Research map / Graph learning / Knowledge and temporal graphs
Temporal Graph Thumbnail: Robust Representation Learning with Global Evolutionary Skeleton
Weining Shi, Zhisen Wen, Qinggang Zhang, Chentao Zhang, Zhihong 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 |
|---|---|---|---|
| TGT thumbnail-guided model instead of best baseline | temporal GNNs · Bitcoin link prediction | AUC: 74.47 -> 91.41 | Improved |
| TGT instead of DGIB | temporal GNNs · MathOverflow link prediction | AUC: 80.29 -> 82.38 | Improved |
| TGT instead of DGIB | temporal GNNs · MOOC link prediction | AUC: 93.06 -> 95.42 | Improved |
| TGT instead of DGIB under 50% feature noise | temporal GNNs · Bitcoin | AUC: 60.78 -> 80.62 | Improved |
| TGT instead of DGIB under 5 temporal permutations | temporal GNNs · MOOC | AUC: 70.32 -> 84.01 | Improved |
| TGT instead of DGIB under 20% structure attack | temporal GNNs · Bitcoin | AUC: 59.13 -> 80.95 | Improved |
| add von Neumann entropy thumbnail instead of normalized node degree (ablation) | TGT · temporal interference, three datasets | AUC | Improved |
| add thumbnail term Is(GT;G) to the evolution loss (ablation) | TGT · temporal interference, three datasets | AUC | Improved |
| TGT instead of DIDA, training time | robust temporal GNNs · Bitcoin | seconds per epoch: 23.46 -> 2.26 | Improved |
| TGT instead of TGN, training time | temporal GNNs · Bitcoin | seconds per epoch: 0.78 -> 2.26 | Hurt |
Closest papers by meaning
- Temporal Generalization Estimation in Evolving Graphs (ICLR 2024 · similarity 0.87)
- Beyond Spatio-Temporal Representations: Evolving Fourier Transform for Temporal Graphs (ICLR 2024 · similarity 0.86)
- Analytical Construction on Geometric Architectures: Transitioning from Static to Temporal Link Prediction (ICML 2025 · similarity 0.86)
- Benchmarking Structural Inference Methods for Interacting Dynamical Systems with Synthetic Data (NeurIPS 2024 · similarity 0.86)
- Neural Persistence Dynamics (NeurIPS 2024 · similarity 0.86)
- State Space Models on Temporal Graphs: A First-Principles Study (NeurIPS 2024 · 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.
