Home

Awesome

Federated Learning with New Knowledge

This is all you need for a brand new but quite important topic -- Federated Learning with New Knowledge, including research papers, datasets, tools, and you name it. Federated Learning (FL) is a privacy-preserving distributed learning approach that is rapidly developing in an era where privacy protection is increasingly valued. It is this rapid development trend, along with the continuous emergence of new demands for FL in the real world, that prompts us to focus on a very important problem: Federated Learning with New Knowledge. The primary challenge here is to effectively incorporate various new knowledge into existing FL systems and evolve these systems to reduce costs, extend their lifespan, and facilitate sustainable development. In this work, we systematically define the main sources of new knowledge in FL, including new features, tasks, models, and algorithms. For each source, we thoroughly analyze and discuss how to incorporate new knowledge into existing FL systems and examine the impact of the form and timing of new knowledge arrival on the incorporation process. Furthermore, we comprehensively discuss the potential future directions for FL with new knowledge, considering a variety of factors such as scenario setups, efficiency, and security. For more detailed information, please refer to our survey paper Federated Learning with New Knowledge: Fundamentals, Advances, and Futures.

overview

Overview of an FL system with new knowledge from different sources. Different types of clients encounter new features and tasks over time, which reflect new demands for FL systems, e.g., client $C_{k_2}$ needs to deal with the night scenes and conduct segmentation when snowing, and client $C_{k_3}$ joins FL with the need to handle night scenes and deraining when raining. From a global view, new more advanced models with better architecture (Transformers) and larger sizes (GPT 4) are also needed to incorporate. Besides, new algorithms with better performance (Scaffold) and security guarantees (SecAgg) should be continuously employed in FL as well.

Taxonomy

New Features

Federated Domain Generalization

Federated Out-of-Distribution Detection

Federated Domain Adaptation

New Tasks

Task-personalized Federated Learning

Self-supervised Federated Learning

New Tasks with New Features

New Models

New Algorithms

<a name="computer-vision" />

Computer Vision

<a name="pure-classification" />

Pure Classification

<a name="advanced-cv-tasks" />

Advanced CV Tasks (object detection, semantic segmentation)

<a name="ood-learning" />

Out-of-Distribution Learning (domain adaptation, domain generalization, out-of-distribution detection)

<a name="nlp" />

Natural Language Processing

<a name="iot" />

Audio and IoT

<a name="security" />

Security Relevant

<a name="other" />

Other Topics

Citation

If you find our survey helpful for your research and study, please consider citing our paper.

@inproceedings{Wang2024FederatedLW,
  title={Federated Learning with New Knowledge: Fundamentals, Advances, and Futures},
  author={Lixu Wang and Yang Zhao and Jiahua Dong and Ating Yin and Qinbin Li and Xiao Wang and Dusit Tao Niyato and Qi Zhu},
  year={2024},
  url={https://api.semanticscholar.org/CorpusID:267412120}
}