Proceedings

Provable Guarantees on the Robustness of Decision Rules to Causal Interventions

Benjie Wang, Clare Lyle, Marta Kwiatkowska

Download BibTeX Cite

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence. Main Track. Pages 4258-4265.

https://doi.org/10.24963/ijcai.2021/585

Keywords

  • Knowledge Representation and Reasoning: Knowledge Compilation and Tractable Languages
  • Uncertainty in AI: Bayesian Networks
  • Machine Learning: Transfer, Adaptation, Multi-task Learning

Abstract

Robustness of decision rules to shifts in the data-generating process is crucial to the successful deployment of decision-making systems. Such shifts can be viewed as interventions on a causal graph, which capture (possibly hypothetical) changes in the data-generating process, whether due to natural reasons or by the action of an adversary. We consider causal Bayesian networks and formally define the interventional robustness problem, a novel model-based notion of robustness for decision functions that measures worst-case performance with respect to a set of interventions that denote changes to parameters and/or causal influences. By relying on a tractable representation of Bayesian networks as arithmetic circuits, we provide efficient algorithms for computing guaranteed upper and lower bounds on the interventional robustness probabilities. Experimental results demonstrate that the methods yield useful and interpretable bounds for a range of practical networks, paving the way towards provably causally robust decision-making systems.

Benjie Wang, Clare Lyle, and Marta Kwiatkowska. 2021. Provable Guarantees on the Robustness of Decision Rules to Causal Interventions. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21. IJCAI, 4258–4265. https://doi.org/10.24963/ijcai.2021/585
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards