Stochastic Deep Graph Clustering for Practical Group Formation

2025-11-04

AI Summary

Existing group recommendation systems typically assume static or pre-defined groups, limiting their applicability in dynamic real-world scenarios. This work reframes group formation as a core recommendation task and addresses three key challenges: modeling higher-order user relationships, enabling real-time group construction, and supporting adaptive group size adjustment. To this end, we propose a retraining-free stochastic clustering learning mechanism integrated with contrastive learning to optimize groups dynamically; additionally, we design a lightweight graph convolutional network to capture higher-order structural dependencies among users. Our approach significantly outperforms state-of-the-art baselines across multiple public benchmarks, achieving consistent improvements in grouping quality, computational efficiency, and recommendation accuracy. To the best of our knowledge, this is the first end-to-end, adaptive, and scalable framework for dynamic group recommendation.

Technology Category

• Data Mining & Knowledge Management: Recommender Systems
• Machine Learning: Graph-based Machine Learning
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• Dynamic group formation in recommender systems
• Real-time adaptive clustering without retraining
• High-order user information integration for groups

Innovation

• Lightweight GCN captures high-order structural signals
• Stochastic cluster learning enables adaptive group reconfiguration
• Contrastive learning refines groups under dynamic conditions