Authors:
Wei Wei
1
;
Tom De Schepper
1
and
Kevin Mets
2
Affiliations:
1
University of Antwerp - imec, IDLab, Department of Computer Science, Sint-Pietersvliet 7, 2000 Antwerp, Belgium
;
2
University of Antwerp - imec, IDLab, Faculty of Applied Engineering, Sint-Pietersvliet 7, 2000 Antwerp, Belgium
Keyword(s):
Continual Graph Learning, Action Recognition, Spatio-Temporal Graph, Sensitivity Analysis, Benchmark.
Abstract:
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 revea
l that task-order robust methods can still be class-order sensitive and observe
results that contradict previous empirical observations on architectural sensitivity in CL.
(More)