Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

10-2024

Abstract

Real-life graph data often expands continually, rendering the learning of graph neural networks (GNNs) on static graph data impractical. Graph continual learning (GCL) tackles this problem by continually adapting GNNs to the expanded graph of the current task while maintaining the performance over the graph of previous tasks. Memory replay-based methods, which aim to replay data of previous tasks when learning new tasks, have been explored as one principled approach to mitigate the forgetting of the knowledge learned from the previous tasks. In this paper we extend this methodology with a novel framework, called Debiased Lossless Memory replay (DeLoMe). Unlike existing methods that sample nodes/edges of previous graphs to construct the memory, DeLoMe learns small lossless synthetic node representations as the memory. The learned memory can not only preserve the graph data privacy but also capture the holistic graph information, for which the samplingbased methods are not viable. Further, prior methods suffer from bias toward the current task due to the data imbalance between the classes in the memory data and the current data. A debiased GCL loss function is devised in DeLoMe to effectively alleviate this bias. Extensive experiments on four graph datasets show the effectiveness of DeLoMe under both class- and task-incremental learning settings.

Discipline

Graphics and Human Computer Interfaces

Research Areas

Intelligent Systems and Optimization

Areas of Excellence

Digital transformation

Publication

Proceedings of the 27th European Conference on Artificial Intelligence (ECAI 2024) Including 13th Conference on Prestigious Applications of Intelligent Systems (PAIS 2024) : Santiago de Compostela, Spain, October 19-24

Volume

392

First Page

1808

Last Page

1815

Identifier

10.3233/FAIA240692

Publisher

IOS Press

City or Country

Santiago de Compostela

Additional URL

https://doi.org/10.3233/FAIA240692

Download

Share

COinS