通过整体记忆多样化实现图模型的持续复用
Towards Continuous Reuse of Graph Models via Holistic Memory Diversification
AI总结：
针对图增量学习中记忆多样性不足的问题，提出整体多样化记忆选择与生成（DMSG）框架，通过考虑类内和类间多样性的缓冲区选择策略及变分生成重放方法，有效提升了模型在图上的持续学习能力。
摘要：
本文探讨了在不断增长的图中应对日益复杂任务的增量学习挑战。目标是通过记忆重放，持续训练图模型以处理新任务，同时保持对先前任务的熟练度。现有方法通常忽视记忆多样性的重要性，限制了从先前任务中选择高质量记忆以及在图上稀缺记忆中记住广泛的先前知识。为此，我们引入了一种新颖的用于图增量学习的整体多样化记忆选择与生成（DMSG）框架。该框架首先引入了一种同时考虑类内和类间多样性的缓冲区选择策略，采用高效的贪心算法，在学习每个新任务后将图中具有代表性的训练节点采样到记忆缓冲区中。然后，为了在学习新任务时充分重新记忆保存在记忆缓冲区中的知识，引入了一种多样化记忆生成重放方法。该方法利用变分层生成缓冲区节点嵌入的分布，并采样合成嵌入进行重放。此外，提出了对抗性变分嵌入学习方法和基于重建的解码器，分别以维持合成节点嵌入的完整性并巩固其泛化能力。在公开可访问数据集上的广泛实验结果证明了DMSG优于最先进的方法。
英文摘要：
This paper addresses the challenge of incremental learning in growing graphs with increasingly complex tasks. The goal is to continuously train a graph model to handle new tasks while retaining proficiency in previous tasks via memory replay. Existing methods usually overlook the importance of memory diversity, limiting in selecting high-quality memory from previous tasks and remembering broad previous knowledge within the scarce memory on graphs. To address that, we introduce a novel holistic Diversified Memory Selection and Generation (DMSG) framework for incremental learning in graphs, which first introduces a buffer selection strategy that considers both intra-class and inter-class diversities, employing an efficient greedy algorithm for sampling representative training nodes from graphs into memory buffers after learning each new task. Then, to adequately rememorize the knowledge preserved in the memory buffer when learning new tasks, a diversified memory generation replay method is introduced. This method utilizes a variational layer to generate the distribution of buffer node embeddings and sample synthesized ones for replaying. Furthermore, an adversarial variational embedding learning method and a reconstruction-based decoder are proposed to maintain the integrity and consolidate the generalization of the synthesized node embeddings, respectively. Extensive experimental results on publicly accessible datasets demonstrate the superiority of \method{} over state-of-the-art methods.
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。
