<ul data-eligibleForWebStory="false"><li>Unsupervised Graph Domain Adaptation (UGDA) aims to achieve effective performance in unlabeled target domains by leveraging labeled source domain graphs despite distribution shifts.</li><li>SLOGAN (Sparse Causal Discovery with Generative Intervention) is a novel approach proposed to address the challenges faced by existing UGDA methods in yielding suboptimal results due to causal-spurious features and global alignment strategies.</li><li>SLOGAN utilizes sparse causal modeling and dynamic intervention mechanisms to achieve stable graph representation transfer by disentangling causal features, compressing domain-dependent correlations, and breaking local spurious couplings through generative intervention.</li><li>Extensive experiments on real-world datasets show that SLOGAN outperforms existing baselines, demonstrating its effectiveness in unsupervised graph domain adaptation.</li></ul>

Sparse Causal Discovery with Generative Intervention for Unsupervised Graph Domain Adaptation

Discover more