arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.07091cs.LGcs.AIcs.CL
收藏

节点级图自编码器:文本图学习的统一预训练

Node Level Graph Autoencoder: Unified Pretraining for Textual Graph Learning

Hong Kong University of Science and Technology(香港科技大学)

Wenbin Hu, Huihao Jing, Qi Hu, Haoran Li, Yangqiu Song

AI总结:

提出节点级图自编码器(NodeGAE),一种统一的无监督预训练框架,利用语言模型进行文本重建并添加辅助损失以感知图结构,在节点分类和链接预测任务上显著提升多种GNN的性能。

摘要:

文本图在现实应用中无处不在,其特点是具有丰富文本信息和复杂关系,这促进了各个领域的先进研究。文本图表示学习旨在从文本图中生成低维特征嵌入,以提高下游任务的性能。高质量的特征嵌入应有效捕获文本图中的结构和文本信息。然而,大多数文本图数据集基准依赖word2vec技术生成特征嵌入,这固有地限制了其能力。近期关于文本图表示学习的工作可分为两类:监督和无监督方法。监督方法在标记节点上微调语言模型,当标记数据稀缺时其能力有限。另一方面,无监督方法通过开发复杂的训练流程提取特征嵌入。为解决这些局限性,我们提出了一种新颖的统一无监督学习自编码器框架,名为节点级图自编码器(NodeGAE)。我们采用语言模型作为自编码器的骨干,并在文本重建上进行预训练。此外,我们添加了一个辅助损失项,使特征嵌入感知局部图结构。我们的方法保持了训练过程的简单性,并展示了在多样文本图和下游任务中的泛化能力。我们在两个核心图表示学习下游任务上评估了我们的方法:节点分类和链接预测。综合实验表明,我们的方法显著提升了多种图神经网络(GNN)在多个文本图数据集上的性能。

英文摘要:

Textual graphs are ubiquitous in real-world applications, featuring rich text information with complex relationships, which enables advanced research across various fields. Textual graph representation learning aims to generate low-dimensional feature embeddings from textual graphs that can improve the performance of downstream tasks. A high-quality feature embedding should effectively capture both the structural and the textual information in a textual graph. However, most textual graph dataset benchmarks rely on word2vec techniques to generate feature embeddings, which inherently limits their capabilities. Recent works on textual graph representation learning can be categorized into two folds: supervised and unsupervised methods. Supervised methods finetune a language model on labeled nodes, which have limited capabilities when labeled data is scarce. Unsupervised methods, on the other hand, extract feature embeddings by developing complex training pipelines. To address these limitations, we propose a novel unified unsupervised learning autoencoder framework, named Node Level Graph AutoEncoder (NodeGAE). We employ language models as the backbone of the autoencoder, with pretraining on text reconstruction. Additionally, we add an auxiliary loss term to make the feature embeddings aware of the local graph structure. Our method maintains simplicity in the training process and demonstrates generalizability across diverse textual graphs and downstream tasks. We evaluate our method on two core graph representation learning downstream tasks: node classification and link prediction. Comprehensive experiments demonstrate that our approach substantially enhances the performance of diverse graph neural networks (GNNs) across multiple textual graph 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。

↑