# Stochastic Deep Graph Clustering for Practical Group Formation

arXiv: https://arxiv.org/abs/2511.02879 · HTML: https://mlsanity.com/paper/2511.02879/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 31 references that are in the map.
- First posted on arXiv 4 Nov 2025.

## Builds on (most cited first, 11 of 11)

- [LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation](https://mlsanity.com/paper/2002.02126/) (2020)
- [Graph Neural Networks in Recommender Systems: A Survey](https://mlsanity.com/paper/2011.02260/) (2020)
- [Structural Deep Clustering Network](https://mlsanity.com/paper/2002.01633/) (2020)
- [A Survey of Deep Graph Clustering: Taxonomy, Challenge, Application, and Open Resource](https://mlsanity.com/paper/2211.12875/) (2022)
- [GroupIM: A Mutual Information Maximization Framework for Neural Group Recommendation](https://mlsanity.com/paper/2006.03736/) (2020)
- [AlignGroup: Learning and Aligning Group Consensus with Member Preferences for Group Recommendation](https://mlsanity.com/paper/2409.02580/) (2024)
- [Thinking inside The Box: Learning Hypercube Representations for Group Recommendation](https://mlsanity.com/paper/2204.02592/) (2022)
- [ConsRec: Learning Consensus Behind Interactions for Group Recommendation](https://mlsanity.com/paper/2302.03555/) (2023)
- [Deep Attention-guided Graph Clustering with Dual Self-supervision](https://mlsanity.com/paper/2111.05548/) (2021)
- [Dying Clusters Is All You Need -- Deep Clustering With an Unknown Number of Clusters](https://mlsanity.com/paper/2410.09491/) (2024)
- [Identify Then Recommend: Towards Unsupervised Group Recommendation](https://mlsanity.com/paper/2410.23757/) (2024)

## Abstract (arXiv)

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.