Introducing New Node Prediction in Graph Mining: Predicting All Links from Isolated Nodes with Graph Neural Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zanardini, Damiano, Serrano, Emilio
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916087224860672
author Zanardini, Damiano
Serrano, Emilio
author_facet Zanardini, Damiano
Serrano, Emilio
contents This paper introduces a new problem in the field of graph mining and social network analysis called new node prediction. More technically, the task can be categorized as zero-shot out-of-graph all-links prediction. This challenging problem aims to predict all links from a new, isolated, and unobserved node that was previously disconnected from the graph. Unlike classic approaches to link prediction (including few-shot out-of-graph link prediction), this problem presents two key differences: (1) the new node has no existing links from which to extract patterns for new predictions; and (2) the goal is to predict not just one, but all the links of this new node, or at least a significant part of them. Experiments demonstrate that an architecture based on Deep Graph Neural Networks can learn to solve this challenging problem in a bibliographic citation network.
format Preprint
id arxiv_https___arxiv_org_abs_2401_05468
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Introducing New Node Prediction in Graph Mining: Predicting All Links from Isolated Nodes with Graph Neural Networks
Zanardini, Damiano
Serrano, Emilio
Social and Information Networks
Artificial Intelligence
Machine Learning
I.2; I.2.6
This paper introduces a new problem in the field of graph mining and social network analysis called new node prediction. More technically, the task can be categorized as zero-shot out-of-graph all-links prediction. This challenging problem aims to predict all links from a new, isolated, and unobserved node that was previously disconnected from the graph. Unlike classic approaches to link prediction (including few-shot out-of-graph link prediction), this problem presents two key differences: (1) the new node has no existing links from which to extract patterns for new predictions; and (2) the goal is to predict not just one, but all the links of this new node, or at least a significant part of them. Experiments demonstrate that an architecture based on Deep Graph Neural Networks can learn to solve this challenging problem in a bibliographic citation network.
title Introducing New Node Prediction in Graph Mining: Predicting All Links from Isolated Nodes with Graph Neural Networks
topic Social and Information Networks
Artificial Intelligence
Machine Learning
I.2; I.2.6
url https://arxiv.org/abs/2401.05468