Community aware method improves continual graph learning without storing old data
CoPE-CGL: Community-aware Prototype Extraction for Replay-Free Continual Graph Learning
Machine LearningDatabases
Summary
Graphs can change over time, making it hard for computer programs to keep learning without forgetting past information. The authors propose CoPE-CGL, a way to remember important graph patterns without saving old data. Their approach uses community structures inside graphs and matches new data to these patterns, working fast and avoiding forgetting. Tests on popular graph datasets show it performs as well or better than methods that rely on storing past graph parts or knowing the task beforehand.
What this means in practice
- •For graph data engineers: Maintain updated graph models that adapt over time without needing to store previous graphs or task labels for ongoing inference.
- •For social network platform developers: Use community-aware prototypes to improve real-time analysis of evolving social graphs while reducing memory and computation costs.
Authors
Bo-Young Lim, Seokhwan Kim, Kisung Lee, Hyuk-Yoon Kwon
Abstract
Continual graph learning (CGL) maintains models as graphs evolve without retraining from scratch, while mitigating catastrophic forgetting. Existing methods typically target either transductive or inductive settings and often store past subgraphs or require task identifiers at inference. We propose Community-aware Prototype Extraction for Continual Graph Learning (CoPE-CGL), a replay-free framework that uses a parameter-free structural prior, precomputed by multi-hop Laplacian smoothing, to anchor learning, memory, and inference. CoPE-CGL combines topology-infused bottleneck adaptation, community-level prototypes, and dynamic routing by majority vote over node-to-prototype matches. The default protocol assumes each test graph comes from one learned task; a node-level variant handles mixed-task graphs. Each task adds at most a constant amount of storage, with no past graph data retained. At equal storage and without task identifiers, CoPE-CGL matches the strongest replay baseline even when it receives true task identifiers: average performance (AP) is 95.17% and 95.72% versus 94.28% and 95.82% on Arxiv and CoraFull, respectively, with 5.9-14.0 times faster runtime and zero forgetting. Across four transductive and three inductive benchmarks and mixed streams, CoPE-CGL exceeds the second-best of up to eleven baselines by up to 1.41, 6.32, and 9.33 AP percentage points, respectively. It runs 1.3-7.9 times faster end-to-end than the most accurate competitor on each benchmark and scales to the largest benchmark graph. On graphs mixing two tasks, its node-level variant achieves the best AP among CGL methods. The design targets homophilic graphs with community structure.