Research map / Federated learning and privacy / Personalized and heterogeneous FL
FRAug: Tackling Federated Learning with Non-IID Features via Representation Augmentation
Haokun Chen, Ahmed Frikha, Denis Krompass, Jindong Gu, Volker Tresp
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 FRAug representation augmentation to FedAvg-style training | FedAvg · OfficeHome (avg) | accuracy: 64.69 -> 66.60 | Improved |
| add FRAug to FedAvg | FedAvg · Digits (avg) | accuracy: 85.62 -> 89.59 | Improved |
| add a shared generator G to the client-specific RTNet (ablation) | FRAug · OfficeHome (avg) | accuracy: 64.58 -> 65.99 | Improved |
| add RTNet transformation to client-agnostic embeddings (ablation) | FRAug · Digits (avg) | accuracy: 87.25 -> 89.51 | Improved |
| add RTNet to generator on PACS (ablation) | FRAug · PACS (avg) | accuracy: 90.82 -> 91.35 | Improved |
| add EMA class-prototype embeddings (ablation) | FRAug · OfficeHome (avg) | accuracy: 65.99 -> 66.60 | Improved |
| add EMA class-prototype embeddings (ablation) | FRAug · PACS (avg) | accuracy: 91.35 -> 91.05 | No clear effect |
| add additional real-image embeddings to finetune prediction head | FedAvg classifier · OfficeHome (motivation) | accuracy: 64.69 -> 75.01 | Improved |
| replace random-noise embedding augmentation with learned FRAug augmentation | prediction head training · OfficeHome (avg) | accuracy: 65.06 -> 66.60 | Improved |
| apply input-space augmentation methods FAug and FedReg instead of FedAvg | FedAvg · OfficeHome (avg) | accuracy: 64.69 -> 60.39 (FAug), 62.00 (FedReg) | Hurt |
| scale to more clients on RxRx1 | FRAug · RxRx1 (avg) | accuracy: 30.84 -> 32.07 -> 33.20 (8, 12, 16 clients) | Improved |
| add FRAug under strong input noise | FedAvg · Noisy OfficeHome (sigma=1.0) | accuracy: 31.26 -> 31.65 | No clear effect |
Closest papers by meaning
- A Simple Data Augmentation for Feature Distribution Skewed Federated Learning (CVPR 2025 · similarity 0.89)
- Federated Model Heterogeneous Matryoshka Representation Learning (NeurIPS 2024 · similarity 0.88)
- FedWon: Triumphing Multi-domain Federated Learning Without Normalization (ICLR 2024 · similarity 0.88)
- TurboSVM-FL: Boosting Federated Learning through SVM Aggregation for Lazy Clients (AAAI 2024 · similarity 0.87)
- FedImpro: Measuring and Improving Client Update in Federated Learning (ICLR 2024 · similarity 0.87)
- (FL)$^2$: Overcoming Few Labels in Federated Semi-Supervised Learning (NeurIPS 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.
