Research map / Graph learning / Knowledge and temporal graphs
DyC-STG: Dynamic Causal Spatio-Temporal Graph Network for Real-time Data Credibility Analysis in IoT
Guanjie Cheng, Boyi Li, Peihan Wu, Feiyi Chen, Xinkui Zhao, Mengying Zhu, Shuiguang Deng
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 causal reasoning module (causal-masked attention) (ablation) | DyC-STG · SHSD92 | F1-Score: 0.8257 -> 0.9297 | Improved |
| add event-driven dynamic graph instead of static graph (ablation) | DyC-STG · SHSD92 | F1-Score: 0.8810 -> 0.9297 | Improved |
| add temporal Transformer encoder (ablation) | DyC-STG · SHSD92 | F1-Score: 0.8467 -> 0.9297 | Improved |
| add GAT spatial layers (ablation) | DyC-STG · SHSD92 | F1-Score: 0.9009 -> 0.9297 | Improved |
| add causal reasoning module (ablation) | DyC-STG · SHSD104 | F1-Score: 0.8239 -> 0.9189 | Improved |
| add event-driven dynamic graph (ablation) | DyC-STG · SHSD104 | F1-Score: 0.8739 -> 0.9189 | Improved |
| use 2 GAT layers and 2 Transformer layers rather than 1 or 3 (ablation) | DyC-STG · SHSD92 | F1-Score: 0.9297 at Gl=2, Tl=2 | Improved |
| use DyC-STG instead of the strongest dynamic-graph baseline PDFormer | spatio-temporal credibility model · SHSD92 | F1-Score: 0.9153 -> 0.9297 | Improved |
| use dynamic-graph models instead of static-graph models | baselines · SHSD92 | F1-Score | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- PDFormer — PDFormer: Propagation Delay-Aware Dynamic Long-Range Transformer for Traffic Flow Prediction (AAAI 2023) · better on 4 of 4 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Deciphering Spatio-Temporal Graph Forecasting: A Causal Lens and Treatment (NeurIPS 2023 · similarity 0.86)
- Towards Dynamic Spatial-Temporal Graph Learning: A Decoupled Perspective (AAAI 2024 · similarity 0.84)
- Long Range Propagation on Continuous-Time Dynamic Graphs (ICML 2024 · similarity 0.83)
- CausalDynamics: A large‐scale benchmark for structural discovery of dynamical causal models (NeurIPS 2025 · similarity 0.83)
- DyG-Mamba: Continuous State Space Modeling on Dynamic Graphs (NeurIPS 2025 · similarity 0.82)
- CausalTime: Realistically Generated Time-series for Benchmarking of Causal Discovery (ICLR 2024 · similarity 0.82)
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.
