# Node Role-Guided LLMs for Dynamic Graph Clustering

arXiv: https://arxiv.org/abs/2603.13799 · HTML: https://mlsanity.com/paper/2603.13799/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 102 references that are in the map.
- First posted on arXiv 14 Mar 2026.

## Builds on (most cited first, 30 of 42)

- [node2vec: Scalable Feature Learning for Networks](https://mlsanity.com/paper/1607.00653/) (2016)
- [GraphGPT: Graph Instruction Tuning for Large Language Models](https://mlsanity.com/paper/2310.13023/) (2023)
- [G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering](https://mlsanity.com/paper/2402.07630/) (2024)
- [Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future](https://mlsanity.com/paper/2309.15402/) (2023)
- [LLMRec: Large Language Models with Graph Augmentation for Recommendation](https://mlsanity.com/paper/2311.00423/) (2023)
- [Representation Learning with Large Language Models for Recommendation](https://mlsanity.com/paper/2310.15950/) (2023)
- [ROLAND: Graph Learning Framework for Dynamic Graphs](https://mlsanity.com/paper/2208.07239/) (2022)
- [Motifs in Temporal Networks](https://mlsanity.com/paper/1612.09259/) (2016)
- [OpenGraph: Towards Open Graph Foundation Models](https://mlsanity.com/paper/2403.01121/) (2024)
- [GIMLET: A Unified Graph-Text Model for Instruction-Based Molecule Zero-Shot Learning](https://mlsanity.com/paper/2306.13089/) (2023)
- [Graph Neural Prompting with Large Language Models](https://mlsanity.com/paper/2309.15427/) (2023)
- [GraphTranslator: Aligning Graph Model to Large Language Model for Open-ended Tasks](https://mlsanity.com/paper/2402.07197/) (2024)
- [HiGPT: Heterogeneous Graph Language Model](https://mlsanity.com/paper/2402.16024/) (2024)
- [Spatio-Temporal Graph Few-Shot Learning with Cross-City Knowledge Transfer](https://mlsanity.com/paper/2205.13947/) (2022)
- [XRec: Large Language Models for Explainable Recommendation](https://mlsanity.com/paper/2406.02377/) (2024)
- [Graph-Aware Language Model Pre-Training on a Large Graph Corpus Can Help Multiple Graph Applications](https://mlsanity.com/paper/2306.02592/) (2023)
- [TempME: Towards the Explainability of Temporal Graph Neural Networks via Motif Discovery](https://mlsanity.com/paper/2310.19324/) (2023)
- [CGC: Contrastive Graph Clustering for Community Detection and Tracking](https://mlsanity.com/paper/2204.08504/) (2022)
- [DyTed: Disentangled Representation Learning for Discrete-time Dynamic Graph](https://mlsanity.com/paper/2210.10592/) (2022)
- [Revisiting Modularity Maximization for Graph Clustering: A Contrastive Learning Perspective](https://mlsanity.com/paper/2406.14288/) (2024)
- [TIGER: Temporal Interaction Graph Embedding with Restarts](https://mlsanity.com/paper/2302.06057/) (2023)
- [DyG-Mamba: Continuous State Space Modeling on Dynamic Graphs](https://mlsanity.com/paper/2408.06966/) (2024)
- [Instant Graph Neural Networks for Dynamic Graphs](https://mlsanity.com/paper/2206.01379/) (2022)
- [Subset Node Anomaly Tracking over Large Dynamic Graphs](https://mlsanity.com/paper/2205.09786/) (2022)
- [Graph2text or Graph2token: A Perspective of Large Language Models for Graph Learning](https://mlsanity.com/paper/2501.01124/) (2025)
- [Interpretable Clustering on Dynamic Graphs with Recurrent Graph Neural Networks](https://mlsanity.com/paper/2012.08740/) (2020)
- [Effective Clustering on Large Attributed Bipartite Graphs](https://mlsanity.com/paper/2405.11922/) (2024)
- [Revisiting Dynamic Graph Clustering via Matrix Factorization](https://mlsanity.com/paper/2502.06117/) (2025)
- [Toward Structure Fairness in Dynamic Graph Embedding: A Trend-aware Dual Debiasing Approach](https://mlsanity.com/paper/2406.13201/) (2024)
- [Adaptive Collaborative Similarity Learning for Unsupervised Multi-view Feature Selection](https://mlsanity.com/paper/1904.11228/) (2019)

## Built on by (most cited first, 1 of 1)

- [Distributionally Robust Set Representation Learning Under Inference-Time Element Corruption](https://mlsanity.com/paper/2605.30089/) (2026)

## Abstract (arXiv)

Dynamic graph clustering aims to detect and track time-varying clusters in dynamic graphs, revealing how complex real-world systems evolve over time. However, existing methods are predominantly black-box models. They lack interpretability in their clustering decisions and fail to provide semantic explanations of why clusters form or how they evolve, severely limiting their use in safety-critical domains such as healthcare or transportation. To address these limitations, we propose an end-to-end interpretable framework that maps continuous graph embeddings into discrete semantic concepts through learnable prototypes. Specifically, we first decompose node representations into orthogonal role and clustering subspaces, so that nodes with similar roles (e.g., hubs, bridges) but different cluster affiliations can be properly distinguished. We then introduce five node role prototypes (Leader, Contributor, Wanderer, Connector, Newcomer) in the role subspace as semantic anchors, transforming continuous embeddings into discrete concepts to facilitate LLM understanding of node roles within communities. Finally, we design a hierarchical LLM reasoning mechanism to generate both clustering results and natural language explanations, while providing consistency feedback as weak supervision to refine node representations. Experimental results on four synthetic and six real-world benchmarks demonstrate the effectiveness, interpretability, and robustness of DyG-RoLLM. Code is available at https://github.com/Clearloveyuan/DyG-RoLLM.