Linked Data Classification using Neurochaos Learning

Honna, Pooja and Patravali, Ayush and Nagaraj, Nithin and Nanjangud C, Narendra (2026) Linked Data Classification using Neurochaos Learning. arXiv.

[img] Text
2602.16204 - Published Version
Download (45kB)
ContributionNameEmail
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.
Item Type: Journal Paper
Subjects: School of Natural and Engineering Sciences > Complex Systems
Divisions: Schools > Natural Sciences and Engineering
Date Deposited: 13 Apr 2026 06:38
Last Modified: 13 Apr 2026 06:38
Official URL: https://arxiv.org/abs/2602.16204
Related URLs:
    Funders: *
    Projects: *
    DOI: https://doi.org/10.48550/arXiv.2602.16204
    URI: http://eprints.nias.res.in/id/eprint/3305

    Actions (login required)

    View Item View Item
    Created and Maintained by National Institute of Advanced Studies      |        ePrints@NIAS is powered by EPrints        |        Disclaimer