

RNN with Particle Flow for Probabilistic Spatio-temporal Forecasting

Variance Reduced Training with Stratified Sampling for Forecasting Models

Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecasting

A Structured Observation Distribution for Generative Biological Sequence Prediction and Forecasting

Principled Simplicial Neural Networks for Trajectory Prediction

IJCAI 2021

TE-ESN: Time Encoding Echo State Network for Prediction Based on Irregularly Sampled Time Series Data

Time-Aware Multi-Scale RNNs for Time Series Modeling

Time-Series Representation Learning via Temporal and Contextual Contrasting

Adversarial Spectral Kernel Matching for Unsupervised Time Series Domain Adaptation

Two Birds with One Stone: Series Saliency for Accurate and Interpretable Multivariate Time Series Forecasting

Multi-series Time-aware Sequence Partitioning for Disease Progression Modeling

Multi-version Tensor Completion for Time-delayed Spatio-temporal Data

Physics-aware Spatiotemporal Modules with Auxiliary Tasks for Meta-Learning

Hierarchical Adaptive Temporal-Relational Modeling for Stock Trend Prediction

Residential Electric Load Forecasting via Attentive Transfer of Graph Neural Networks

TrafficStream: A Streaming Traffic Flow Forecasting Framework Based on Graph Neural Networks and Continual Learning

Multimodal Transformer Networks for Pedestrian Trajectory Prediction

Cooperative Joint Attentive Network for Patient Outcome Prediction on Irregular Multi-Rate Multivariate Health Data

WWW 2021

DeepFEC: Energy Consumption Prediction under Real-World Driving Conditions for Smart Cities

HINTS: Citation Time Series Prediction for New Publications viaDynamic Heterogeneous Information Network Embedding

Network of Tensor Time Series

Radflow: A Recurrent, Aggregated, and Decomposable Model for Networks of Time Series

REST: Reciprocal Framework for Spatiotemporal coupled predictions

SDFVAE: Static and Dynamic Factorized VAE for Anomaly Detection of Multivariate CDN KPIs

SRVAR: Joint Discrete Hidden State Discovery and Structure Learning from Time Series Data

Time-series Change Point Detection with Self-Supervised Contrastive Predictive Coding

STUaNet: Understanding uncertainty in spatiotemporal collective human mobility

SDM 2021

Learning Time-series Shapelets via Supervised Feature Selection

Robust Dual Recurrent Neural Networks for Financial Time Series Prediction

Attention-Based Autoregression for Accurate and Efficient Multivariate Time Series Forecasting

UNIANO: robust and efficient anomaly consensus in time series sensitive to cross-correlated anomaly profiles

Inter-Series Attention Model for COVID-19 Forecasting

Stochastic Time Series Representation for Interval Pattern Mining via Gaussian Processes

Hypa: Efficient Detection of Path Anomalies in Time Series Data on Networks

Filling Missing Values on Wearable-Sensory Time Series Data

Lag-Aware Multivariate Time-Series Segmentation

Learning Time-series Shapelets for Optimizing Partial AUC

A Fine-grained Graph-based Spatiotemporal Network for Bike Flow Prediction in Bike-sharing Systems

Semantic Discord: Finding Unusual Local Patterns for Time Series

MT-STNets: Multi-Task Spatial-Temporal Networks for Multi-Scale Traffic Prediction

ICASSP 2021

GDTW: A Novel Differentiable DTW Loss for Time Series Tasks

Recursive Input and State Estimation: A General Framework for Learning from Time Series with Missing Data

Semi-supervised Time Series Classification by Temporal Relation Prediction

Spatiotemporal Attention for Multivariate Time Series Prediction and Interpretation

Tabular Transformers for Modeling Multivariate Time Series

Two-Stage Framework for Seasonal Time Series Forecasting

AISTATS 2021

Simultaneously Reconciled Quantile Forecasting of Hierarchically Related Time Series

Aligning Time Series on Incomparable Spaces

Differentiable Divergences Between Time Series

ICLR 2021

Multi-Time Attention Networks for Irregularly Sampled Time Series

Unsupervised Representation Learning for Time Series with Temporal Neighborhood Coding

Multivariate Probabilistic Time Series Forecasting via Conditioned Normalizing Flows

Generative Time-series Modeling with Fourier Flows

Discrete Graph Structure Learning for Forecasting Multiple Time Series

Clairvoyance: A Pipeline Toolkit for Medical Time Series

HalentNet: Multimodal Trajectory Forecasting with Hallucinative Intents

Augmenting Physical Models with Deep Networks for Complex Dynamics Forecasting

Trajectory Prediction using Equivariant Continuous Convolution

AAAI 2021

Meta-Learning Framework with Applications to Zero-Shot Time-Series Forecasting

Deep Switching Auto-Regressive Factorization: Application to Time Series Forecasting

Dynamic Gaussian Mixture Based Deep Generative Model for Robust Forecasting on Sparse Multivariate Time Series

Second Order Techniques for Learning Time-Series with Structural Breaks

Correlative Channel-Aware Fusion for Multi-View Time Series Classification

Learnable Dynamic Temporal Pooling for Time Series Classification

Time Series Domain Adaptation via Sparse Associative Structure Alignment

Learning Representations for Incomplete Time Series Clustering

Temporal Latent Autoencoder: A Method for Probabilistic Multivariate Time Series Forecasting

Graph Neural Network-Based Anomaly Detection in Multivariate Time Series

ShapeNet: A Shapelet-Neural Network Approach for Multivariate Time Series Classification

Time Series Anomaly Detection with Multiresolution Ensemble Decoding

Joint-Label Learning by Dual Augmentation for Time Series Classification

Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting

Generative Semi-Supervised Learning for Multivariate Time Series Imputation

Outlier Impact Characterization for Time Series Data

Robust Spatio-Temporal Purchase Prediction via Deep Meta Learning

Sub-Seasonal Climate Forecasting via Machine Learning: Challenges, Analysis, and Advances

A Multi-Step-Ahead Markov Conditional Forward Model with Cube Perturbations for Extreme Weather Forecasting

WSDM 2021

Time-Series Event Prediction with Evolutionary State Graph

Modeling Inter-station Relationships with Attentive Temporal Graph Convolutional Network for Air Quality Prediction

Explainable Multivariate Time Series Classification: A Deep Neural Network Which Learns To Attend To Important Variables As Well As Time Intervals

FluxEV: A Fast and Effective Unsupervised Framework for Time-Series Anomaly Detection

Predicting Crowd Flows via Pyramid Dilated Deeper Spatial-temporal Network