Stochastic Deep Graph Clustering for Practical Group Formation

TL;DR

This paper introduces DeepForm, a novel framework for dynamic group formation in recommender systems that leverages high-order user data, real-time clustering, and adaptive reconfiguration without retraining.

Contribution

DeepForm is the first framework to integrate stochastic deep graph clustering for real-time, dynamic group formation in GRSs, addressing key operational challenges.

Findings

DeepForm outperforms baselines in group quality and efficiency.

It achieves higher recommendation accuracy in dynamic scenarios.

The framework effectively adapts to changing group structures without retraining.

Abstract

While prior work on group recommender systems (GRSs) has primarily focused on improving recommendation accuracy, most approaches assume static or predefined groups, making them unsuitable for dynamic, real-world scenarios. We reframe group formation as a core challenge in GRSs and propose DeepForm (Stochastic Deep Graph Clustering for Practical Group Formation), a framework designed to meet three key operational requirements: (1) the incorporation of high-order user information, (2) real-time group formation, and (3) dynamic adjustment of the number of groups. DeepForm employs a lightweight GCN architecture that effectively captures high-order structural signals. Stochastic cluster learning enables adaptive group reconfiguration without retraining, while contrastive learning refines groups under dynamic conditions. Experiments on multiple datasets demonstrate that DeepForm achieves superior group formation quality, efficiency, and recommendation accuracy compared with various baselines.