无需存储旧数据，实现多模态图数据的持续学习。
MCIGLE: Multimodal Exemplar-Free Class-Incremental Graph Learning
- 通过多模态特征提取与对齐，避免遗忘旧知识。
- 采用递归最小二乘法提升知识保留效率。
- 适合长期更新的多模态图数据场景。
无示例类增量学习使模型能在不存储旧数据的情况下持续学习新类别。随着多模态图结构数据日益普及，现有方法面临灾难性遗忘、分布偏移、内存限制和泛化能力弱等挑战。本文提出MCIGLE框架，通过提取并对齐多模态图特征，结合串联递归最小二乘法实现有效知识保留。通过多通道处理，该方法在准确率与记忆保持间取得平衡。在多个公开数据集上的实验验证了其有效性与泛化能力。
原文摘要 · Abstract (English)
Exemplar-free class-incremental learning enables models to learn new classes over time without storing data from old ones. As multimodal graph-structured data becomes increasingly prevalent, existing methods struggle with challenges like catastrophic forgetting, distribution bias, memory limits, and weak generalization. We propose MCIGLE, a novel framework that addresses these issues by extracting and aligning multimodal graph features and applying Concatenated Recursive Least Squares for effective knowledge retention. Through multi-channel processing, MCIGLE balances accuracy and memory preservation. Experiments on public datasets validate its effectiveness and generalizability.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。