Research map / Probabilistic and scientific modeling / Causal discovery
Shapley Regularized Neural Granger Causality
Maolin Yang, Zhoufan Zhu, Yuanhe Tian, Kun Gao, MUYI LI
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 |
|---|---|---|---|
| replace local Jacobian importance with global Info-Shap in the regularizer (l1 form) (ablation) | Residual MLP neural Granger causality · Lorenz-96 (d=50, F=40, T=1000) | AUROC: 0.941 -> 0.984 | Improved |
| replace Jacobian with Info-Shap on linear VAR(3) (ablation) | Residual MLP neural Granger causality · VAR(3) (d=50, T=500) | AUROC: 0.895 -> 0.898 | No clear effect |
| use Frobenius-norm random-projection variants instead of exact l1 penalties (ablation) | Info-Shap and Jacobian regularizers · Lorenz-96 (d=50, F=40, T=1000) | AUROC: 0.984 -> 0.775 (Shap -> F-Shap) | Hurt |
| use exact Shap instead of F-Shap on small-sample DREAM3 (ablation) | SRNGC · DREAM3 Ecoli-1 | AUROC: 0.632 -> 0.700 | Improved |
| use F-Shap instead of exact Shap on larger-sample CausalTime (ablation) | SRNGC · CausalTime AQI | AUROC: 0.946 -> 0.961 | Improved |
| use joint modeling instead of component-wise modeling (ablation) | Shap regularizer with MLP backbone · fMRI first 5 subjects | AUROC: 0.854 -> 0.874 | Improved |
| use joint modeling instead of component-wise modeling (ablation) | Shap regularizer with LSTM backbone · fMRI first 5 subjects | AUROC: 0.705 -> 0.847 | Improved |
| use model-agnostic Shap regularizer instead of layer-weight importance in component-wise cMLP (ablation) | cMLP · fMRI first 5 subjects | AUROC: 0.726 -> 0.854 | Improved |
| use F-Shap instead of Shap with LSTM joint model (ablation) | LSTM · fMRI first 5 subjects | AUROC: 0.847 -> 0.713 | Hurt |
| apply Info-Shap on the Medical dataset with the same Residual MLP | SRNGC / F-SRNGC · CausalTime Medical | AUROC: SRNGC 0.720 vs CUTS+ 0.820 | Hurt |
| use knockoff-style thresholding with q = 0.01 and an over-specified lag order of 4 | SRNGC · VAR(3) (d=10, T=1000) | graph recovery | 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.
- CUTS+ — CUTS: Neural Causal Discovery from Irregular Time-Series Data (ICLR 2023) · better on 2 of 3 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
- Jacobian Regularizer-based Neural Granger Causality (ICML 2024 · similarity 0.91)
- Exploring Neural Granger Causality with xLSTMs: Unveiling Temporal Dependencies in Complex Data (NeurIPS 2025 · similarity 0.89)
- TNPAR: Topological Neural Poisson Auto-Regressive Model for Learning Granger Causal Structure from Event Sequences (AAAI 2024 · similarity 0.88)
- CUTS+: High-Dimensional Causal Discovery from Irregular Time-Series (AAAI 2024 · similarity 0.87)
- Towards the Disappearing Truth: Fine-Grained Joint Causal Influences Learning with Hidden Variable-Driven Causal Hypergraphs in Time Series (AAAI 2024 · similarity 0.87)
- GCAD: Anomaly Detection in Multivariate Time Series from the Perspective of Granger Causality (AAAI 2025 · 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.
