发表机构
Universidade Federal de Ouro Preto（欧鲁普雷图联邦大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出HCPN-GCN，用图卷积网络替换线性提取器并引入锥原型与多样性正则化，在六个基准上提升持续图学习准确率且遗忘近零，原型数减少约30倍。
AI 中文摘要
持续图学习（CGL）旨在从图结构数据中增量学习，同时保留从先前任务中获得的知识。该设置中的一个主要挑战是灾难性遗忘，即学习新任务会降低对先前学习任务的性能。层次原型网络（HPNs）通过基于原型的记忆机制解决了这一问题，该机制避免了存储历史数据，但其对线性特征提取器的依赖限制了其利用图拓扑的能力，而基于点的原型通常会导致在结构多样的图上原型增长效率低下。在这项工作中，我们提出了HCPN-GCN，一种图感知的HPN扩展，它将原始线性特征提取器替换为图卷积网络（GCNs），并引入了基于锥的原型以及多样性正则化目标。所提出的设计产生了更丰富的图感知表示，同时紧凑地建模嵌入空间，减少了原型增殖而不牺牲判别性。在六个持续图学习基准上的实验结果表明，HCPN-GCN在平均分类准确率上持续优于原始HPN和代表性的持续学习基线，同时保持接近零的遗忘。此外，我们的分析表明，所提出的模型使用比原始HPN少约30倍的原子原型学习了更丰富的类级原型层次结构，为持续图学习提供了更紧凑且有效的记忆表示。
英文摘要
Continual Graph Learning (CGL) aims to incrementally learn from graph-structured data while preserving knowledge acquired from previous tasks. A major challenge in this setting is catastrophic forgetting, where learning new tasks degrades performance on previously learned ones. Hierarchical Prototype Networks (HPNs) address this problem through a prototype-based memory mechanism that avoids storing historical data, but their reliance on linear feature extractors limits their ability to exploit graph topology, while point-based prototypes often lead to inefficient prototype growth on structurally diverse graphs. In this work, we propose HCPN-GCN, a graph-aware extension of HPN that replaces the original linear feature extractors with Graph Convolutional Networks (GCNs) and introduces cone-based prototypes with a diversity regularization objective. The proposed design produces richer graph-aware representations while compactly modeling the embedding space, reducing prototype proliferation without sacrificing discriminability. Experimental results on six continual graph learning benchmarks demonstrate that HCPN-GCN consistently improves average classification accuracy over the original HPN and representative continual learning baselines while maintaining near-zero forgetting. Furthermore, our analysis shows that the proposed model learns substantially richer class-level prototype hierarchies using approximately $30\times$ fewer atomic prototypes than the original HPN, providing a more compact and effective memory representation for continual graph learning.
