youngfish42/Awesome-FL

Comprehensive and timely academic information on federated learning (papers, frameworks, datasets, tutorials, workshops)

What it is

A curated, hand-maintained list of resources about federated learning — a machine-learning technique where models are trained across multiple devices or servers without moving the raw data to a central place. The project collects papers, software frameworks, datasets, surveys, tutorials, and academic events related to this field.

What's inside

Papers — the bulk of the list. They're grouped by the venue where they were published (e.g., NeurIPS, ICML, CVPR, ACL, KDD) and by research area (AI, machine learning, data mining, security, computer vision, NLP, information retrieval, databases, networking, systems, and others). Each venue has links to accepted-paper lists for recent years (roughly 2020–2025).
Special paper topics — dedicated sections for federated learning applied to graph data / graph neural networks and to tabular data (e.g., tree-based models like XGBoost).
Frameworks — software tools for building federated learning systems.
Datasets — data collections used in federated learning research.
Surveys — overview papers.
Tutorials and courses — learning materials.
Events — workshops, journal special issues, and conference special tracks focused on federated learning.

How it's organized

The README is a table of contents with links. The full content lives on a separate homepage (youngfish42.github.io/Awesome-FL); the README notes that if the page doesn't display everything, readers should visit that site.

Maintenance status (important)

As of September 30, 2024, the main author finished his PhD and shifted research focus. Consequences:

Paper lists will be updated monthly or quarterly instead of regularly.
Updates will be shallower — details like author affiliations and links to open-source code will no longer be actively maintained.
The author invites other contributors to help keep the list current.

How to contribute

Suggest new resources by opening a GitHub issue, submitting a pull request, or emailing the author (im.young@foxmail.com). There's also a QQ group (number 833638275) for discussing federated learning.

Related project

A companion tool, FL-paper-update-tracker, automatically tracks new federated learning papers — useful since the main list is now updated less frequently.

License

MIT (per the badge in the README).