免回放且免遗忘的图类别增量学习：一种任务分析与提示方法
Replay-and-Forget-Free Graph Class-Incremental Learning: A Task Profiling and Prompting Approach
AI总结：
针对图类别增量学习中的任务识别与灾难性遗忘问题，提出基于拉普拉斯平滑的任务原型分析和逐任务图提示方法，实现100%任务ID预测、免回放免遗忘，并较SOTA平均准确率提升至少18%。
摘要：
类别增量学习（CIL）旨在持续学习一系列任务，其中每个任务由一组独特类别组成。图 CIL（GCIL）遵循相同设定，但需要处理图任务（例如图中的节点分类）。CIL 的关键特征在于推理阶段不存在任务标识符（ID），这给区分来自不同任务的类别（即任务间类别分离）带来了重大挑战。能够准确预测任务 ID 有助于解决该问题，但这是一个具有挑战性的问题。本文从理论上表明，通过基于拉普拉斯平滑的图任务分析方法，可以在图数据上实现准确的任务 ID 预测；在该方法中，每个图任务都基于对图的拉普拉斯平滑由一个任务原型建模。该方法保证：在较大平滑步数下，同一图任务的任务原型几乎相同，而不同任务的任务原型则因图结构和节点属性的差异而彼此不同。此外，为避免灾难性遗忘先前图任务中学习到的知识，我们提出了一种用于 GCIL 的新型图提示方法，该方法为每个任务学习一个小型判别性图提示，本质上为每个任务生成一个独立的分类模型。提示学习只需要在第一个任务上训练单个图神经网络（GNN）一次，此后不需要任何数据回放，从而得到一个既免回放又免遗忘的 GCIL 模型。在四个 GCIL 基准上的大量实验表明：i）我们基于任务原型的方法能够在全部四个数据集上实现 100% 的任务 ID 预测准确率；ii）我们的 GCIL 模型在平均 CIL 准确率上显著优于最先进的竞争方法至少 18%；iii）我们的模型在四个数据集上完全不存在遗忘。
英文摘要：
Class-incremental learning (CIL) aims to continually learn a sequence of tasks, with each task consisting of a set of unique classes. Graph CIL (GCIL) follows the same setting but needs to deal with graph tasks (e.g., node classification in a graph). The key characteristic of CIL lies in the absence of task identifiers (IDs) during inference, which causes a significant challenge in separating classes from different tasks (i.e., inter-task class separation). Being able to accurately predict the task IDs can help address this issue, but it is a challenging problem. In this paper, we show theoretically that accurate task ID prediction on graph data can be achieved by a Laplacian smoothing-based graph task profiling approach, in which each graph task is modeled by a task prototype based on Laplacian smoothing over the graph. It guarantees that the task prototypes of the same graph task are nearly the same with a large smoothing step, while those of different tasks are distinct due to differences in graph structure and node attributes. Further, to avoid the catastrophic forgetting of the knowledge learned in previous graph tasks, we propose a novel graph prompting approach for GCIL which learns a small discriminative graph prompt for each task, essentially resulting in a separate classification model for each task. The prompt learning requires the training of a single graph neural network (GNN) only once on the first task, and no data replay is required thereafter, thereby obtaining a GCIL model being both replay-free and forget-free. Extensive experiments on four GCIL benchmarks show that i) our task prototype-based method can achieve 100% task ID prediction accuracy on all four datasets, ii) our GCIL model significantly outperforms state-of-the-art competing methods by at least 18% in average CIL accuracy, and iii) our model is fully free of forgetting on the four datasets.
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。
