Link Prediction of Artificial Intelligence Concepts using Low Computational Power

TL;DR

This paper introduces a low computational power method for predicting future associations between AI concepts by leveraging simple topological features and an optimized classifier, suitable for resource-constrained environments.

Contribution

It presents a novel approach that uses low-order topological features and an optimized classifier for link prediction in semantic networks with limited computational resources.

Findings

Effective prediction with low computational resources

Utilizes simple topological features for link prediction

Discusses limitations and potential improvements

Abstract

This paper presents an approach proposed for the Science4cast 2021 competition, organized by the Institute of Advanced Research in Artificial Intelligence, whose main goal was to predict the likelihood of future associations between machine learning concepts in a semantic network. The developed methodology corresponds to a solution for a scenario of availability of low computational power only, exploiting the extraction of low order topological features and its incorporation in an optimized classifier to estimate the degree of future connections between the nodes. The reasons that motivated the developed methodologies will be discussed, as well as some results, limitations and suggestions of improvements.