Research map / Federated learning and privacy / Personalized and heterogeneous FL
Federated Graph-Level Clustering Network with Dual Knowledge Separation
Xiaobao Wang, Renda Han, Ronghao Fu, Di Jin
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 client-side subgraph separation and two-stage k-means (with FedAvg server) (ablation) | FGCN-DKS · SM non-IID | ACC (%): 61.7 -> 68.1 | Improved |
| add client-side subgraph separation and two-stage k-means (with FedAvg server) (ablation) | FGCN-DKS · CV non-IID | ACC (%): 29.5 -> 37.7 | Improved |
| add CKSS server aggregation without local separation (ablation) | FGCN-DKS · SM non-IID | ACC (%): 61.7 -> 64.6 | Improved |
| add CKSS server aggregation without local separation (ablation) | FGCN-DKS · CV non-IID | ACC (%): 29.5 -> 32.4 | Improved |
| add CKSS server aggregation on top of local separation (ablation) | FGCN-DKS · SM non-IID | ACC (%): 68.1 -> 79.2 | Improved |
| add CKSS server aggregation on top of local separation (ablation) | FGCN-DKS · SM-BIO-SY non-IID | ACC (%): 67.2 -> 73.6 | Improved |
| add local separation on top of CKSS (ablation) | FGCN-DKS · SM-BIO non-IID | ACC (%): 61.6 -> 73.8 | Improved |
| full FGCN-DKS vs prior best FedPKA | FGCN-DKS · SM non-IID | ACC (%): 77.0 -> 79.2 | Improved |
| full FGCN-DKS vs prior FedGCN | FGCN-DKS · unequal cluster counts | ACC (%): 54.5 -> 62.1 | Improved |
| increase alpha:beta loss weight ratio above 1:1 (ablation) | FGCN-DKS · four non-IID settings | ACC, NMI, ARI, F1 | Mixed |
| use FGCN-DKS instead of FedGCN in communication cost (1 client, CV) | FGCN-DKS · CV non-IID | communication time (s): 15.9 -> 16.8 | Hurt |
Closest papers by meaning
- Federated Graph-Level Clustering Network (AAAI 2025 · similarity 0.93)
- Federated Node-Level Clustering Network with Cross-Subgraph Link Mending (ICML 2025 · similarity 0.91)
- Decoupled Subgraph Federated Learning (ICLR 2025 · similarity 0.87)
- OmniFC: Rethinking Federated Clustering via Lossless and Secure Distance Reconstruction (NeurIPS 2025 · similarity 0.87)
- Graph Consistency and Diversity Measurement for Federated Multi-View Clustering (AAAI 2025 · similarity 0.87)
- Asynchronous Federated Clustering with Unknown Number of Clusters (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.
