Online Continual Graph Learning

2025-08-05

AI Summary

To address the lack of formal definition and systematic investigation into online continual learning for dynamic graph data streams, this paper introduces the first formal characterization of “online continual graph learning,” emphasizing topology-aware batch efficiency and real-time prediction capability. We propose a unified framework that tightly integrates graph neural networks with continual learning mechanisms, enabling incremental task learning under non-i.i.d. graph stream distributions while mitigating catastrophic forgetting. Furthermore, we construct the first standardized benchmark—comprising diverse real-world graph streams and a unified evaluation protocol—to rigorously assess mainstream continual learning methods in graph streaming settings. This work bridges critical gaps in theoretical modeling, algorithmic design, and empirical evaluation, establishing foundational principles for sustainable online graph learning.

Technology Category

• Machine Learning: Life-Long and Continual Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Game Theory and Economic Paradigms: Adversarial Learning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

The aim of Continual Learning (CL) is to learn new tasks incrementally while avoiding catastrophic forgetting. Online Continual Learning (OCL) specifically focuses on learning efficiently from a continuous stream of data with shifting distribution. While recent studies explore Continual Learning on graphs exploiting Graph Neural Networks (GNNs), only few of them focus on a streaming setting. Yet, many real-world graphs evolve over time, often requiring timely and online predictions. Current approaches, however, are not well aligned with the standard OCL setting, partly due to the lack of a clear definition of online Continual Learning on graphs. In this work, we propose a general formulation for online Continual Learning on graphs, emphasizing the efficiency requirements on batch processing over the graph topology, and providing a well-defined setting for systematic model evaluation. Finally, we introduce a set of benchmarks and report the performance of several methods in the CL literature, adapted to our setting.

Problem

• Defining online continual learning for evolving graphs
• Addressing catastrophic forgetting in graph neural networks
• Evaluating models in streaming graph learning scenarios

Innovation

• Proposes online Continual Learning for evolving graphs
• Emphasizes efficient batch processing on graph topology
• Introduces benchmarks for systematic model evaluation