Research map / Federated learning and privacy / Communication-efficient FL
Game of Gradients: Mitigating Irrelevant Clients in Federated Learning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use Shapley-value-based client selection instead of random client selection | S-FedAvg · MNIST irrelevant data setting (6 relevant, 4 irrelevant clients) | test accuracy | Helped |
| Select clients using Shapley-based relevance scores | S-FedAvg · MNIST irrelevant data setting | client relevance score | Helped |
| Use class-specific validation data to compute client relevance | S-FedAvg class-specific client selection · MNIST class 2 | client relevance score | Helped |
| Add client-side label permutation detection and correction | S-FedAvg-Label-Std · MNIST irrelevant data setting with a corrupted client | test performance | Helped |
| Include updates from irrelevant clients in aggregation | FedAvg · MNIST with 6 relevant and 4 irrelevant clients | model stability | Hurt |
Closest papers by meaning
- Heterogeneity-Guided Client Sampling: Towards Fast and Efficient Non-IID Federated Learning (NeurIPS 2024 · similarity 0.88)
- Ranking-based Client Imitation Selection for Efficient Federated Learning (ICML 2024 · similarity 0.87)
- Understanding Server-Assisted Federated Learning in the Presence of Incomplete Client Participation (ICML 2024 · similarity 0.87)
- FedQS: Optimizing Gradient and Model Aggregation for Semi-Asynchronous Federated Learning (NeurIPS 2025 · similarity 0.87)
- (FL)$^2$: Overcoming Few Labels in Federated Semi-Supervised Learning (NeurIPS 2024 · similarity 0.87)
- FedCS: Coreset Selection for Federated Learning (CVPR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.