Predicting Research Trends in Artificial Intelligence with Gradient Boosting Decision Trees and Time-aware Graph Neural Networks

TL;DR

This paper presents two innovative methods, gradient boosting decision trees and time-aware graph neural networks, for predicting future research collaborations in AI, achieving top results in a competitive scientific prediction task.

Contribution

The paper introduces a novel combination of tree-based and deep learning approaches for dynamic scientific network prediction, winning the Science4cast 2021 competition.

Findings

Both approaches achieved competitive performance.

The blended model secured 1st place in the competition.

Source code is publicly available.

Abstract

The Science4cast 2021 competition focuses on predicting future edges in an evolving semantic network, where each vertex represents an artificial intelligence concept, and an edge between a pair of vertices denotes that the two concepts have been investigated together in a scientific paper. In this paper, we describe our solution to this competition. We present two distinct approaches: a tree-based gradient boosting approach and a deep learning approach, and demonstrate that both approaches achieve competitive performance. Our final solution, which is based on a blend of the two approaches, achieved the 1st place among all the participating teams. The source code for this paper is available at https://github.com/YichaoLu/Science4cast2021.