# Interpretable Clustering on Dynamic Graphs with Recurrent Graph Neural Networks

arXiv: https://arxiv.org/abs/2012.08740 · HTML: https://mlsanity.com/paper/2012.08740/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Dec 2020.

## Built on by (most cited first, 11 of 11)

- [Deep Temporal Graph Clustering](https://mlsanity.com/paper/2305.10738/) (2023)
- [A Survey of Deep Graph Clustering: Taxonomy, Challenge, Application, and Open Resource](https://mlsanity.com/paper/2211.12875/) (2022)
- [CGC: Contrastive Graph Clustering for Community Detection and Tracking](https://mlsanity.com/paper/2204.08504/) (2022)
- [Contrastive Graph Clustering in Curvature Spaces](https://mlsanity.com/paper/2305.03555/) (2023)
- [GCN-SE: Attention as Explainability for Node Classification in Dynamic Graphs](https://mlsanity.com/paper/2110.05598/) (2021)
- [Revisiting Dynamic Graph Clustering via Matrix Factorization](https://mlsanity.com/paper/2502.06117/) (2025)
- [FedRule: Federated Rule Recommendation System with Graph Neural Networks](https://mlsanity.com/paper/2211.06812/) (2022)
- [DECRL: A Deep Evolutionary Clustering Jointed Temporal Knowledge Graph Representation Learning Approach](https://mlsanity.com/paper/2410.22631/) (2024)
- [Hypergraph-Based Dynamic Graph Node Classification](https://mlsanity.com/paper/2412.20321/) (2024)
- [Deep Temporal Graph Clustering: A Comprehensive Benchmark and Datasets](https://mlsanity.com/paper/2601.12903/) (2026)
- [Node Role-Guided LLMs for Dynamic Graph Clustering](https://mlsanity.com/paper/2603.13799/) (2026)

## Abstract (arXiv)

We study the problem of clustering nodes in a dynamic graph, where the connections between nodes and nodes' cluster memberships may change over time, e.g., due to community migration. We first propose a dynamic stochastic block model that captures these changes, and a simple decay-based clustering algorithm that clusters nodes based on weighted connections between them, where the weight decreases at a fixed rate over time. This decay rate can then be interpreted as signifying the importance of including historical connection information in the clustering. However, the optimal decay rate may differ for clusters with different rates of turnover. We characterize the optimal decay rate for each cluster and propose a clustering method that achieves almost exact recovery of the true clusters. We then demonstrate the efficacy of our clustering algorithm with optimized decay rates on simulated graph data. Recurrent neural networks (RNNs), a popular algorithm for sequence learning, use a similar decay-based method, and we use this insight to propose two new RNN-GCN (graph convolutional network) architectures for semi-supervised graph clustering. We finally demonstrate that the proposed architectures perform well on real data compared to state-of-the-art graph clustering algorithms.