A Method to Predict Semantic Relations on Artificial Intelligence Papers
Francisco Andrades, Ricardo \~Nanculef

TL;DR
This paper introduces a Graph Neural Network-based method to predict future semantic links between AI concepts, demonstrating competitive performance in a large-scale, computationally constrained network prediction challenge.
Contribution
The paper presents a novel GNN approach for link prediction in evolving AI concept networks, emphasizing efficiency and the ability to learn complex graph patterns.
Findings
Model effectively predicts future links with limited data
GNN captures node absorption and sub-graph union patterns
Approach is competitive in large-scale AI concept networks
Abstract
Predicting the emergence of links in large evolving networks is a difficult task with many practical applications. Recently, the Science4cast competition has illustrated this challenge presenting a network of 64.000 AI concepts and asking the participants to predict which topics are going to be researched together in the future. In this paper, we present a solution to this problem based on a new family of deep learning approaches, namely Graph Neural Networks. The results of the challenge show that our solution is competitive even if we had to impose severe restrictions to obtain a computationally efficient and parsimonious model: ignoring the intrinsic dynamics of the graph and using only a small subset of the nodes surrounding a target link. Preliminary experiments presented in this paper suggest the model is learning two related, but different patterns: the absorption of a node by a…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
