Research map / Federated learning and privacy / Communication-efficient FL
Analysis of Error Feedback in Federated Non-Convex Optimization with Biased Compression: Fast Convergence and Partial Participation
Xiaoyun Li, Ping Li
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| Add error feedback to Fed-EF-SGD (Sign/TopK/Heavy-Sign compressors) | Fed-SGD with biased compression · MNIST p=0.5 and p=0.1 | test accuracy (%) | Improved |
| Add error feedback to Fed-EF-AMS on FMNIST at p=0.1 (ablation) | AMSGrad global optimizer with Sign compression · FMNIST p=0.1 | test accuracy (%): 57.60 -> 64.09 | Improved |
| Use TopK compressor instead of sign-based compressors in Fed-EF-AMS | Fed-EF-AMS on FMNIST · FMNIST p=0.1 vs p=0.5 | test accuracy (%): TopK 50.77 vs Sign 64.09 at p=0.1; TopK 70.73 vs Sign 71.90 at p=0.5 | Mixed |
| Use Sign compressor with Fed-EF-AMS instead of full precision (p=0.5, MNIST) | Fed-EF-AMS · MNIST p=0.5 | test accuracy (%): 92.74 vs 92.23 | No clear effect |
| Use unbiased stochastic quantization without EF instead of Fed-EF-SGD with heavy-Sign | Fed-SGD communication compression · MNIST p=0.5 | test accuracy (%): 90.85 vs 90.16 (Hv-Sign) | Hurt |
| Error restarting (reset error accumulator if stale for S=10 rounds) under partial participation (ablation) | Fed-EF under PP with TopK-0.01 · MNIST and FMNIST p=0.1, logistic regression and MLP | squared gradient norm | Improved |
| Increase participation from m=20 to m=100 vs increase n under full participation | Fed-EF-SGD convergence · MNIST MLP | squared gradient norm | Improved |
| Partial participation (p=0.1) instead of p=0.5 in Fed-EF-SGD | Fed-EF-SGD · MNIST and FMNIST | test accuracy (%): MNIST full-precision 90.87 (p=0.5) vs 90.15 (p=0.1); FMNIST 71.20 vs 67.50 | Hurt |
Closest papers by meaning
- EFSkip: A New Error Feedback with Linear Speedup for Compressed Federated Learning with Arbitrary Data Heterogeneity (AAAI 2025 · similarity 0.93)
- Safe-EF: Error Feedback for Non-smooth Constrained Optimization (ICML 2025 · similarity 0.90)
- Tight analyses of first-order methods with error feedback (NeurIPS 2025 · similarity 0.89)
- Stochastic Controlled Averaging for Federated Learning with Communication Compression (ICLR 2024 · similarity 0.89)
- Federated Optimization with Doubly Regularized Drift Correction (ICML 2024 · similarity 0.88)
- Accelerated Methods with Compressed Communications for Distributed Optimization Problems Under Data Similarity (AAAI 2025 · similarity 0.88)
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.
