Research map / Graph learning / Knowledge and temporal graphs
Entangled No More: Multi-Domain Decoupling for Robust Dynamic Graph Neural Networks
Youda Mo, Chaobo He, Junwei Cheng, Peng Mei, Quanlong Guan
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 MP-K2alman (multi-particle kernel Kalman module) (ablation) | DeR-Mamba · COLLAB link prediction, original | AUC (%): 91.79 -> 94.83 | Improved |
| add MP-K2alman (ablation) | DeR-Mamba · COLLAB NETTACK evasion | average AUC drop (%): 31.8 -> 18.0 | Improved |
| add AFDM (adversarial-aware frequency decoupling) (ablation) | DeR-Mamba · COLLAB link prediction, original | AUC (%): 94.06 -> 94.83 | Improved |
| add AFDM (ablation) | DeR-Mamba · COLLAB NETTACK evasion | average AUC drop (%): 21.9 -> 18.0 | Improved |
| add AFDM (ablation) | DeR-Mamba · COLLAB feature attack gamma=0.5 | AUC (%): 69.35 -> 70.16 | No clear effect |
| add both MP-K2alman and AFDM (ablation) | DeR-Mamba · COLLAB structure attack | AUC (%): 90.10 -> 93.74 | Improved |
| add both modules (ablation) | DeR-Mamba · Yelp structure attack | AUC (%): 74.07 -> 79.28 | Improved |
| add both modules (ablation) | DeR-Mamba · ACT structure attack | AUC (%): 94.13 -> 96.60 | Improved |
| use DeR-Mamba instead of DG-Mamba | robust DGNN · COLLAB structure attack | AUC (%): 92.60 -> 93.74 | Improved |
| use DeR-Mamba instead of DG-Mamba | robust DGNN · Yelp NETTACK evasion | average AUC drop (%): 22.1 -> 13.9 | Improved |
| use DeR-Mamba instead of DG-Mamba | robust DGNN · COLLAB NETTACK evasion np=1 | AUC drop (%): 12.6 -> 12.7 | No clear effect |
| use DeR-Mamba instead of DG-Mamba | robust DGNN · Yelp feature attack gamma=0.5 | AUC (%): 61.82 -> 61.60 | Hurt |
Closest papers by meaning
- DG-Mamba: Robust and Efficient Dynamic Graph Structure Learning with Selective State Space Models (AAAI 2025 · similarity 0.88)
- When Graph Neural Networks Meet Dynamic Mode Decomposition (ICLR 2025 · similarity 0.87)
- CSG-ODE: ControlSynth Graph ODE For Modeling Complex Evolution of Dynamic Graphs (ICML 2025 · similarity 0.86)
- Beyond Spatio-Temporal Representations: Evolving Fourier Transform for Temporal Graphs (ICLR 2024 · similarity 0.86)
- A Graph Dynamics Prior for Relational Inference (AAAI 2024 · similarity 0.85)
- Valid Conformal Prediction for Dynamic GNNs (ICLR 2025 · 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.
