Research map / Graph learning / Graph self-supervised learning
Cooperative Graph Transformer with Structural Consensus for Multi-View Learning
Zhiyuan Lai, Jiacheng Li, Jiayuan Wang, Shiping 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 structure-guided attention (vs standard attention) (ablation) | CoGFormer · ALOI | accuracy: 96.80 -> 98.04 | Improved |
| add structure-guided attention (vs standard attention) (ablation) | CoGFormer · MNIST | accuracy: 93.61 -> 93.78 | No clear effect |
| add structure-guided attention (vs standard attention) (ablation) | CoGFormer · 100leaves | accuracy: 95.71 -> 96.93 | Improved |
| add denoising structural consensus GCN (vs average-weighted GCN) (ablation) | CoGFormer · ALOI | accuracy: 93.24 -> 98.04 | Improved |
| add denoising structural consensus GCN (vs average-weighted GCN) (ablation) | CoGFormer · Caltech20 | accuracy: 85.75 -> 90.24 | Improved |
| add denoising structural consensus GCN (vs average-weighted GCN) (ablation) | CoGFormer · NoisyMNIST | accuracy: 96.46 -> 97.06 | Improved |
| use both structure-guided attention and denoised GCN (vs both standard) (ablation) | CoGFormer · 100leaves | accuracy: 94.96 -> 96.93 | Improved |
| CoGFormer vs best baseline | CoGFormer · MNIST | accuracy: 93.61 -> 93.78 | No clear effect |
| CoGFormer vs best baseline | CoGFormer · 100leaves | accuracy: 90.39 -> 96.93 | Improved |
| increase kNN graph density k (ablation) | CoGFormer · ALOI and Animals | accuracy | Improved |
| vary number of METIS communities C (ablation) | CoGFormer · ALOI and Animals | accuracy | No clear effect |
Closest papers by meaning
- SURER: Structure-Adaptive Unified Graph Neural Network for Multi-View Clustering (AAAI 2024 · similarity 0.88)
- Highly Confident Local Structure Based Consensus Graph Learning for Incomplete Multi-View Clustering (CVPR 2023 · similarity 0.87)
- Less is More: on the Over-Globalizing Problem in Graph Transformers (ICML 2024 · similarity 0.86)
- Stationary Diffusion State Neural Estimation for Multiview Clustering (AAAI 2022 · similarity 0.86)
- Global Graph Propagation with Hierarchical Information Transfer for Incomplete Contrastive Multi-view Clustering (AAAI 2025 · similarity 0.85)
- Hierarchical Consensus Network for Multiview Feature Learning (AAAI 2025 · similarity 0.85)
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.
