Causal-aware Graph Neural Architecture Search under Distribution Shifts

ICLR 2025 Conference Submission9825 Authors

Keywords: Graph Neural Architecture Search, Out-of-Distribution Generalization, Causal Learning

Abstract: Graph neural architecture search (Graph NAS) has emerged as a promising approach for autonomously designing graph neural network architectures by leveraging the correlations between graphs and architectures. However, the existing methods fail to generalize under distribution shifts that are ubiquitous in real-world graph scenarios, mainly because the graph-architecture correlations they exploit might be spurious and varying across distributions. In this paper, we propose to handle the distribution shifts in the graph architecture search process by discovering and exploiting the causal relationship between graphs and architectures to search for the optimal architectures that can generalize under distribution shifts. The problem remains unexplored with the following critical challenges: 1) how to discover the causal graph-architecture relationship that has stable predictive abilities across distributions, 2) how to handle distribution shifts with the discovered causal graph-architecture relationship to search the generalized graph architectures. To address these challenges, we propose a novel approach, Causal-aware Graph Neural Architecture Search (CARNAS), which is able to capture the causal graph-architecture relationship during the architecture search process and discover the generalized graph architecture under distribution shifts. Specifically, we propose Disentangled Causal Subgraph Identification to capture the causal subgraphs that have stable prediction abilities across distributions. Then, we propose Graph Embedding Intervention to intervene on causal subgraphs within the latent space, ensuring that these subgraphs encapsulate essential features for prediction while excluding non-causal elements. Additionally, we propose Invariant Architecture Customization to reinforce the causal invariant nature of the causal subgraphs, which are utilized to tailor generalized graph architectures. Extensive experiments on synthetic and real-world datasets demonstrate that our proposed CARNAS achieves advanced out-of-distribution generalization ability by discovering the causal relationship between graphs and architectures during the search process.

Primary Area: learning on graphs and other geometries & topologies

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 9825