
Graph Continual Learning (GCL) research is hindered by the lack of standardized benchmarks and frameworks, a problem addressed by the introduction of BeGin, a new framework offering diverse scenarios and an easy-to-use structure for robust GCL method development and evaluation.


coremsg

begin-a-comprehensive-benchmark-framework-for-graph-continual-learning-with-extensive-scenarios


BeGin: A Comprehensive Benchmark Framework for Graph Continual Learning with Extensive Scenarios


title_rewrite


Replay buffer selection is crucial in graph continual learning to prevent overfitting and improve model performance.


dslr-diversity-enhancement-and-structure-learning-for-rehearsal-based-graph-continual-learning


DSLR: Diversity Enhancement and Structure Learning for Rehearsal-based Graph Continual Learning



Replay buffer selection in graph continual learning methods is enhanced by considering both class representativeness and diversity within each class of the replayed nodes, leading to improved model performance.


dsl-diversity-enhancement-and-structure-learning-for-rehearsal-based-graph-continual-learning


DSL: Diversity Enhancement and Structure Learning for Rehearsal-based Graph Continual Learning
