Research map / Federated learning and privacy / Communication-efficient FL
Personalized Federated Learning with Bidirectional Communication Compression via One-Bit Random Sketching
Jiacheng Cheng, Xu Zhang, Guanghui Qiu, Yifang Zhang, Yinchuan Li, Kaiyuan Feng
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 |
|---|---|---|---|
| use pFed1BS instead of full-precision FedAvg | FL baseline · CIFAR-100 | top-1 accuracy (%): 59.60 -> 52.88 | Hurt |
| use pFed1BS instead of full-precision FedAvg | FL baseline · CIFAR-10 | top-1 accuracy (%): 87.78 -> 85.21 | Hurt |
| use pFed1BS instead of full-precision FedAvg | FL baseline · SVHN | top-1 accuracy (%): 96.33 -> 95.07 | Hurt |
| use pFed1BS instead of full-precision FedAvg | FL baseline · FMNIST | top-1 accuracy (%): 84.40 -> 84.15 | No clear effect |
| use pFed1BS instead of full-precision FedAvg | FL baseline · MNIST | top-1 accuracy (%): 97.21 -> 97.83 | Improved |
| use pFed1BS instead of OBDA one-bit baseline | OBDA · CIFAR-100 | top-1 accuracy (%): 42.47 -> 52.88 | Improved |
| use pFed1BS instead of OBDA one-bit baseline | OBDA · CIFAR-10 | top-1 accuracy (%): 73.26 -> 85.21 | Improved |
| use pFed1BS instead of EDEN | EDEN · SVHN | top-1 accuracy (%): 89.01 -> 95.07 | Improved |
| use pFed1BS instead of FedBAT | FedBAT · CIFAR-100 | top-1 accuracy (%): 46.89 -> 52.88 | Improved |
| use pFed1BS instead of FedAvg for communication | FedAvg · CIFAR-10 | per-round communication cost (MB): 42.85 -> 0.13 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- FedBAT — FedBAT: Communication-Efficient Federated Learning via Learnable Binarization (ICML 2024) · better on 5 of 5 shared results
- EDEN — EDEN: Communication-Efficient and Robust Distributed Mean Estimation for Federated Learning (ICML 2022) · better on 5 of 5 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Decentralized Directed Collaboration for Personalized Federated Learning (CVPR 2024 · similarity 0.90)
- Understanding the Statistical Accuracy-Communication Trade-off in Personalized Federated Learning with Minimax Guarantees (ICML 2025 · similarity 0.88)
- LoCoDL: Communication-Efficient Distributed Learning with Local Training and Compression (ICLR 2025 · similarity 0.87)
- pFedClub: Controllable Heterogeneous Model Aggregation for Personalized Federated Learning (NeurIPS 2024 · similarity 0.87)
- z-SignFedAvg: A Unified Stochastic Sign-Based Compression for Federated Learning (AAAI 2024 · similarity 0.87)
- Stochastic Controlled Averaging for Federated Learning with Communication Compression (ICLR 2024 · 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.
