GraphSAD: Learning Graph Representations with Structure-Attribute Disentanglement
Graph Neural Networks (GNNs) learn effective node/graph representations by aggregating the attributes of neighboring nodes, which commonly derives a single representation mixing the information of graph structure and node attributes. However, these two kinds of information might be semantically inconsistent and could be useful for different tasks. In this paper, we aim at learning node/graph representations with Structure-Attribute Disentanglement (GraphSAD). We propose to disentangle graph structure and node attributes into two distinct sets of representations, and such disentanglement can be done in either the input or the embedding space. We further design a metric to quantify the extent of such a disentanglement. Extensive experiments on multiple datasets show that our approach can indeed disentangle the semantics of graph structure and node attributes, and it achieves superior performance on both node and graph classification tasks.
Code (0)
등록된 구현이 없습니다.
Tasks
AttributeDisentanglementGraph ClassificationSimilar Papers 제목 키워드 기반
Interpretable Deep Graph Generation with Node-Edge Co-Disentanglement
Disentangled representation learning has recently attracted a significant amount of attention, particularly in the field of image representation learning. However, learning the disentangled representations behind a graph…
DisentanglementGraph GenerationRepresentation LearningEnhancing Fairness in Unsupervised Graph Anomaly Detection through Disentanglement
Graph anomaly detection (GAD) is increasingly crucial in various applications, ranging from financial fraud detection to fake news detection. However, current GAD methods largely overlook the fairness problem, which migh…
Anomaly DetectionDecision MakingDisentanglementFairness+5Is Disentanglement enough? On Latent Representations for Controllable Music Generation
Improving controllability or the ability to manipulate one or more attributes of the generated data has become a topic of interest in the context of deep generative models of music. Recent attempts in this direction have…
DecoderDisentanglementMusic GenerationDisentangling, Amplifying, and Debiasing: Learning Disentangled Representations for Fair Graph Neural Networks
Graph Neural Networks (GNNs) have become essential tools for graph representation learning in various domains, such as social media and healthcare. However, they often suffer from fairness issues due to inherent biases i…
AttributeDisentanglementFairnessGraph Representation Learning+1FairREAD: Re-fusing Demographic Attributes after Disentanglement for Fair Medical Image Classification
Recent advancements in deep learning have shown transformative potential in medical imaging, yet concerns about fairness persist due to performance disparities across demographic subgroups. Existing methods aim to addres…
DiagnosticDisentanglementFairnessimage-classification+2