Research map / Federated learning and privacy / Communication-efficient FL
Toward Understanding the Influence of Individual 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 Fed-Influence estimates to identify and remove least-valuable clients | FedAvg · Synthetic, Setting 1; remove 30% of clients at round 700 | accuracy: 53.86% -> 55.66% | Helped |
| Use Fed-Influence estimates to identify and remove least-valuable clients | FedAvg · FEMNIST, Setting 3; remove 5% of clients at round 1500 | accuracy: 76.10% -> 76.50% | Helped |
| Add layer-wise examination and truncation (LWET) (ablation) | Basic Fed-Influence estimator · FEMNIST, Setting 2 | FIP estimation error | Helped |
| Approximate the Hessian rather than computing the exact Hessian (ablation) | Fed-Influence estimator · FEMNIST, Setting 2 | FIP estimation error | Hurt |
| Use LWET instead of the basic estimator (ablation) | Fed-Influence estimator · Synthetic, Setting 1 | FIP estimate | No clear effect |
| Remove clients with high FIL or low FIA | Federated training · Synthetic, Setting 1 and FEMNIST, Setting 3 | final model performance | Hurt |
Closest papers by meaning
- FedImpro: Measuring and Improving Client Update in Federated Learning (ICLR 2024 · similarity 0.88)
- Federated Learning under Periodic Client Participation and Heterogeneous Data: A New Communication-Efficient Algorithm and Analysis (NeurIPS 2024 · similarity 0.87)
- FLUX: Efficient Descriptor-Driven Clustered Federated Learning under Arbitrary Distribution Shifts (NeurIPS 2025 · similarity 0.86)
- Federated Learning with Sample-level Client Drift Mitigation (AAAI 2025 · similarity 0.86)
- A Bayesian Approach for Personalized Federated Learning in Heterogeneous Settings (NeurIPS 2024 · similarity 0.86)
- Heterogeneity-Guided Client Sampling: Towards Fast and Efficient Non-IID Federated Learning (NeurIPS 2024 · similarity 0.86)
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.