Beyond the Academic Monoculture: A Unified Framework and Industrial Perspective for Attributed Graph Clustering

TL;DR

This paper reviews attributed graph clustering (AGC) from an industrial perspective, proposing a unified framework, critiquing evaluation practices, and offering practical strategies for real-world deployment of AGC methods.

Contribution

It introduces the Encode-Cluster-Optimize framework, critically examines evaluation protocols, and provides actionable strategies for scalable, heterophily-robust AGC in industrial settings.

Findings

Current benchmarks rely heavily on small, homophilous networks.

Supervised metrics are insufficient for evaluating AGC.

Scalability and heterophily are critical challenges in industrial AGC.

Abstract

Attributed Graph Clustering (AGC) is a fundamental unsupervised task that partitions nodes into cohesive groups by jointly modeling structural topology and node attributes. While the advent of graph neural networks and self-supervised learning has catalyzed a proliferation of AGC methodologies, a widening chasm persists between academic benchmark performance and the stringent demands of real-world industrial deployment. To bridge this gap, this survey provides a comprehensive, industrially grounded review of AGC from three complementary perspectives. First, we introduce the Encode-Cluster-Optimize taxonomic framework, which decomposes the diverse algorithmic landscape into three orthogonal, composable modules: representation encoding, cluster projection, and optimization strategy. This unified paradigm enables principled architectural comparisons and inspires novel methodological combinations. Second, we critically examine prevailing evaluation protocols to expose the field's academic monoculture: a pervasive over-reliance on small, homophilous citation networks, the inadequacy of supervised-only metrics for an inherently unsupervised task, and the chronic neglect of computational scalability. In response, we advocate for a holistic evaluation standard that integrates supervised semantic alignment, unsupervised structural integrity, and rigorous efficiency profiling. Third, we explicitly confront the practical realities of industrial deployment. By analyzing operational constraints such as massive scale, severe heterophily, and tabular feature noise alongside extensive empirical evidence from our companion benchmark, we outline actionable engineering strategies. Furthermore, we chart a clear roadmap for future research, prioritizing heterophily-robust encoders, scalable joint optimization, and unsupervised model selection criteria to meet production-grade requirements.