Research map / Probabilistic and scientific modeling / Causal discovery
DAG-Informed Structure Learning from Multi-Dimensional Point Processes
Chunming Zhang, Muhong Gao, Shengji Jia
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 the DAG constraint to the L1/weighted-L1 regularized estimator (ablation) | nonDAG-L1 / nonDAG-wL1 · Simulated Network 1 (10 nodes, 15 edges) | SHD, false positives, FDR | Improved |
| add the DAG constraint (ablation) | nonDAG-L1 / nonDAG-wL1 · Simulated Network 1 (10 nodes, 15 edges) | Mi (false negatives) | No clear effect |
| add the DAG constraint to the unregularized MLE (ablation) | nonDAG-unreg · Simulated Network 2 (10 nodes, 40 edges, dense) | Ex, SHD, FDR | Improved |
| add the DAG constraint (ablation) | L1 and weighted-L1 estimators · Simulated Network 3 (50 nodes) | SHD, FDR | Improved |
| add the DAG constraint (ablation) | L1 and weighted-L1 estimators · Simulated Network 4 (100 nodes) | SHD, FDR | Improved |
| use adaptive weighted L1 penalty instead of plain L1 (ablation) | DAG-constrained estimator · Simulated Networks 1 and 3 | SHD | Improved |
| add regularization to the unregularized estimator (ablation) | nonDAG-unreg / DAG-unreg · Simulated Network 1 (sparse) | false positives, SHD | Improved |
| use Flex-AL updates instead of classical AL updates | DAG-wL1 and DAG-unreg · Simulated Network 3, T=1200 | iterations to convergence: more than 10 -> within 5 steps | Improved |
| use Flex-AL updates instead of classical AL updates | DAG-wL1 and DAG-unreg · Simulated Network 3, T=1200 | runtime | Improved |
| use DAG-wL1 instead of nonDAG-wL1 | neuronal spike train estimator · Neuronal spike train (EE.188, 102 neurons), test | predictive log-likelihood | Improved |
| use DAG-wL1 instead of nonDAG-wL1 | IPTV estimator · IPTV viewing records (81 channels), test | predictive log-likelihood | Improved |
Closest papers by meaning
- Gradient-Based Neural DAG Learning (ICLR 2020 · similarity 0.89)
- Boosting Causal Structure Learning: An Asymmetric Exponential Modulation Gaussian-Based Adaptive Sample Reweighting Framework (AAAI 2025 · similarity 0.88)
- Differentiable Structure Learning with Ancestral Constraints (ICML 2025 · similarity 0.88)
- CoLiDE: Concomitant Linear DAG Estimation (ICLR 2024 · similarity 0.88)
- Causal Discovery via Bayesian Optimization (ICLR 2025 · similarity 0.87)
- Effective Causal Discovery under Identifiable Heteroscedastic Noise Model (AAAI 2024 · similarity 0.87)
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.
