Linked Data Classification using Neurochaos Learning

TL;DR

This paper explores applying Neurochaos Learning to linked data, specifically knowledge graphs, by integrating node aggregation and testing on various graph datasets, showing promising results especially on homophilic graphs.

Contribution

It extends Neurochaos Learning to knowledge graphs through node aggregation, demonstrating its effectiveness on different types of graph datasets.

Findings

Better performance on homophilic graphs

Effective node aggregation method for linked data

Insights into heterophilic vs. homophilic graph classification

Abstract

Neurochaos Learning (NL) has shown promise in recent times over traditional deep learning due to its two key features: ability to learn from small sized training samples, and low compute requirements. In prior work, NL has been implemented and extensively tested on separable and time series data, and demonstrated its superior performance on both classification and regression tasks. In this paper, we investigate the next step in NL, viz., applying NL to linked data, in particular, data that is represented in the form of knowledge graphs. We integrate linked data into NL by implementing node aggregation on knowledge graphs, and then feeding the aggregated node features to the simplest NL architecture: ChaosNet. We demonstrate the results of our implementation on homophilic graph datasets as well as heterophilic graph datasets of verying heterophily. We show better efficacy of our approach on homophilic graphs than on heterophilic graphs. While doing so, we also present our analysis of the results, as well as suggestions for future work.