面向基于骨架的动作识别的持续图学习敏感性基准测试
Benchmarking Sensitivity of Continual Graph Learning for Skeleton-Based Action Recognition
AI总结：
本文提出首个面向时空图的持续图学习基准，基于N-UCLA和NTU-RGB+D评估CGL方法，并揭示其类别顺序与架构敏感性。
摘要：
持续学习（CL）是一个研究领域，旨在构建能够在不同任务上持续积累知识而无需从头重新训练的机器学习模型。既往研究表明，对图神经网络（GNN）进行预训练后再微调，可能会导致负迁移（Hu等人，2020），而这一设置与CL密切相关。因此，我们专注于在持续图学习（CGL）设置下研究GNN。我们提出了首个面向时空图的持续图学习基准，并用其在这一新颖设置下对知名CGL方法进行基准测试。该基准基于用于基于骨架动作识别的N-UCLA和NTU-RGB+D数据集。除了对标准性能指标进行基准测试外，我们还研究了CGL方法的类别与任务顺序敏感性，即学习顺序对每个类别/任务性能的影响，以及CGL方法在不同宽度和深度的骨干GNN下的架构敏感性。我们揭示，任务顺序鲁棒的方法仍可能对类别顺序敏感，并观察到与既往关于CL中架构敏感性的经验观察相矛盾的结果。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
