A Selective Learning Method for Temporal Graph Continual Learning

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 show that LTF effectively addresses the TGCL challenge.

Many real-world networks—like social media or online marketplaces—change over time. Our research was motivated by a challenge faced in these dynamic systems: traditional models assume a fixed set of categories, but over time, new categories arise while old ones evolve. To address this, we developed a method called Learning Towards the Future (LTF) that smartly selects and updates a small, representative subset of old data instead of retraining with the full dataset. This selective approach reduces costly computations, avoids losing important information on older categories, and maintains an up-to-date model in environments where data is continuously changing. Our experiments using real-world datasets show that LTF effectively preserves accuracy and adapts over time, ensuring better performance in dynamic settings.