Line Graph Neural Networks for Link Weight Prediction

TL;DR

This paper introduces LGLWP, a deep learning approach using line graph neural networks to predict link weights in networks, outperforming previous shallow feature-based methods across multiple datasets.

Contribution

The paper presents a novel deep learning framework that directly learns link features via line graph neural networks for improved link weight prediction.

Findings

Outperforms state-of-the-art methods on six diverse network datasets.

Effectively captures deeper graph features for link weight prediction.

Demonstrates superiority over methods using shallow features.

Abstract

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.