Research map / Graph learning / Graph self-supervised learning
Multiplex Graph Representation Learning via Common and Private Information Mining
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 |
|---|---|---|---|
| add graph-structure reconstruction loss to both decorrelation losses (ablation) | CPIM · ACM | Macro-F1: 89.7 ± 0.1 -> 91.4 ± 0.3 | Helped |
| add graph-structure reconstruction loss to both decorrelation losses (ablation) | CPIM · IMDB | Macro-F1: 54.4 ± 0.2 -> 55.9 ± 0.4 | Helped |
| add graph-structure reconstruction loss to both decorrelation losses (ablation) | CPIM · DBLP | Macro-F1: 92.3 ± 0.1 -> 93.2 ± 0.3 | Helped |
| add graph-structure reconstruction loss to both decorrelation losses (ablation) | CPIM · Amazon | Macro-F1: 87.0 ± 0.2 -> 90.1 ± 0.1 | Helped |
| add cross-graph decorrelation loss to within-graph decorrelation and reconstruction (ablation) | CPIM · ACM | Macro-F1: 69.4 ± 0.2 -> 91.4 ± 0.3 | Helped |
| add cross-graph decorrelation loss to within-graph decorrelation and reconstruction (ablation) | CPIM · IMDB | Macro-F1: 45.8 ± 0.2 -> 55.9 ± 0.4 | Helped |
| add cross-graph decorrelation loss to within-graph decorrelation and reconstruction (ablation) | CPIM · DBLP | Macro-F1: 78.1 ± 0.4 -> 93.2 ± 0.3 | Helped |
| add cross-graph decorrelation loss to within-graph decorrelation and reconstruction (ablation) | CPIM · Amazon | Macro-F1: 80.8 ± 0.1 -> 90.1 ± 0.1 | Helped |
| add within-graph decorrelation loss to cross-graph decorrelation and reconstruction (ablation) | CPIM · ACM | Macro-F1: 84.2 ± 0.4 -> 91.4 ± 0.3 | Helped |
| add within-graph decorrelation loss to cross-graph decorrelation and reconstruction (ablation) | CPIM · IMDB | Macro-F1: 52.3 ± 0.4 -> 55.9 ± 0.4 | Helped |
| add within-graph decorrelation loss to cross-graph decorrelation and reconstruction (ablation) | CPIM · DBLP | Macro-F1: 81.8 ± 0.3 -> 93.2 ± 0.3 | Helped |
| add within-graph decorrelation loss to cross-graph decorrelation and reconstruction (ablation) | CPIM · Amazon | Macro-F1: 81.2 ± 0.4 -> 90.1 ± 0.1 | Helped |
Closest papers by meaning
- Multiplex Graph Representation Learning with Homophily and Consistency (AAAI 2025 · similarity 0.90)
- Beyond Redundancy: Information-aware Unsupervised Multiplex Graph Structure Learning (NeurIPS 2024 · similarity 0.86)
- Revisiting Self-Supervised Heterogeneous Graph Learning from Spectral Clustering Perspective (NeurIPS 2024 · similarity 0.85)
- Structural Entropy Based Graph Structure Learning for Node Classification (AAAI 2024 · similarity 0.85)
- Exploring Correlations of Self-Supervised Tasks for Graphs (ICML 2024 · similarity 0.84)
- Equivalence is All: A Unified View for Self-supervised Graph Learning (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.