Can GNNs Learn Link Heuristics? A Concise Review and Evaluation of Link Prediction Methods

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liang, Shuming, Ding, Yu, Li, Zhidong, Liang, Bin, Zhang, Siqi, Wang, Yang, Chen, Fang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908695924834304
author Liang, Shuming
Ding, Yu
Li, Zhidong
Liang, Bin
Zhang, Siqi
Wang, Yang
Chen, Fang
author_facet Liang, Shuming
Ding, Yu
Li, Zhidong
Liang, Bin
Zhang, Siqi
Wang, Yang
Chen, Fang
contents This paper explores the ability of Graph Neural Networks (GNNs) in learning various forms of information for link prediction, alongside a brief review of existing link prediction methods. Our analysis reveals that GNNs cannot effectively learn structural information related to the number of common neighbors between two nodes, primarily due to the nature of set-based pooling of the neighborhood aggregation scheme. Also, our extensive experiments indicate that trainable node embeddings can improve the performance of GNN-based link prediction models. Importantly, we observe that the denser the graph, the greater such the improvement. We attribute this to the characteristics of node embeddings, where the link state of each link sample could be encoded into the embeddings of nodes that are involved in the neighborhood aggregation of the two nodes in that link sample. In denser graphs, every node could have more opportunities to attend the neighborhood aggregation of other nodes and encode states of more link samples to its embedding, thus learning better node embeddings for link prediction. Lastly, we demonstrate that the insights gained from our research carry important implications in identifying the limitations of existing link prediction methods, which could guide the future development of more robust algorithms.
format Preprint
id arxiv_https___arxiv_org_abs_2411_14711
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Can GNNs Learn Link Heuristics? A Concise Review and Evaluation of Link Prediction Methods
Liang, Shuming
Ding, Yu
Li, Zhidong
Liang, Bin
Zhang, Siqi
Wang, Yang
Chen, Fang
Social and Information Networks
Machine Learning
This paper explores the ability of Graph Neural Networks (GNNs) in learning various forms of information for link prediction, alongside a brief review of existing link prediction methods. Our analysis reveals that GNNs cannot effectively learn structural information related to the number of common neighbors between two nodes, primarily due to the nature of set-based pooling of the neighborhood aggregation scheme. Also, our extensive experiments indicate that trainable node embeddings can improve the performance of GNN-based link prediction models. Importantly, we observe that the denser the graph, the greater such the improvement. We attribute this to the characteristics of node embeddings, where the link state of each link sample could be encoded into the embeddings of nodes that are involved in the neighborhood aggregation of the two nodes in that link sample. In denser graphs, every node could have more opportunities to attend the neighborhood aggregation of other nodes and encode states of more link samples to its embedding, thus learning better node embeddings for link prediction. Lastly, we demonstrate that the insights gained from our research carry important implications in identifying the limitations of existing link prediction methods, which could guide the future development of more robust algorithms.
title Can GNNs Learn Link Heuristics? A Concise Review and Evaluation of Link Prediction Methods
topic Social and Information Networks
Machine Learning
url https://arxiv.org/abs/2411.14711