Test-Time Learning of Causal Structure from Interventional Data
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914342343016448 |
|---|---|
| author | Chen, Wei Ding, Rui Huang, Bojun Zhang, Yang Fu, Qiang Liang, Yuxuan Shi, Han Zhang, Dongmei |
| author_facet | Chen, Wei Ding, Rui Huang, Bojun Zhang, Yang Fu, Qiang Liang, Yuxuan Shi, Han Zhang, Dongmei |
| contents | Supervised causal learning has shown promise in causal discovery, yet it often struggles with generalization across diverse interventional settings, particularly when intervention targets are unknown. To address this, we propose TICL (Test-time Interventional Causal Learning), a novel method that synergizes Test-Time Training with Joint Causal Inference. Specifically, we design a self-augmentation strategy to generate instance-specific training data at test time, effectively avoiding distribution shifts. Furthermore, by integrating joint causal inference, we developed a PC-inspired two-phase supervised learning scheme, which effectively leverages self-augmented training data while ensuring theoretical identifiability. Extensive experiments on bnlearn benchmarks demonstrate TICL's superiority in multiple aspects of causal discovery and intervention target detection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_19131 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Test-Time Learning of Causal Structure from Interventional Data Chen, Wei Ding, Rui Huang, Bojun Zhang, Yang Fu, Qiang Liang, Yuxuan Shi, Han Zhang, Dongmei Machine Learning Artificial Intelligence Supervised causal learning has shown promise in causal discovery, yet it often struggles with generalization across diverse interventional settings, particularly when intervention targets are unknown. To address this, we propose TICL (Test-time Interventional Causal Learning), a novel method that synergizes Test-Time Training with Joint Causal Inference. Specifically, we design a self-augmentation strategy to generate instance-specific training data at test time, effectively avoiding distribution shifts. Furthermore, by integrating joint causal inference, we developed a PC-inspired two-phase supervised learning scheme, which effectively leverages self-augmented training data while ensuring theoretical identifiability. Extensive experiments on bnlearn benchmarks demonstrate TICL's superiority in multiple aspects of causal discovery and intervention target detection. |
| title | Test-Time Learning of Causal Structure from Interventional Data |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2602.19131 |