近日，实验室王治政博士关于图表示学习的研究成果被人工智能领域顶级期刊Pattern Recognition (PR)录用，Pattern Recognition为CCF推荐期刊B类，中科院一区期刊，影响因子7.5。

Title: Continual Learning with High-order Experience Replay for Dynamic Network Embedding

Abstract: Dynamic network embedding (DNE) poses a tough challenge in graph representation learning, especially when confronted with the frequent updates of streaming data. Conventional DNEs primarily resort to parameter updating, but perform inadequately on historical networks, resulting in the problem of catastrophic forgetting. To tackle such issues, recent advancements in graph neural networks (GNNs) have explored matrix factorization techniques. However, these approaches encounter difficulties in preserving the global patterns of incremental data. In this paper, we propose CLDNE, a Continual Learning framework specifically designed for Dynamic Network Embedding. At the core of CLDNE lies a streaming graph auto-encoder that effectively captures both global and local patterns of the input graph. To further overcome catastrophic forgetting, CLDNE is equipped with an experience replay buffer and a knowledge distillation module, which preserves high-order historical topology and static historical patterns. We conduct experiments on four dynamic networks using link prediction and node classification tasks to evaluate the effectiveness of CLDNE. The outcomes demonstrate that CLDNE successfully mitigates the catastrophic forgetting problem and reduces training time by 80% without a significant loss in learning new patterns.

题目：用于动态网络嵌入的基于高阶经验重放的持续学习

摘要：动态网络嵌入 (DNE) 是图表示学习任务中的一项严峻挑战，尤其是在面对流数据的频繁更新时。传统的 DNE 主要依靠参数更新策略，但却在历史网络上表现不佳，通常导致灾难性遗忘的问题。为了解决此类问题，图神经网络 (GNN) 的最新进展探索了矩阵分解技术在DNE上的应用。然而，这些方法在保留增量数据的全局模式方面遇到了困难。在本文中，我们提出了 CLDNE，一个专门为动态网络嵌入设计的持续学习框架。CLDNE 的核心是一个“流式”图自动编码器，它可以有效地捕获输入图的全局和局部模式。为了进一步克服灾难性遗忘，CLDNE 配备了经验重放缓冲区和知识蒸馏模块，可以保留高阶历史拓扑和静态历史模式。我们使用链接预测和节点分类任务在四个动态网络上进行实验，以评估 CLDNE 的有效性。结果表明，CLDNE 成功缓解了灾难性遗忘问题，并与模型重训策略相比，训练时间减少了近80%，并且在学习新模式时没有造成重大损失。