Research map / Federated learning and privacy / Personalized and heterogeneous FL
FedSST: Rethinking Fair Federated Graph Learning under Structural Shift
Dingyi Zhao
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 SSCA to FedAvg baseline (ablation) | FedAvg · SM | average accuracy: 75.04 -> 78.75 | Improved |
| add SLTA to FedAvg baseline (ablation) | FedAvg · SM | average accuracy: 75.04 -> 80.07 | Improved |
| add SLTA on top of SSCA (ablation) | FedSST · SM | average accuracy: 78.75 -> 82.29 | Improved |
| add SLTA on top of SSCA (ablation) | FedSST · SM-SN-CV | client accuracy STD: 13.80 -> 13.29 | Improved |
| add SLTA alone to FedAvg (ablation) | FedAvg · SM-SN-CV | average accuracy: 74.147 -> 74.98 | No clear effect |
| add SSCA alone to FedAvg (ablation) | FedAvg · SM-SN-CV | average accuracy: 74.147 -> 77.36 | Improved |
| FedSST vs FedSSP on SM-CV | FedSST · SM-CV | average accuracy: 83.70 -> 82.17 | Hurt |
| use SLTA to cut communication rounds | FedSST · SM, SM-CV, SM-SN-CV | communication rounds to converge: 200 -> 100 rounds | Improved |
| tune lambda_reg per setting (20, 25, 30) (ablation) | FedSST SLTA · chem, chemcv, chemsncv | accuracy and STD | Mixed |
Closest papers by meaning
- FedGOG: Federated Graph Out-of-Distribution Generalization with Diffusion Data Exploration and Latent Embedding Decorrelation (AAAI 2025 · similarity 0.90)
- FedSPA: Generalizable Federated Graph Learning under Homophily Heterogeneity (CVPR 2025 · similarity 0.90)
- FedSSP: Federated Graph Learning with Spectral Knowledge and Personalized Preference (NeurIPS 2024 · similarity 0.90)
- Subgraph Federated Learning via Spectral Methods (NeurIPS 2025 · similarity 0.89)
- Federated Graph Learning under Domain Shift with Generalizable Prototypes (AAAI 2024 · similarity 0.89)
- Demystifying Local & Global Fairness Trade-offs in Federated Learning Using Partial Information Decomposition (ICLR 2024 · similarity 0.89)
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.
