弱监督下渐进式学习新图类别，支持少样本甚至无样本场景。
GOTHAM: Graph Class Incremental Learning Framework under Weak Supervision
- 基于原型匹配与知识蒸馏，实现弱监督下的图分类增量学习。
- 在Cora-ML、Amazon等数据集上，零样本与少样本场景下仍保持高准确率。
- 适合动态演化图数据的持续学习，如社交网络、电商推荐系统。
图数据正快速增长，其标签类别也不断扩展。在电商、医疗、推荐系统和社交媒体中，图结构能有效捕捉节点间的结构与属性信息，因此被广泛用于节点分类任务。然而，在实际应用中，新类别常以少量甚至无标签形式出现。传统方法依赖大量标注数据，难以满足需求。本文提出在弱监督下进行图类别增量学习（GCL）的新范式：通过少量标注的基类进行元训练，后续在增量流中支持少样本或零样本的新类别。所提出的GOTHAM框架利用属性空间中的最近原型表示来处理未标记节点，并针对文本属性图（TAGs）引入语义信息增强表征。通过教师-学生知识蒸馏缓解遗忘问题。在Cora-ML、Amazon、OBGN-Arxiv等数据集上的实验表明，该方法在有限监督条件下仍具优异性能。代码已开源。
原文摘要 · Abstract (English)
Graphs are growing rapidly, along with the number of distinct label categories associated with them. Applications like e-commerce, healthcare, recommendation systems, and various social media platforms are rapidly moving towards graph representation of data due to their ability to capture both structural and attribute information. One crucial task in graph analysis is node classification, where unlabeled nodes are categorized into predefined classes. In practice, novel classes appear incrementally sometimes with just a few labels (seen classes) or even without any labels (unseen classes), either because they are new or haven't been explored much. Traditional methods assume abundant labeled data for training, which isn't always feasible. We investigate a broader objective: \emph{Graph Class Incremental Learning under Weak Supervision (GCL)}, addressing this challenge by meta-training on base classes with limited labeled instances. During the incremental streams, novel classes can have few-shot or zero-shot representation. Our proposed framework GOTHAM efficiently accommodates these unlabeled nodes by finding the closest prototype representation, serving as class representatives in the attribute space. For Text-Attributed Graphs (TAGs), our framework additionally incorporates semantic information to enhance the representation. By employing teacher-student knowledge distillation to mitigate forgetting, GOTHAM achieves promising results across various tasks. Experiments on datasets such as Cora-ML, Amazon, and OBGN-Arxiv showcase the effectiveness of our approach in handling evolving graph data under limited supervision. The repository is available here: \href{https://github.com/adityashahane10/GOTHAM--Graph-based-Class-Incremental-Learning-Framework-under-Weak-Supervision}{\small \textcolor{blue}{Code}}
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。