Research map / Probabilistic and scientific modeling / Dynamical systems
Iterative Structural Inference of Directed Graphs
Aoran Wang, Jun Pang
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 |
|---|---|---|---|
| remove signal smoothness term Omega from the objective (ablation) | iSIDG · LI | reconstruction heat map | Hurt |
| remove connectiveness term Ld from the objective (ablation) | iSIDG · LI | reconstruction heat map | Hurt |
| remove sparsity term Ls from the objective (ablation) | iSIDG · LI | reconstruction heat map | Hurt |
| use iSIDG instead of fNRI on directed synthetic networks | iSIDG · LI | AUROC: 73.0 -> 86.2 | Improved |
| use iSIDG instead of ACD on NetSim3 | iSIDG · NetSim3 | AUROC: 62.9 -> 71.0 | Improved |
| use iSIDG instead of fNRI on Kuramoto | iSIDG · Kuramoto | AUROC: 79.5 -> 79.8 | No clear effect |
| use iSIDG instead of ACD on Kuramoto | iSIDG · Kuramoto | AUROC: 80.5 -> 79.8 | Hurt |
| use iSIDG instead of fNRI on Springs | iSIDG · Springs | AUROC: 90.4 -> 90.5 | No clear effect |
| scale to 100 nodes (Springs100) with iSIDG instead of fNRI | iSIDG · Springs100 | AUROC: 68.4 -> 72.7 | Improved |
| use iSIDG instead of fNRI on real GRN ESC | iSIDG · ESC | AUROC: 39.8 -> 56.7 | Improved |
| use iSIDG instead of fNRI on real GRN HSC | iSIDG · HSC | AUROC: 45.0 -> 58.6 | Improved |
| larger graph (100 nodes) than small simulations | iSIDG · Springs vs Springs100 | AUROC: 90.5 -> 72.7 | Hurt |
Closest papers by meaning
- Benchmarking Structural Inference Methods for Interacting Dynamical Systems with Synthetic Data (NeurIPS 2024 · similarity 0.89)
- A Graph Dynamics Prior for Relational Inference (AAAI 2024 · similarity 0.87)
- ProDAG: Projected Variational Inference for Directed Acyclic Graphs (NeurIPS 2025 · similarity 0.86)
- Graph Structure Inference with BAM: Neural Dependency Processing via Bilinear Attention (NeurIPS 2024 · similarity 0.86)
- Guided Structural Inference: Leveraging Priors with Soft Gating Mechanisms (ICML 2025 · similarity 0.86)
- Interpretable Relational Inference with LLM-Guided Symbolic Dynamics Modeling (NeurIPS 2026 · 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.
