# Graph Clustering with Cross-View Feature Propagation

arXiv: https://arxiv.org/abs/2408.06029 · HTML: https://mlsanity.com/paper/2408.06029/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 84 references that are in the map.
- First posted on arXiv 12 Aug 2024.

## Builds on (most cited first, 8 of 8)

- [Graph Clustering with Graph Neural Networks](https://mlsanity.com/paper/2006.16904/) (2020)
- [Optimizing the Latent Space of Generative Networks](https://mlsanity.com/paper/1707.05776/) (2017)
- [Auto-GNN: Neural Architecture Search of Graph Neural Networks](https://mlsanity.com/paper/1909.03184/) (2019)
- [Community Detection in Networks with Node Attributes](https://mlsanity.com/paper/1401.7267/) (2014)
- [Learning Conjoint Attentions for Graph Neural Nets](https://mlsanity.com/paper/2102.03147/) (2021)
- [Adaptive Graph Auto-Encoder for General Data Clustering](https://mlsanity.com/paper/2002.08648/) (2020)
- [Learning Hierarchical Graph Neural Networks for Image Clustering](https://mlsanity.com/paper/2107.01319/) (2021)
- [Relational Thematic Clustering with Mutually Preferred Neighbors](https://mlsanity.com/paper/2001.08412/) (2020)

## Abstract (arXiv)

Graph clustering is a fundamental and challenging learning task, which is conventionally approached by grouping similar vertices based on edge structure and feature similarity.In contrast to previous methods, in this paper, we investigate how multi-view feature propagation can influence cluster discovery in graph data.To this end, we present Graph Clustering With Cross-View Feature Propagation (GCCFP), a novel method that leverages multi-view feature propagation to enhance cluster identification in graph data.GCCFP employs a unified objective function that utilizes graph topology and multi-view vertex features to determine vertex cluster membership, regularized by a module that supports key latent feature propagation. We derive an iterative algorithm to optimize this function, prove model convergence within a finite number of iterations, and analyze its computational complexity. Our experiments on various real-world graphs demonstrate the superior clustering performance of GCCFP compared to well-established methods, manifesting its effectiveness across different scenarios.