Benchmarking Sensitivity of Continual Graph Learning for Skeleton-Based Action Recognition
This work addresses the challenge of continual learning for graph-based action recognition, which is incremental as it benchmarks existing methods in a new setting.
The authors tackled the problem of continual learning for spatio-temporal graphs in skeleton-based action recognition by proposing the first benchmark for this setting and using it to evaluate existing methods, revealing that task-order robust methods can still be class-order sensitive and contradicting previous observations on architectural sensitivity.
Continual learning (CL) is the research field that aims to build machine learning models that can accumulate knowledge continuously over different tasks without retraining from scratch. Previous studies have shown that pre-training graph neural networks (GNN) may lead to negative transfer (Hu et al., 2020) after fine-tuning, a setting which is closely related to CL. Thus, we focus on studying GNN in the continual graph learning (CGL) setting. We propose the first continual graph learning benchmark for spatio-temporal graphs and use it to benchmark well-known CGL methods in this novel setting. The benchmark is based on the N-UCLA and NTU-RGB+D datasets for skeleton-based action recognition. Beyond benchmarking for standard performance metrics, we study the class and task-order sensitivity of CGL methods, i.e., the impact of learning order on each class/task's performance, and the architectural sensitivity of CGL methods with backbone GNN at various widths and depths. We reveal that task-order robust methods can still be class-order sensitive and observe results that contradict previous empirical observations on architectural sensitivity in CL.