Research map / Graph learning / Graph self-supervised learning
Disentangled Multiplex Graph Representation Learning
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 correlation loss Lcor (disentanglement) (ablation) | DMG · ACM | Macro-F1: 91.0 vs 87.8 without Lcor-less variant | Helped |
| add contrastive private-information loss Lcon (ablation) | DMG · ACM | Macro-F1: 91.0 vs 87.8 | Helped |
| add reconstruction loss Lrec (ablation) | DMG · ACM | Macro-F1: 91.0 vs 86.5 | Helped |
| add contrastive loss Lcon (ablation) | DMG · DBLP | Macro-F1: 93.3 vs 92.5 | Helped |
| add contrastive loss Lcon (ablation) | DMG · IMDB | Macro-F1: 57.6 vs 54.7 | Helped |
| add Lrec and Lcor and Lcon jointly over Lmat-only setup (Lmat + Lcon only) (ablation) | DMG · ACM | Macro-F1: 91.0 vs 76.1 | Helped |
| full DMG vs strongest multiplex baseline on multiplex datasets | DMG · Table 1 classification average | Macro-F1: ~1.6% average gain over MCGC (text) | Helped |
| DMG vs CKD under increasing edge noise on DBLP | DMG · DBLP noisy edges | Macro-F1: DMG 93.3 vs CKD 92.0 at eta=0; gap widens with noise | Helped |
Closest papers by meaning
- Multiplex Graph Representation Learning with Homophily and Consistency (AAAI 2025 · similarity 0.90)
- Multiplex Graph Representation Learning via Common and Private Information Mining (AAAI 2023 · similarity 0.90)
- Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language Models (NeurIPS 2024 · similarity 0.89)
- Beyond Redundancy: Information-aware Unsupervised Multiplex Graph Structure Learning (NeurIPS 2024 · similarity 0.88)
- Disentangled Graph Self-supervised Learning for Out-of-Distribution Generalization (ICML 2024 · similarity 0.87)
- Enhancing Size Generalization in Graph Neural Networks through Disentangled Representation Learning (ICML 2024 · 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.