Research map / Graph learning / Graph self-supervised learning
Deep Fusion Clustering Network
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| replace SDCN with DFCN | deep clustering · USPS | ACC: 78.1±0.2 -> 79.5±0.2 | Helped |
| replace SDCN with DFCN | deep clustering · HHAR | ACC: 84.3±0.2 -> 87.1±0.1 | Helped |
| replace SDCN_Q with DFCN | deep clustering · REUT | ACC: 79.3±0.1 -> 77.7±0.2 | Hurt |
| replace SDCN with DFCN | deep clustering · ACM | ACC: 90.5±0.2 -> 90.9±0.2 | Helped |
| replace SDCN with DFCN | deep clustering · DBLP | ACC: 68.1±1.8 -> 76.0±0.8 | Helped |
| replace SDCN with DFCN | deep clustering · CITE | ACC: 66.0±0.3 -> 69.5±0.2 | Helped |
| use both AE and IGAE information instead of only one source (ablation) | DFCN target distribution generation · USPS, HHAR, REUT, ACM, DBLP, CITE | ACC | Helped |
| add cross-modality dynamic fusion (ablation) | AE+IGAE baseline · six benchmark datasets | clustering performance: 0.5% to 5.0% | Helped |
| use triplet rather than single self-supervision (ablation) | Baseline-C · all datasets | clustering performance | Helped |
| reconstruct both weighted attributes and adjacency rather than adjacency only (ablation) | IGAE · six benchmark datasets | clustering performance | Helped |
| use weighted-attribute reconstruction rather than adjacency reconstruction only (ablation) | graph autoencoder · six benchmark datasets | clustering performance | Helped |
Closest papers by meaning
- SURER: Structure-Adaptive Unified Graph Neural Network for Multi-View Clustering (AAAI 2024 · similarity 0.86)
- Deep Contrastive Graph Learning with Clustering-Oriented Guidance (AAAI 2024 · similarity 0.85)
- LSEnet: Lorentz Structural Entropy Neural Network for Deep Graph Clustering (ICML 2024 · similarity 0.85)
- Deep Multi-modal Graph Clustering via Graph Transformer Network (AAAI 2025 · similarity 0.85)
- Attribute-Missing Graph Clustering Network (AAAI 2024 · similarity 0.85)
- DGCLUSTER: A Neural Framework for Attributed Graph Clustering via Modularity Maximization (AAAI 2024 · similarity 0.84)
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.