DisenSemi: Semi-supervised Graph Classification via Disentangled Representation Learning

TL;DR

DisenSemi introduces a semi-supervised graph classification framework that learns disentangled representations, effectively transferring relevant semantics from unlabeled data to improve classification accuracy.

Contribution

The paper proposes a novel disentangled graph encoder and MI-based regularization for semi-supervised graph classification, emphasizing relevant knowledge transfer.

Findings

DisenSemi outperforms existing methods on multiple datasets.

Disentangled representations improve classification accuracy.

MI-based regularization enhances knowledge transfer effectiveness.

Abstract

Graph classification is a critical task in numerous multimedia applications, where graphs are employed to represent diverse types of multimedia data, including images, videos, and social networks. Nevertheless, in real-world scenarios, labeled graph data can be limited or scarce. To address this issue, we focus on the problem of semi-supervised graph classification, which involves both supervised and unsupervised models learning from labeled and unlabeled data. In contrast to recent approaches that transfer the entire knowledge from the unsupervised model to the supervised one, we argue that an effective transfer should only retain the relevant semantics that align well with the supervised task. In this paper, we propose a novel framework named DisenSemi, which learns disentangled representation for semi-supervised graph classification. Specifically, a disentangled graph encoder is proposed to generate factor-wise graph representations for both supervised and unsupervised models. Then we train two models via supervised objective and mutual information (MI)-based constraints respectively. To ensure the meaningful transfer of knowledge from the unsupervised encoder to the supervised one, we further define an MI-based disentangled consistency regularization between two models and identify the corresponding rationale that aligns well with the current graph classification task. Experimental results on a range of publicly accessible datasets reveal the effectiveness of our DisenSemi.