Research map / Federated learning and privacy / Personalized and heterogeneous FL
FedSDWC: Federated Synergistic Dual-Representation Weak Causal Learning for OOD
Zhenyuan Huang, Hui Zhang, Wenzhong Tang, Haijun Yang
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 |
|---|---|---|---|
| model weak causal link z --> s instead of none (ablation) | FedSDWC · CIFAR-10 OOD detection, LSUN-Crop | FPR95: 39.71 -> 32.61 | Improved |
| weak causal link instead of full causal link z -> s (ablation) | FedSDWC · CIFAR-10 OOD detection, Textures | FPR95: 34.02 -> 37.20 | Hurt |
| weak causal link vs full link on SVHN FPR95 (ablation) | FedSDWC · CIFAR-10 OOD detection, SVHN | FPR95: 36.75 -> 35.46 | Mixed |
| weak causal link instead of none or full link (ablation) | FedSDWC · CIFAR-10 OOD generalization (ID-C) | accuracy | Improved |
| FedSDWC vs FedICON on corrupted data | federated OOD generalization · CIFAR-10-C avg | ID-C accuracy: 83.46 -> 86.50 | Improved |
| FedSDWC vs FedICON on Contrast corruption | federated OOD generalization · CIFAR-10-C Contrast | ID-C accuracy: 87.09 -> 81.48 | Hurt |
| FedSDWC vs FedAvg | federated OOD detection · CIFAR-10 vs LSUN-Crop | FPR95: 83.41 -> 32.61 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- PerAda — PerAda: Parameter-Efficient Federated Learning Personalization with Generalization Guarantees (CVPR 2024) · 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
- Causality Inspired Federated Learning for OOD Generalization (ICML 2025 · similarity 0.90)
- FedCSL: A Scalable and Accurate Approach to Federated Causal Structure Learning (AAAI 2024 · similarity 0.89)
- Federated Causal Structure Learning with Non-identical Variable Sets (ICML 2025 · similarity 0.88)
- Federated Causally Invariant Feature Learning (AAAI 2025 · similarity 0.88)
- Causally Motivated Personalized Federated Invariant Learning with Shortcut-Averse Information-Theoretic Regularization (ICML 2024 · similarity 0.87)
- FedLoGe: Joint Local and Generic Federated Learning under Long-tailed Data (ICLR 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.
