Research map / Graph learning / Graph self-supervised learning
DANCE: Dynamic, Available, Neighbor-gated Condensation for Federated Text-Attributed Graphs
Zekai Chen, Haodong Lu, Xunkai Li, Henan Sun, Jia Li, Hongchao Qin, Rong-Hua Li, Guoren Wang
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 Self-expressive Topology Reconstruction (ablation) | DANCE · Cora 8% | accuracy (%): 87.08 -> 88.87 | Improved |
| add Hierarchical Text Condensation (ablation) | DANCE · Cora 8% | accuracy (%): 85.14 -> 88.87 | Improved |
| add Label-aware Node Condensation (ablation) | DANCE · Cora 8% | accuracy (%): 81.22 -> 88.87 | Improved |
| add Self-expressive Topology Reconstruction (ablation) | DANCE · CiteSeer 8% | accuracy (%): 77.32 -> 80.19 | Improved |
| add Hierarchical Text Condensation (ablation) | DANCE · CiteSeer 8% | accuracy (%): 77.11 -> 80.19 | Improved |
| add Label-aware Node Condensation (ablation) | DANCE · CiteSeer 8% | accuracy (%): 75.19 -> 80.19 | Improved |
| add Label-aware Node Condensation (ablation) | DANCE · CiteSeer 8% | Overall-F1: 65.44 -> 77.16 | Improved |
| use DANCE instead of FedC4 at 8% ratio | federated condensation · Arxiv | accuracy (%): 72.87 -> 78.26 | Improved |
| use DANCE instead of FedC4 at 8% ratio | federated condensation · CiteSeer | accuracy (%): 75.95 -> 80.19 | Improved |
| use DANCE instead of LLM4RGNN at 4% ratio | condensation · Cora | accuracy (%): 87.26 -> 87.12 | No clear effect |
| use DANCE instead of SFGC at 2% ratio | condensation · Instagram | accuracy (%): 65.12 -> 65.17 | No clear effect |
| use DANCE instead of FedC4 at 1% ratio | condensation · Children | accuracy (%): 48.24 -> 48.25 | No clear effect |
Closest papers by meaning
- Generalization Principles for Inference over Text-Attributed Graphs with Large Language Models (ICML 2025 · similarity 0.87)
- Virtual Nodes Can Help: Tackling Distribution Shifts in Federated Graph Learning (AAAI 2025 · similarity 0.87)
- $S^2$FGL: Spatial Spectral Federated Graph Learning (ICML 2025 · similarity 0.87)
- Towards Effective Federated Graph Foundation Model via Mitigating Knowledge Entanglement (NeurIPS 2025 · similarity 0.86)
- Federated Graph-Level Clustering Network (AAAI 2025 · similarity 0.86)
- FedGOG: Federated Graph Out-of-Distribution Generalization with Diffusion Data Exploration and Latent Embedding Decorrelation (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.
