arXiv 2504.136912025-08-20cs.LG

MEGA：用于GFSCIL中灾难性遗忘缓解的二阶梯度对齐

MEGA: Second-Order Gradient Alignment for Catastrophic Forgetting Mitigation in GFSCIL

Beijing Institute of Technology（北京理工大学）；Department of Biomedical Engineering, Hefei University of Technology（合肥工业大学生物医学工程学院）；School of Artificial Intelligence and Computer Science, Nantong University（南通大学人工智能与计算机科学学院）；Faculty of Data Science, City University of Macau（澳门城市大学数据科学学院）；Beijing Academy of Artificial Intelligence（北京人工智能研究院）

Jinhui Pang, Changqing Lin, Hao Lin, Zhihui Zhang, Weiping Ding, Yu Liu, Xiaoshuai Hao

备注：: Under Review

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对图少样本类增量学习（GFSCIL）中现有基于原型网络方法的不足，提出MEGA范式，通过二阶梯度对齐技术缓解灾难性遗忘，在排除查询集的严谨设置下提升性能并增强GCL方法有效性。

摘要：

图少样本类增量学习（GFSCIL）使模型能够在大型基础数据集上完成初始训练后，从新任务的有限样本中持续学习。现有GFSCIL方法通常利用原型网络（PNs）获取基于度量的类表示，并在增量学习阶段微调模型。然而，这些基于PN的方法通过新查询集微调过度简化了学习过程，且因架构限制未能整合图持续学习（GCL）技术。为应对这些挑战，我们提出更严谨实用的GFSCIL设置，在增量训练阶段排除查询集。基于此，我们引入模型无关的元图持续学习（MEGA），旨在有效缓解GFSCIL中的灾难性遗忘。具体而言，通过在元训练阶段计算增量二阶梯度，使模型学习高质量先验，通过对齐元训练和增量学习阶段的行为提升增量学习效果。在四个主流图数据集上的大量实验表明，MEGA取得了最先进的结果，并增强了多种GCL方法在GFSCIL中的有效性。我们认为，所提出的MEGA可作为模型无关的GFSCIL范式，为未来研究铺路。

英文摘要：

Graph Few-Shot Class-Incremental Learning (GFSCIL) enables models to continually learn from limited samples of novel tasks after initial training on a large base dataset. Existing GFSCIL approaches typically utilize Prototypical Networks (PNs) for metric-based class representations and fine-tune the model during the incremental learning stage. However, these PN-based methods oversimplify learning via novel query set fine-tuning and fail to integrate Graph Continual Learning (GCL) techniques due to architectural constraints. To address these challenges, we propose a more rigorous and practical setting for GFSCIL that excludes query sets during the incremental training phase. Building on this foundation, we introduce Model-Agnostic Meta Graph Continual Learning (MEGA), aimed at effectively alleviating catastrophic forgetting for GFSCIL. Specifically, by calculating the incremental second-order gradient during the meta-training stage, we endow the model to learn high-quality priors that enhance incremental learning by aligning its behaviors across both the meta-training and incremental learning stages. Extensive experiments on four mainstream graph datasets demonstrate that MEGA achieves state-of-the-art results and enhances the effectiveness of various GCL methods in GFSCIL. We believe that our proposed MEGA serves as a model-agnostic GFSCIL paradigm, paving the way for future research.

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。