Research map / Graph learning / Graph self-supervised learning
T-GINEE: A Tensor-Based Multi-Graph Representation Learning
Maolin Wang, ZiTing Mai, Xuhui Chen, Zhiqi Li, Tianshuo Wei, Yutian Xiao, Wenlin Zhang, Wanyu Wang, Ruocheng Guo, Haoxuan Li, Zenglin Xu, Xiangyu Zhao
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 GEE working-covariance regularization to CP decomposition | CP tensor model · Synthetic multilayer network | AUC: 0.4488 -> 0.9395 | Improved |
| use T-GINEE instead of best baseline | link prediction · WAT | AUC: 0.820 -> 0.838 | Improved |
| use T-GINEE instead of NMF | link prediction · DBLP (large-scale) | AUC: 0.6505 -> 0.6478 | No clear effect |
| use T-GINEE instead of SVD | link prediction · Stack Overflow | AUC: 0.9682 -> 0.9831 | Improved |
| use T-GINEE instead of GCN | community detection · Polbooks | NMI: 0.021 -> 0.428 | Improved |
| use T-GINEE instead of GCN | link prediction · Karate | AUC: 0.834 -> 0.817 | Hurt |
| use T-GINEE zero-shot instead of retrained MGCN | new-layer link prediction · DBLP-5K | AUC: 0.7089 -> 0.7733 | Improved |
| add learned working covariance to CP on heterogeneous synthetic layers (ablation) | T-GINEE · Synthetic heterogeneous layers | AUC: 0.5897 -> 0.5822 | No clear effect |
| increase overdetermination ratio (density 3% to 15%, n=500) | T-GINEE · Synthetic n=500 | AUC std: 0.0781 -> 0.0312 | Improved |
Closest papers by meaning
- A tensor factorization model of multilayer network interdependence (JMLR 2024 · similarity 0.91)
- A Latent Multilayer Graphical Model For Complex, Interdependent Systems (NeurIPS 2025 · similarity 0.88)
- Graph Traversal with Tensor Functionals: A Meta-Algorithm for Scalable Learning (ICLR 2021 · similarity 0.87)
- Dissecting the Failure of Invariant Learning on Graphs (NeurIPS 2024 · similarity 0.85)
- Link Prediction in Multilayer Networks via Cross-Network Embedding (AAAI 2024 · similarity 0.85)
- Graph Structure Inference with BAM: Neural Dependency Processing via Bilinear Attention (NeurIPS 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.
