Research map / Graph learning / Graph self-supervised learning
Multi-View Multi-Graph Embedding for Brain Network Clustering Analysis
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 |
|---|---|---|---|
| Represent each view's collection of graphs as a partially symmetric tensor and jointly factorize views with soft consensus regularization | M2E · HIV | Accuracy: 68.57 -> 71.43 | Helped |
| Represent each view's collection of graphs as a partially symmetric tensor and jointly factorize views with soft consensus regularization | M2E · BP | Accuracy: 60.82 -> 68.04 | Helped |
| Replace separate per-view factorization and later combination with joint multi-view, multi-graph embedding (ablation) | M2E · HIV | Accuracy: 52.86 -> 71.43 | Helped |
| Replace separate per-view factorization and later combination with joint multi-view, multi-graph embedding (ablation) | M2E · BP | Accuracy: 57.73 -> 68.04 | Helped |
| Add soft consensus regularization rather than directly sharing coefficient matrices across views (ablation) | M2E · HIV | F1: 68.57 -> 72.22 | Helped |
| Add soft consensus regularization rather than directly sharing coefficient matrices across views (ablation) | M2E · BP | F1: 61.22 -> 68.69 | Helped |
| Use joint multi-view, multi-graph embedding instead of separate per-view factorization and later combination (ablation) | M2E · HIV | F1: 49.23 -> 72.22 | Helped |
| Use joint multi-view, multi-graph embedding instead of separate per-view factorization and later combination (ablation) | M2E · BP | F1: 64.34 -> 68.69 | Helped |
| Use M2E rather than MIC | brain-network clustering · BP | F1: 72.59 -> 68.69 | Hurt |
| Set embedding dimension R to 7 (ablation) | M2E · HIV | Accuracy | Helped |
| Set embedding dimension R to 12 (ablation) | M2E · BP | Accuracy | Helped |
| Increase the view weights to very large values (ablation) | M2E · HIV and BP | Accuracy | Hurt |
Closest papers by meaning
- SURER: Structure-Adaptive Unified Graph Neural Network for Multi-View Clustering (AAAI 2024 · similarity 0.86)
- S2MVTC: a Simple yet Efficient Scalable Multi-View Tensor Clustering (CVPR 2024 · similarity 0.85)
- Biologically Plausible Brain Graph Transformer (ICLR 2025 · similarity 0.85)
- BrainMAP: Learning Multiple Activation Pathways in Brain Networks (AAAI 2025 · similarity 0.85)
- Causal Invariance-aware Augmentation for Brain Graph Contrastive Learning (ICML 2025 · similarity 0.84)
- Multi-View Graph Clustering via Node-Guided Contrastive Encoding (ICML 2025 · 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.