English

Differentiable and Transportable Structure Learning

Machine Learning 2023-06-13 v4 Machine Learning

Abstract

Directed acyclic graphs (DAGs) encode a lot of information about a particular distribution in their structure. However, compute required to infer these structures is typically super-exponential in the number of variables, as inference requires a sweep of a combinatorially large space of potential structures. That is, until recent advances made it possible to search this space using a differentiable metric, drastically reducing search time. While this technique -- named NOTEARS -- is widely considered a seminal work in DAG-discovery, it concedes an important property in favour of differentiability: transportability. To be transportable, the structures discovered on one dataset must apply to another dataset from the same domain. We introduce D-Struct which recovers transportability in the discovered structures through a novel architecture and loss function while remaining fully differentiable. Because D-Struct remains differentiable, our method can be easily adopted in existing differentiable architectures, as was previously done with NOTEARS. In our experiments, we empirically validate D-Struct with respect to edge accuracy and structural Hamming distance in a variety of settings.

Keywords

Cite

@article{arxiv.2206.06354,
  title  = {Differentiable and Transportable Structure Learning},
  author = {Jeroen Berrevoets and Nabeel Seedat and Fergus Imrie and Mihaela van der Schaar},
  journal= {arXiv preprint arXiv:2206.06354},
  year   = {2023}
}

Comments

Accepted at the International Conference on Machine Learning (ICML) 2023

R2 v1 2026-06-24T11:49:35.837Z