Home

Awesome

Knowledge Graphs and Data Integration in Database Conferences (2020)

You can check the conference prograpm webpages and attend the sessions that you are interested in.

VLDB 2020 [Conference Program, you can listen to the talk of each paper on Youtube or Bilibili]

Researh Papers:

  1. Mining an "Anti-Knowledge Base" from Wikipedia Updates with Applications to Fact Checking and Beyond
  2. KBPearl: A Knowledge Base Population System Supported by Joint Entity and Relation Linking
  3. Knowledge Translation [Technical Report]
  4. A Benchmarking Study of Embedding-based Entity Alignment for Knowledge Graphs
  5. Effective and Efficient Relational Community Detection and Search in Large Dynamic Heterogeneous Information Networks
  6. Obi-Wan: Ontology-Based RDF Integration of Heterogeneous Data
  7. Selecting Data to Clean for Fact Checking: Minimizing Uncertainty vs. Maximizing Surprise

Other Intersting Papers:

  1. Optimizing DNN Computation Graph using Graph Substitutions

Demo Papers:

  1. RDFFrames: Knowledge Graph Access for Machine Learning Tools
  2. SPHINX: A System for Metapath-based Entity Exploration in Heterogeneous Information Networks

Workshops:

  1. Fast Entity Resolution With Mock Labels and Sorted Integer Sets
  2. Entity Resolution on Camera Records without Machine Learning
  3. CheetahER: A Fast Entity Resolution System for Heterogeneous Camera Data
  4. An Extensible Block Scheme-Based Method for Entity Matching
  5. Spread the good around! Information Propagation in Schema Matching and Entity Resolution for Heterogeneous Data
  6. Intermediate Training of BERT for Product Matching
  7. Towards Guaranteeing Global Consistency for Peer-based Data Integration Architecture
  8. Integration of Fast-Evolving Data Sources Using A Deep Learning Approach
  9. Reliable Clustering with Applications to Data Integration

Recommend Sessions (Tokyo time):

  1. W2_3-6 Tuesday, September 1st 2020, 11:00 am - Knowledge Graphs
  2. Day3-Block1 Thursday, September 3rd 2020, 6:00 pm - Knowledge Bases
  3. Day2-Block3 Thursday, September 3rd 2020, 7:00 am - Knowledge Graphs & Hypergraphs
  4. Pre-Conference-Workshop Monday, August 31st 2020, 4:00 pm - DI2KG (1)
  5. Pre-Conference-Workshop Monday, August 31st 2020, 11:00 pm - DI2KG (2) (Same as DI2KG(1))

You can also go to the graph sessions, where a lot of novel graph algorithms (e.g., subgraph seraching) are proposed...

ICDE 2020 [Conference Program, videos and slides avaliable]

Research Papers:

  1. Optimizing Knowledge Graphs through Voting-based User Feedback [Video][Slides][Paper]
  2. AutoSF: Searching Scoring Functions for Knowledge Graph Embedding [Video][Slides][Paper]
  3. Semantic Guided and Response Times Bounded Top-k Similarity Search over Knowledge Graphs [Video][Slides][Paper]
  4. Online Indices for Predictive Top-k Entity and Aggregate Queries on Knowledge Graphs [Video][Slides][Paper]
  5. Sya: Enabling Spatial Awareness inside Probabilistic Knowledge Base Construction [Video][Slides][Paper]
  6. Crowdsourced Collective Entity Resolution with Relational Match Propagation [Video][Slides][Paper]
  7. Improving Neural Relation Extraction with Implicit Mutual Relations [Video][Slides][Paper]
  8. Dataset Discovery in Data Lakes [Video][Slides][Paper]
  9. TransN: Heterogeneous Network Representation Learning by Translating Node Embeddings [Video][Slides][Paper]

Recommened Sessions:

  1. R02: Data Integration and Machine Learning (Tuesday 21st April, 10:00-11:30)
  2. R08: Graph and Social Networks 2 (Tuesday 21st April, 13:30-15:00)
  3. R13: Data Cleaning, Curation and Analytics (Wed 22nd April, 12:00-13:30)
  4. R18: Search and Information Extraction (Wed 22nd April, 14:00-15:30)

SIGMOD 2020 [Conference Program (user account required, you can ask Xin for the account)]

Research Papers:

  1. A Comprehensive Benchmark Framework for Active Learning Methods in Entity Matching [Paper]
  2. ZeroER: Entity Resolution using Zero Labeled Examples [Paper]
  3. Towards Interpretable and Learnable Risk Analysis for Entity Resolution [Paper]
  4. SLIM: Scalable Linkage of Mobility Data [Paper]
  5. Learning Over Dirty Data Without Cleaning [Paper]
  6. Creating Embeddings of Heterogeneous Relational Datasets for Data Integration Tasks [Paper]
  7. SPARQL Rewriting: Towards Desired Results [Paper]
  8. Realistic Re-evaluation of Knowledge Graph Completion Methods: An Experimental Study [Paper]

Demos:

  1. CoClean: Collaborative Data Cleaning [Paper]
  2. T-REx: Table Repair Explanations [Paper]

Tutorials:

  1. State of the Art and Open Challenges in Natural Language Interfaces to Data [PDF], Tuesday 1:30 PM – 3:00 PM
  2. Automating Exploratory Data Analysis via Machine Learning: An Overview [PDF], Thursday 10:30 AM – 12:00 PM

Industries:

  1. AliCoCo: Alibaba E-commerce Cognitive Concept Net [Paper]
  2. An Ontology-Based Conversation System for Knowledge Bases [Paper]
  3. GIANT: Scalable Creation of a Web-scale Ontology [Paper]
  4. Entity Matching in the Wild: a Consistent and Versatile Framework to Unify Data in Industrial Applications [Paper]

Other interesting papers:

  1. Monotonic Cardinality Estimation of Similarity Selection: A Deep Learning Approach [Paper]
  2. Minimization of Classifier Construction Cost for Search Queries [Paper]
  3. Complaint-driven Training Data Debugging for Query 2.0 [Paper]
  4. Densely Connected User Community and Location Cluster Search in Location-Based Social Networks [Paper]
  5. Reliable Data Distillation on Graph Convolutional Network [Paper]
  6. DB4ML – An In-Memory Database Kernel with Machine Learning Support [Paper]
  7. Efficient Algorithms for Densest Subgraph Discovery on Large Directed Graphs [Paper]
  8. Organizing Data Lakes for Navigation [Paper]
  9. Finding Related Tables in Data Lakes for Interactive Data Science [Paper]
  10. Web Data Extraction using Hybrid Program Synthesis: A Combination of Top-down and Bottom-up Inference [Paper]
  11. Cleaning Denial Constraint Violations through Relaxation [Paper]
  12. SCODED: Statistical Constraint Oriented Data Error Detection [Paper]
  13. A Method for Optimizing Opaque Filter Queries [Paper]

Recommened Sessions:

  1. Research 13: Data Matching, Wednesday 10:30 AM – 12:00 PM
  2. Research 15: Machine Learning for Cleaning, Integration, and Search, Wednesday 10:30 AM – 12:00 PM
  3. Research 9: Data Cleaning, Wednesday 4:30 AM – 6:00 PM (I think this should be 4:30PM, the official website has a typo)
  4. Research 22: Data Lakes, Web, and Knowledge Graph, Thursday 10:30 AM – 12:00 PM
  5. Industry 3: Graph Databases and Knowledge Bases, Wednesday 4:30 PM -6:00 PM

KDD 2020 [Videos avaliable (you can ask Professor Chen for the account)]

Research Papers and Applied Data Science Track Papers:

  1. Dynamic Knowledge Graph based Multi-Event Forecasting
  2. Improving Conversational Recommender Systems via Knowledge Graph based Semantic Fusion
  3. Incremental Mobile User Profiling: Reinforcement Learning with Spatial Knowledge Graph for Modeling Event Streams
  4. MultiImport: Inferring Node Importance in a Knowledge Graph from Multiple Input Signals
  5. REA: Robust Cross-lingual Entity Alignment Between Knowledge Graphs
  6. AutoKnow: Self-Driving Knowledge Collection for Products of Thousands of Types (Applied Data Science Track)
  7. Domain Specific Knowledge Graphs as a Service to the Public (Applied Data Science Track)
  8. BOND: Bert-Assisted Open-Domain Named Entity Recognition with Distant Supervision
  9. CoRel: Seed-Guided Topical Taxonomy Construction by Concept Learning and Relation Transferring
  10. Representing Temporal Attributes for Schema Matching
  11. Automatic Validation of Textual Attribute Values in ECommerce Catalog by Learning with Limited Labeled Data (Applied Data Science Track)

VLDBJ 2020

  1. A survey of community search over big graphs
  2. An analytical study of large SPARQL query logs
  3. Snorkel: rapid training data creation with weak supervision
  4. Automatic weighted matching rectifying rule discovery for data repairing
  5. Diversified spatial keyword search on RDF data
  6. RDF graph summarization for first-sight structure discovery [Paper]

TKDE 2020

  1. r-HUMO: A Risk-Aware Human-Machine Cooperation Framework for Entity Resolution with Quality Guarantees
  2. Bayesian Networks for Data Integration in the Absence of Foreign Keys
  3. Efficient Entity Resolution on Heterogeneous Records
  4. Generalized Translation-Based Embedding of Knowledge Graph
  5. Joint Learning of Question Answering and Question Generation