Scalable Graph Condensation with Evolving Capabilities

2025-02-24

AI Summary

Existing graph condensation methods treat training graphs as static, rendering them ill-suited for dynamically evolving real-world graph data and resulting in inefficient incremental compression. To address this, we propose GECC—the first evolution-aware graph condensation framework—that enables incremental migration of historical condensed graphs to newly arrived graphs via class-aware feature clustering and a traceable centroid inheritance mechanism, thereby avoiding redundant computation. We theoretically establish its convergence and structural fidelity guarantees. Empirical evaluation on large-scale dynamic graphs demonstrates that GECC achieves up to ~1000× speedup in compression time over static baselines while significantly outperforming state-of-the-art (SOTA) methods in downstream task performance. GECC thus introduces an efficient, scalable, and theoretically grounded paradigm for graph condensation in dynamic learning settings.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Data Compression
• Search and Optimization: Evolutionary Computation

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Web Mining and Content Analysis: Models for Web evolution
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

Graph data has become a pivotal modality due to its unique ability to model relational datasets. However, real-world graph data continues to grow exponentially, resulting in a quadratic increase in the complexity of most graph algorithms as graph sizes expand. Although graph condensation (GC) methods have been proposed to address these scalability issues, existing approaches often treat the training set as static, overlooking the evolving nature of real-world graph data. This limitation leads to inefficiencies when condensing growing training sets. In this paper, we introduce GECC (Graph Evolving Clustering Condensation), a scalable graph condensation method designed to handle large-scale and evolving graph data. GECC employs a traceable and efficient approach by performing class-wise clustering on aggregated features. Furthermore, it can inherits previous condensation results as clustering centroids when the condensed graph expands, thereby attaining an evolving capability. This methodology is supported by robust theoretical foundations and demonstrates superior empirical performance. Comprehensive experiments show that GECC achieves better performance than most state-of-the-art graph condensation methods while delivering an around 1,000x speedup on large datasets.

Problem

• Address scalability issues in graph data
• Handle evolving nature of real-world graphs
• Improve efficiency of graph condensation methods

Innovation

• Scalable graph condensation method
• Evolving graph data handling
• Class-wise clustering on features