Research map / Federated learning and privacy / Personalized and heterogeneous FL
Eliminating Domain Bias for Federated Learning in Representation Space
Jianqing Zhang, Yang Hua, Jian Cao, Hao Wang, Tao Song, Zhengui XUE, Ruhui Ma, Haibing Guan
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 mean regularization (MR) alone (ablation) | FedAvg · Tiny-ImageNet 4-layer CNN | accuracy: 19.46 -> 22.21 | Improved |
| add personalized representation bias memory (PRBM) alone (ablation) | FedAvg · Tiny-ImageNet 4-layer CNN | accuracy: 19.46 -> 26.70 | Improved |
| add both PRBM and MR (full DBE) (ablation) | FedAvg · Tiny-ImageNet 4-layer CNN | accuracy: 19.46 -> 43.32 | Improved |
| add MR alone (ablation) | FedAvg · Tiny-ImageNet 4-layer CNN | MDL (bits): 3844 -> 3643 | Improved |
| add PRBM alone (ablation) | FedAvg · Tiny-ImageNet ResNet-18 | accuracy: 19.45 -> 38.27 | Improved |
| add MR alone (ablation) | FedAvg · Tiny-ImageNet ResNet-18 | accuracy: 19.45 -> 20.85 | Improved |
| insert DBE after CONV2 instead of after FC1 (ablation) | FedAvg+DBE · Tiny-ImageNet 4-layer CNN | accuracy: 43.32 -> 47.03 | Improved |
| insert DBE after CONV1 instead of after FC1 (ablation) | FedAvg+DBE · Tiny-ImageNet 4-layer CNN | accuracy: 43.32 -> 21.81 | Hurt |
| add DBE to SCAFFOLD | SCAFFOLD · Cifar100 | accuracy: 33.08 -> 63.61 | Improved |
| add DBE to FedGen | FedGen · AG News | accuracy: 89.86 -> 97.16 | Improved |
| add Gaussian noise (s=5, q=0.2) to client means (ablation) | FedAvg+DBE · Tiny-ImageNet | accuracy: 43.32 -> 36.27 | Hurt |
| add small Gaussian noise (s=0.05, q=0.2) to client means (ablation) | FedAvg+DBE · Tiny-ImageNet | accuracy: 43.32 -> 44.10 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- FedBABU — FedBABU: Toward Enhanced Representation for Federated Image Classification (ICLR 2022) · better on 3 of 3 shared results
- Ditto — Ditto: Fair and Robust Federated Learning Through Personalization (ICML 2021) · better on 1 of 1 shared result
- SCAFFOLD — SCAFFOLD: Stochastic Controlled Averaging for Federated Learning (ICML 2020) · better on 1 of 1 shared result
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
- Fair Federated Learning under Domain Skew with Local Consistency and Domain Diversity (CVPR 2024 · similarity 0.87)
- A Bayesian Approach for Personalized Federated Learning in Heterogeneous Settings (NeurIPS 2024 · similarity 0.86)
- Fine-Tuning Personalization in Federated Learning to Mitigate Adversarial Clients (NeurIPS 2024 · similarity 0.86)
- Understanding the Statistical Accuracy-Communication Trade-off in Personalized Federated Learning with Minimax Guarantees (ICML 2025 · similarity 0.86)
- Overcoming Data and Model heterogeneities in Decentralized Federated Learning via Synthetic Anchors (ICML 2024 · similarity 0.86)
- FedGMKD: An Efficient Prototype Federated Learning Framework through Knowledge Distillation and Discrepancy-Aware Aggregation (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.
