Research map / Federated learning and privacy / Personalized and heterogeneous FL
FedX: Unsupervised Federated Learning with Cross Knowledge Distillation
Sungwon Han, Sungwon Park, Fangzhao Wu, Sundong Kim, Chuhan Wu, Xing Xie, Meeyoung Cha
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 FedX two-sided knowledge distillation | FedSimCLR · CIFAR-10 (last round) | top-1 accuracy: 51.31 -> 56.88 | Improved |
| add FedX | FedProtoCL · SVHN (last round) | top-1 accuracy: 49.85 -> 69.31 | Improved |
| add FedX | FedProtoCL · F-MNIST (best round) | top-1 accuracy: 83.57 -> 83.34 | Hurt |
| add FedX | FedMoCo · CIFAR-10 (last round) | top-1 accuracy: 56.74 -> 58.23 | Improved |
| add global knowledge distillation to local KD (ablation) | L_local-KD · CIFAR-10 (last round) | top-1 accuracy: 51.89 -> 56.88 | Improved |
| replace global KD with SCAFFOLD or FedProx (ablation) | L_local-KD + L_global-KD · CIFAR-10 (last round) | top-1 accuracy: 56.88 -> 52.73 (SCAFFOLD), 52.48 (FedProx) | Hurt |
| use global KD instead of FedProx (ablation) | L_local-KD · SVHN (last round) | top-1 accuracy: 77.43 -> 77.19 | No clear effect |
| add FedX across data sizes | FedSimCLR · CIFAR-10 (10% data, last round) | top-1 accuracy: 46.80 -> 51.03 | Improved |
| add FedX with 15 clients | FedSimCLR · CIFAR-10 (15 clients, last round) | top-1 accuracy: 52.31 -> 55.12 | Improved |
| reduce data size from 100% to 10% (ablation) | FedSimCLR + FedX · CIFAR-10 (last round) | top-1 accuracy: 56.88 -> 51.03 | Hurt |
| add FedX | FedSimCLR · ImageNet-10 (last round) | top-1 accuracy: 81.50 -> 86.17 | Improved |
| use FedX instead of FedCA (ablation) | FedSimCLR · CIFAR-10 (last round) | top-1 accuracy: 47.46 -> 56.88 | Improved |
Closest papers by meaning
- Rethinking the Representation in Federated Unsupervised Learning with Non-IID Data (CVPR 2024 · similarity 0.87)
- Efficient Federated Learning via Clients-to-Server Knowledge Distillation (Student Abstract) (AAAI 2025 · similarity 0.87)
- Federated Learning via Input-Output Collaborative Distillation (AAAI 2024 · similarity 0.87)
- FLUX: Efficient Descriptor-Driven Clustered Federated Learning under Arbitrary Distribution Shifts (NeurIPS 2025 · similarity 0.86)
- FedGMKD: An Efficient Prototype Federated Learning Framework through Knowledge Distillation and Discrepancy-Aware Aggregation (NeurIPS 2024 · similarity 0.86)
- Relaxed Contrastive Learning for Federated Learning (CVPR 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.
