Research map / Graph learning / Graph self-supervised learning
Graph Meets Deep Unfolding: An Interpretable Mutual-benefit Multi-view Learning Network
Renjie Lin, Hongzhi He, Yilin Wu, Shide Du, Le Zhang
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 reconstruction loss LR (ablation) | IMML-Net · Notting-Hill | ACC (%): 57.0 -> 79.4 | Improved |
| add orthogonality loss LO (ablation) | IMML-Net · Notting-Hill | ACC (%): 57.0 -> 83.8 | Improved |
| add LO on top of LR (ablation) | IMML-Net · Notting-Hill | ACC (%): 79.4 -> 89.5 | Improved |
| add LR on top of LO (ablation) | IMML-Net · Youtube | ACC (%): 26.9 -> 37.0 | Improved |
| add LR alone (ablation) | IMML-Net · Youtube | ACC (%): 26.1 -> 30.5 | Improved |
| add LO alone (ablation) | IMML-Net · Youtube | ACC (%): 26.1 -> 26.9 | No clear effect |
| add LR and LO together (ablation) | IMML-Net · ALOI | ACC (%): 51.5 -> 76.5 | Improved |
| vary loss weights lambda1 and lambda2 over 0.0001 to 10.0 (ablation) | IMML-Net · Caltech101-20 | ACC (%) | No clear effect |
| use IMML-Net instead of best baseline | IMML-Net · Notting-Hill | ACC (%): 73.9 -> 89.5 | Improved |
Closest papers by meaning
- How Interpretable Are Interpretable Graph Neural Networks? (ICML 2024 · similarity 0.87)
- The Underappreciated Power of Vision Models for Graph Structural Understanding (NeurIPS 2025 · similarity 0.87)
- UniGTE: Unified Graph–Text Encoding for Zero-Shot Generalization across Graph Tasks and Domains (NeurIPS 2025 · similarity 0.86)
- Beyond Redundancy: Information-aware Unsupervised Multiplex Graph Structure Learning (NeurIPS 2024 · similarity 0.86)
- SURER: Structure-Adaptive Unified Graph Neural Network for Multi-View Clustering (AAAI 2024 · similarity 0.86)
- From GNNs to Trees: Multi-Granular Interpretability for Graph Neural Networks (ICLR 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.
