Benchmarking Sensitivity of Continual Graph Learning for Skeleton-Based Action Recognition

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wei, Wei, De Schepper, Tom, Mets, Kevin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916286689181696
author Wei, Wei
De Schepper, Tom
Mets, Kevin
author_facet Wei, Wei
De Schepper, Tom
Mets, Kevin
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2401_18054
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Benchmarking Sensitivity of Continual Graph Learning for Skeleton-Based Action Recognition
Wei, Wei
De Schepper, Tom
Mets, Kevin
Computer Vision and Pattern Recognition
Machine Learning
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.
title Benchmarking Sensitivity of Continual Graph Learning for Skeleton-Based Action Recognition
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2401.18054