Research map / Federated learning and privacy / Personalized and heterogeneous FL
Collaborative Unsupervised Visual Representation Learning From Decentralized Data
Weiming Zhuang, Xin Gan, Yonggang Wen, Shuai Zhang, Shuai Yi
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 |
|---|---|---|---|
| aggregate and update the online encoder instead of aggregating the target encoder and updating the online encoder (ablation) | FedU · CIFAR-10 non-IID | top-1 accuracy (global predictor): 82.10 -> 84.07 | Improved |
| update only the target encoder with the aggregated encoder instead of the online encoder (ablation) | FedU · CIFAR-10 non-IID | top-1 accuracy (global predictor): 84.07 -> 9.99 | Hurt |
| update both online and target encoders instead of only the online encoder (ablation) | FedU · CIFAR-10 non-IID | top-1 accuracy (global predictor): 84.07 -> 81.24 | Hurt |
| update both encoders instead of only the online encoder with a local predictor (ablation) | FedU · CIFAR-10 non-IID | top-1 accuracy (local predictor): 82.18 -> 18.23 | Hurt |
| use divergence-aware predictor update instead of always local or always global predictor (ablation) | FedU · CIFAR-10/100 non-IID | top-1 accuracy: around 5% | Improved |
| always update with the global predictor instead of local predictor (online encoder aggregation) (ablation) | FedU · CIFAR-10 non-IID | top-1 accuracy: 82.18 -> 84.07 | Improved |
| set DAPU threshold mu to 0.2 (ablation) | FedU · CIFAR-10 non-IID | top-1 accuracy | Improved |
| increase local epochs E at fixed 500 total epochs (ablation) | FedU · CIFAR-10 non-IID | top-1 accuracy | Hurt |
| increase total training rounds R from 100 to 800 (ablation) | FedU · CIFAR-10 non-IID | top-1 accuracy | Improved |
| use FedU instead of single client training (ResNet-50) | BYOL · CIFAR-10 non-IID linear evaluation | top-1 accuracy: 77.84 -> 83.25 | Improved |
| use FedU instead of FedCA (ResNet-50) | federated unsupervised learning · CIFAR-100 non-IID linear evaluation | top-1 accuracy: 42.34 -> 61.94 | Improved |
| use deeper backbone ResNet-50 instead of ResNet-18 | FedU · CIFAR-10 non-IID linear evaluation | top-1 accuracy: 78.71 -> 83.25 | Improved |
Closest papers by meaning
- Rethinking the Representation in Federated Unsupervised Learning with Non-IID Data (CVPR 2024 · similarity 0.89)
- FedNE: Surrogate-Assisted Federated Neighbor Embedding for Dimensionality Reduction (NeurIPS 2024 · similarity 0.89)
- FORLA: Federated Object-centric Representation Learning with Slot Attention (NeurIPS 2025 · similarity 0.87)
- FLUX: Efficient Descriptor-Driven Clustered Federated Learning under Arbitrary Distribution Shifts (NeurIPS 2025 · similarity 0.87)
- FedMSGL: A Self-Expressive Hypergraph Based Federated Multi-View Learning (AAAI 2025 · similarity 0.86)
- Data-Free Black-Box Federated Learning via Zeroth-Order Gradient Estimation (AAAI 2025 · 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.
