Virtual Node Tuning for Few-shot Node Classification
Virtual Node Tuning for Few-shot Node Classification
复制标题
DOI：
10.1145/3580305.3599541
复制
发表时间：
2023-06
期刊：
影响因子：
--
通讯作者：
Zhen Tan;Ruocheng Guo;Kaize Ding;Huan Liu
中科院分区：
文献类型：
--
作者：
Zhen Tan;Ruocheng Guo;Kaize Ding;Huan Liu
少样本节点分类（FSNC）是图表示学习中的一个挑战，其中每个类别只有少数标记节点可用于训练。为了解决这个问题，元学习已被提出用于将结构知识从具有丰富标签的基础类别转移到目标新类别。然而，当基础类别没有或只有有限的标记节点时，现有的解决方案变得无效或不适用。为了应对这一挑战，我们提出了一种名为虚拟节点调整（VNT）的创新方法。我们的方法利用预训练的图变换器作为编码器，并在嵌入空间中注入虚拟节点作为软提示，这些虚拟节点可以通过新类别中的少样本标签进行优化，以便为每个特定的FSNC任务调整节点嵌入。VNT的一个独特特点是，通过结合基于图的伪提示进化（GPPE）模块，VNT - GPPE可以处理基础类别中标签稀疏的情况。在四个数据集上的实验结果表明，所提出的方法在处理具有未标记或稀疏标记基础类别的FSNC问题上具有优势，优于现有的最先进方法，甚至优于完全监督的基线方法。
Few-shot Node Classification (FSNC) is a challenge in graph representation learning where only a few labeled nodes per class are available for training. To tackle this issue, meta-learning has been proposed to transfer structural knowledge from base classes with abundant labels to target novel classes. However, existing solutions become ineffective or inapplicable when base classes have no or limited labeled nodes. To address this challenge, we propose an innovative method dubbed Virtual Node Tuning (VNT). Our approach utilizes a pretrained graph transformer as the encoder and injects virtual nodes as soft prompts in the embedding space, which can be optimized with few-shot labels in novel classes to modulate node embeddings for each specific FSNC task. A unique feature of VNT is that, by incorporating a Graph-based Pseudo Prompt Evolution (GPPE) module, VNT-GPPE can handle scenarios with sparse labels in base classes. Experimental results on four datasets demonstrate the superiority of the proposed approach in addressing FSNC with unlabeled or sparsely labeled base classes, outperforming existing state-of-the-art methods and even fully supervised baselines.