Saved in:
Bibliographic Details
Main Authors: Ling, Chen, Li, Zhuofeng, Hu, Yuntong, Zhang, Zheng, Liu, Zhongyuan, Zheng, Shuang, Pei, Jian, Zhao, Liang
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.16606
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929594512179200
author Ling, Chen
Li, Zhuofeng
Hu, Yuntong
Zhang, Zheng
Liu, Zhongyuan
Zheng, Shuang
Pei, Jian
Zhao, Liang
author_facet Ling, Chen
Li, Zhuofeng
Hu, Yuntong
Zhang, Zheng
Liu, Zhongyuan
Zheng, Shuang
Pei, Jian
Zhao, Liang
contents Textual-edge Graphs (TEGs), characterized by rich text annotations on edges, are increasingly significant in network science due to their ability to capture rich contextual information among entities. Existing works have proposed various edge-aware graph neural networks (GNNs) or let language models directly make predictions. However, they often fall short of fully capturing the contextualized semantics on edges and graph topology, respectively. This inadequacy is particularly evident in link prediction tasks that require a comprehensive understanding of graph topology and semantics between nodes. In this paper, we present a novel framework - Link2Doc, designed especially for link prediction on textual-edge graphs. Specifically, we propose to summarize neighborhood information between node pairs as a human-written document to preserve both semantic and topology information. A self-supervised learning model is then utilized to enhance GNN's text-understanding ability from language models. Empirical evaluations, including link prediction, edge classification, parameter analysis, runtime comparison, and ablation studies, on four real-world datasets demonstrate that Link2Doc achieves generally better performance against existing edge-aware GNNs and pre-trained language models in predicting links on TEGs.
format Preprint
id arxiv_https___arxiv_org_abs_2405_16606
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Link Prediction on Textual Edge Graphs
Ling, Chen
Li, Zhuofeng
Hu, Yuntong
Zhang, Zheng
Liu, Zhongyuan
Zheng, Shuang
Pei, Jian
Zhao, Liang
Social and Information Networks
Textual-edge Graphs (TEGs), characterized by rich text annotations on edges, are increasingly significant in network science due to their ability to capture rich contextual information among entities. Existing works have proposed various edge-aware graph neural networks (GNNs) or let language models directly make predictions. However, they often fall short of fully capturing the contextualized semantics on edges and graph topology, respectively. This inadequacy is particularly evident in link prediction tasks that require a comprehensive understanding of graph topology and semantics between nodes. In this paper, we present a novel framework - Link2Doc, designed especially for link prediction on textual-edge graphs. Specifically, we propose to summarize neighborhood information between node pairs as a human-written document to preserve both semantic and topology information. A self-supervised learning model is then utilized to enhance GNN's text-understanding ability from language models. Empirical evaluations, including link prediction, edge classification, parameter analysis, runtime comparison, and ablation studies, on four real-world datasets demonstrate that Link2Doc achieves generally better performance against existing edge-aware GNNs and pre-trained language models in predicting links on TEGs.
title Link Prediction on Textual Edge Graphs
topic Social and Information Networks
url https://arxiv.org/abs/2405.16606