Bridging Academia and Industry: A Comprehensive Benchmark for Attributed Graph Clustering

2026-02-09

AI Summary

This work addresses the gap between academic research and industrial practice in attributed graph clustering (AGC), where existing evaluations rely on small-scale, highly homophilic datasets and non-scalable full-batch training that poorly reflect real-world scenarios. To bridge this divide, we propose PyAGC—the first scalable AGC benchmark platform designed for industrial deployment. PyAGC unifies prominent methods under a modular Encode-Cluster-Optimize framework, enabling memory-efficient mini-batch training and distributed scalability while supporting complex tabular features and heterogeneous graph structures. We introduce a benchmark suite of 12 datasets (ranging from 2.7K to 111M nodes), including low-homophily industrial graphs, and establish a comprehensive evaluation protocol combining unsupervised structural metrics with efficiency analysis. The effectiveness of PyAGC is validated in high-stakes applications at Ant Group. The platform is open-sourced to advance reproducible, scalable, and practical AGC research.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Scalability, Parallel & Distributed Systems
• Search and Optimization: Distributed Search

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Attributed Graph Clustering (AGC) is a fundamental unsupervised task that integrates structural topology and node attributes to uncover latent patterns in graph-structured data. Despite its significance in industrial applications such as fraud detection and user segmentation, a significant chasm persists between academic research and real-world deployment. Current evaluation protocols suffer from the small-scale, high-homophily citation datasets, non-scalable full-batch training paradigms, and a reliance on supervised metrics that fail to reflect performance in label-scarce environments. To bridge these gaps, we present PyAGC, a comprehensive, production-ready benchmark and library designed to stress-test AGC methods across diverse scales and structural properties. We unify existing methodologies into a modular Encode-Cluster-Optimize framework and, for the first time, provide memory-efficient, mini-batch implementations for a wide array of state-of-the-art AGC algorithms. Our benchmark curates 12 diverse datasets, ranging from 2.7K to 111M nodes, specifically incorporating industrial graphs with complex tabular features and low homophily. Furthermore, we advocate for a holistic evaluation protocol that mandates unsupervised structural metrics and efficiency profiling alongside traditional supervised metrics. Battle-tested in high-stakes industrial workflows at Ant Group, this benchmark offers the community a robust, reproducible, and scalable platform to advance AGC research towards realistic deployment. The code and resources are publicly available via GitHub (https://github.com/Cloudy1225/PyAGC), PyPI (https://pypi.org/project/pyagc), and Documentation (https://pyagc.readthedocs.io).

Problem

• Attributed Graph Clustering
• benchmark
• industrial deployment
• evaluation protocol
• unsupervised learning

Innovation

• Attributed Graph Clustering
• Mini-batch Training
• Low Homophily
• Industrial Benchmark
• Unsupervised Evaluation