Abstract
Evaluating graphs learned by causal discovery algorithms is difficult: The number of edges that differ between two graphs does not reflect how the graphs differ with respect to the identifying formulas they suggest for causal effects. We introduce a framework for developing causal distances between graphs which includes the structural intervention distance for directed acyclic graphs as a special case. We use this framework to develop improved adjustment-based distances as well as extensions to completed partially directed acyclic graphs and causal orders. We develop new reachability algorithms to compute the distances efficiently and to prove their low polynomial time complexity. In our package gadjid (open source at github.com/CausalDisco/gadjid), we provide implementations of our distances; they are orders of magnitude faster with proven lower time complexity than the structural intervention distance and thereby provide a success metric for causal discovery that scales to graph sizes that were previously prohibitive.
Original language | English |
---|---|
Title of host publication | Proceedings of the 40th Conference on Uncertainty in Artificial Intelligence (UAI 2024) |
Number of pages | 30 |
Volume | 244 |
Publisher | PMLR |
Publication date | 2024 |
Pages | 1569-1598 |
Publication status | Published - 2024 |
Event | 40th Conference on Uncertainty in Artificial Intelligence, UAI 2024 - Barcelona, Spain Duration: 15 Jul 2024 → 19 Jul 2024 |
Conference
Conference | 40th Conference on Uncertainty in Artificial Intelligence, UAI 2024 |
---|---|
Country/Territory | Spain |
City | Barcelona |
Period | 15/07/2024 → 19/07/2024 |
Sponsor | Barcelona School of Economics (BSE), DE Shaw and Co, Google, Huawei, Universitat Pompeu Fabra (UPF) |
Series | Proceedings of Machine Learning Research |
---|---|
Volume | 244 |
ISSN | 2640-3498 |
Bibliographical note
Publisher Copyright:© 2024 Proceedings of Machine Learning Research. All rights reserved.