基于去偏无损记忆回放的图持续学习
Graph Continual Learning with Debiased Lossless Memory Replay
AI总结：
本文提出图持续学习框架DeLoMe，通过学习无损合成节点表示作为记忆以保护隐私并捕获整体图信息，同时设计去偏损失函数缓解数据不平衡导致的任务偏差，在四个数据集上验证了其有效性。
摘要：
现实生活中的图数据通常会不断扩展，使得在静态图数据上学习图神经网络（GNNs）变得不切实际。图持续学习（GCL）通过持续地将GNNs适配到当前任务的扩展图上，同时保持在先前任务图上的性能，来解决这一问题。基于记忆回放的方法旨在学习新任务时回放先前任务的数据，已被探索作为缓解对先前任务所学知识遗忘的一种原则性方法。在本文中，我们用一个名为Debiased Lossless Memory replay（DeLoMe）的新颖框架扩展了这一方法论。与采样先前图的节点/边来构建记忆的现有方法不同，DeLoMe学习小的无损合成节点表示作为记忆。所学到的记忆不仅能保护图数据隐私，还能捕获整体图信息，而基于采样的方法对此是不可行的。此外，由于记忆数据和当前数据中类别之间的数据不平衡，先前的方法存在偏向当前任务的问题。DeLoMe中设计了一个去偏的GCL损失函数来有效缓解这种偏差。在四个图数据集上的大量实验表明了DeLoMe在类增量和任务增量学习设置下的有效性。
英文摘要：
Real-life graph data often expands continually, rendering the learning of graph neural networks (GNNs) on static graph data impractical. Graph continual learning (GCL) tackles this problem by continually adapting GNNs to the expanded graph of the current task while maintaining the performance over the graph of previous tasks. Memory replay-based methods, which aim to replay data of previous tasks when learning new tasks, have been explored as one principled approach to mitigate the forgetting of the knowledge learned from the previous tasks. In this paper we extend this methodology with a novel framework, called Debiased Lossless Memory replay (DeLoMe). Unlike existing methods that sample nodes/edges of previous graphs to construct the memory, DeLoMe learns small lossless synthetic node representations as the memory. The learned memory can not only preserve the graph data privacy but also capture the holistic graph information, for which the sampling-based methods are not viable. Further, prior methods suffer from bias toward the current task due to the data imbalance between the classes in the memory data and the current data. A debiased GCL loss function is devised in DeLoMe to effectively alleviate this bias. Extensive experiments on four graph datasets show the effectiveness of DeLoMe under both class- and task-incremental learning settings.
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。
