loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

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)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.144.88.153

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Wei, W. ; De Schepper, T. and Mets, K. (2024). Benchmarking Sensitivity of Continual Graph Learning for Skeleton-Based Action Recognition. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP; ISBN 978-989-758-679-8; ISSN 2184-4321, SciTePress, pages 639-651. DOI: 10.5220/0012394400003660

@conference{visapp24,
author={Wei Wei and Tom {De Schepper} and Kevin Mets},
title={Benchmarking Sensitivity of Continual Graph Learning for Skeleton-Based Action Recognition},
booktitle={Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP},
year={2024},
pages={639-651},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012394400003660},
isbn={978-989-758-679-8},
issn={2184-4321},
}

TY - CONF

JO - Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP
TI - Benchmarking Sensitivity of Continual Graph Learning for Skeleton-Based Action Recognition
SN - 978-989-758-679-8
IS - 2184-4321
AU - Wei, W.
AU - De Schepper, T.
AU - Mets, K.
PY - 2024
SP - 639
EP - 651
DO - 10.5220/0012394400003660
PB - SciTePress