Structured Citation Trend Prediction Using Graph Neural Networks

TL;DR

This paper introduces a GNN-based model for predicting the top cited papers at publication time, leveraging citation graphs to identify future influential works across academic fields.

Contribution

The paper presents a novel GNN architecture that predicts top papers at publication without relying on prior citation trends, outperforming traditional models.

Findings

GNN model achieves higher F1-score than classic methods.

Model effectively captures citation dynamics across multiple conferences.

Predicts influential papers at publication time with improved accuracy.

Abstract

Academic citation graphs represent citation relationships between publications across the full range of academic fields. Top cited papers typically reveal future trends in their corresponding domains which is of importance to both researchers and practitioners. Prior citation prediction methods often require initial citation trends to be established and do not take advantage of the recent advancements in graph neural networks (GNNs). We present GNN-based architecture that predicts the top set of papers at the time of publication. For experiments, we curate a set of academic citation graphs for a variety of conferences and show that the proposed model outperforms other classic machine learning models in terms of the F1-score.