A Selective Learning Method for Temporal Graph Continual Learning
This addresses the challenge of efficiently updating models for temporal graphs with evolving classes, which is incremental as it builds on existing graph continual learning methods.
The paper tackles the problem of node classification in temporal graphs where new classes emerge over time, proposing a selective learning framework called LTF that minimizes classification error while preserving old-class knowledge, achieving validated effectiveness on three real-world datasets.
Node classification is a key task in temporal graph learning (TGL). Real-life temporal graphs often introduce new node classes over time, but existing TGL methods assume a fixed set of classes. This assumption brings limitations, as updating models with full data is costly, while focusing only on new classes results in forgetting old ones. Graph continual learning (GCL) methods mitigate forgetting using old-class subsets but fail to account for their evolution. We define this novel problem as temporal graph continual learning (TGCL), which focuses on efficiently maintaining up-to-date knowledge of old classes. To tackle TGCL, we propose a selective learning framework that substitutes the old-class data with its subsets, Learning Towards the Future (LTF). We derive an upper bound on the error caused by such replacement and transform it into objectives for selecting and learning subsets that minimize classification error while preserving the distribution of the full old-class data. Experiments on three real-world datasets validate the effectiveness of LTF on TGCL.