Research map / Federated learning and privacy / Personalized and heterogeneous FL
Prior Refinement Is Better: Diffusion-Driven Graph Harmonization for Federated Graph Learning
Shuman Zhuang, Zhihao Wu, Wei Huang, Luojun Lin, Jia-Li Yin, Lele Fu, Hong-Ning Dai
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 FedGH prior refinement to FedTAD | FedTAD · Cora (20 clients) | accuracy: 63.74 -> 67.28 | Improved |
| add FedGH prior refinement to FedTAD | FedTAD · PubMed (20 clients) | accuracy: 81.19 -> 83.73 | Improved |
| add FedGH prior refinement to FedTAD | FedTAD · Photo (10 clients) | accuracy: 87.76 -> 87.92 | No clear effect |
| add FedGH prior refinement to FedTAD | FedTAD · Photo (20 clients) | accuracy: 84.94 -> 86.29 | Improved |
| add FedGH prior refinement to FedTAD | FedTAD · Cora (20 clients) | F1-score: 60.34 -> 63.90 | Improved |
| add FedGH prior refinement to FedTAD | FedTAD · PubMed (10 clients) | F1-score: 80.26 -> 80.47 | No clear effect |
| use FedGH instead of FedAvg alone | FedAvg · Cora (20 clients) | accuracy: 62.4 -> 70.7 | Improved |
| use FedGH instead of FedATH | FedATH · ogbn-arxiv (20 clients) | accuracy: 38.9 -> 38.1 | Hurt |
| add the KL divergence term to the VGAE loss (ablation) | FedGH · Cora and PubMed (10, 15, 20 clients) | accuracy | Improved |
| add the conditional vector to the diffusion model (ablation) | FedGH · Cora and PubMed (10, 15, 20 clients) | accuracy | Improved |
| add contrastive learning on pseudo-graphs (ablation) | FedGH · Cora and PubMed (10, 15, 20 clients) | accuracy | Improved |
| vary the KL weight gamma | FedGH · Cora and PubMed (10, 15, 20 clients) | accuracy | No clear effect |
Closest papers by meaning
- Virtual Nodes Can Help: Tackling Distribution Shifts in Federated Graph Learning (AAAI 2025 · similarity 0.91)
- FedGOG: Federated Graph Out-of-Distribution Generalization with Diffusion Data Exploration and Latent Embedding Decorrelation (AAAI 2025 · similarity 0.89)
- Towards Effective Federated Graph Foundation Model via Mitigating Knowledge Entanglement (NeurIPS 2025 · similarity 0.89)
- Federated Graph Learning under Domain Shift with Generalizable Prototypes (AAAI 2024 · similarity 0.89)
- FedSPA: Generalizable Federated Graph Learning under Homophily Heterogeneity (CVPR 2025 · similarity 0.89)
- $S^2$FGL: Spatial Spectral Federated Graph Learning (ICML 2025 · 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.
