Sparse Causal Discovery with Generative Intervention for Unsupervised Graph Domain Adaptation

TL;DR

This paper introduces SLOGAN, a novel method for unsupervised graph domain adaptation that disentangles causal features from spurious correlations using sparse causal modeling and generative intervention, leading to improved transfer stability.

Contribution

SLOGAN combines sparse causal discovery with generative intervention and dynamic calibration to enhance graph domain adaptation performance.

Findings

Outperforms existing methods on multiple datasets

Effectively disentangles causal and spurious features

Improves stability of graph representation transfer

Abstract

Unsupervised Graph Domain Adaptation (UGDA) leverages labeled source domain graphs to achieve effective performance in unlabeled target domains despite distribution shifts. However, existing methods often yield suboptimal results due to the entanglement of causal-spurious features and the failure of global alignment strategies. We propose SLOGAN (Sparse Causal Discovery with Generative Intervention), a novel approach that achieves stable graph representation transfer through sparse causal modeling and dynamic intervention mechanisms. Specifically, SLOGAN first constructs a sparse causal graph structure, leveraging mutual information bottleneck constraints to disentangle sparse, stable causal features while compressing domain-dependent spurious correlations through variational inference. To address residual spurious correlations, we innovatively design a generative intervention mechanism that breaks local spurious couplings through cross-domain feature recombination while maintaining causal feature semantic consistency via covariance constraints. Furthermore, to mitigate error accumulation in target domain pseudo-labels, we introduce a category-adaptive dynamic calibration strategy, ensuring stable discriminative learning. Extensive experiments on multiple real-world datasets demonstrate that SLOGAN significantly outperforms existing baselines.