Line Graph Neural Networks for Link Weight Prediction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liang, Jinbi, Pu, Cunlai, Shu, Xiangbo, Xia, Yongxiang, Xia, Chengyi
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913565031530496
author Liang, Jinbi
Pu, Cunlai
Shu, Xiangbo
Xia, Yongxiang
Xia, Chengyi
author_facet Liang, Jinbi
Pu, Cunlai
Shu, Xiangbo
Xia, Yongxiang
Xia, Chengyi
contents In real-world networks, predicting the weight (strength) of links is as crucial as predicting the existence of the links themselves. Previous studies have primarily used shallow graph features for link weight prediction, limiting the prediction performance. In this paper, we propose a new link weight prediction method, namely Line Graph Neural Networks for Link Weight Prediction (LGLWP), which learns deeper graph features through deep learning. In our method, we first extract the enclosing subgraph around a target link and then employ a weighted graph labeling algorithm to label the subgraph nodes. Next, we transform the subgraph into the line graph and apply graph convolutional neural networks to learn the node embeddings in the line graph, which can represent the links in the original subgraph. Finally, the node embeddings are fed into a fully-connected neural network to predict the weight of the target link, treated as a regression problem. Our method directly learns link features, surpassing previous methods that splice node features for link weight prediction. Experimental results on six network datasets of various sizes and types demonstrate that our method outperforms state-of-the-art methods.
format Preprint
id arxiv_https___arxiv_org_abs_2309_15728
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Line Graph Neural Networks for Link Weight Prediction
Liang, Jinbi
Pu, Cunlai
Shu, Xiangbo
Xia, Yongxiang
Xia, Chengyi
Social and Information Networks
In real-world networks, predicting the weight (strength) of links is as crucial as predicting the existence of the links themselves. Previous studies have primarily used shallow graph features for link weight prediction, limiting the prediction performance. In this paper, we propose a new link weight prediction method, namely Line Graph Neural Networks for Link Weight Prediction (LGLWP), which learns deeper graph features through deep learning. In our method, we first extract the enclosing subgraph around a target link and then employ a weighted graph labeling algorithm to label the subgraph nodes. Next, we transform the subgraph into the line graph and apply graph convolutional neural networks to learn the node embeddings in the line graph, which can represent the links in the original subgraph. Finally, the node embeddings are fed into a fully-connected neural network to predict the weight of the target link, treated as a regression problem. Our method directly learns link features, surpassing previous methods that splice node features for link weight prediction. Experimental results on six network datasets of various sizes and types demonstrate that our method outperforms state-of-the-art methods.
title Line Graph Neural Networks for Link Weight Prediction
topic Social and Information Networks
url https://arxiv.org/abs/2309.15728