Linked Data Classification using Neurochaos Learning
This work addresses classification on linked data for domains like social networks or bioinformatics, but it is incremental as it extends an existing method to a new data type.
The paper applied Neurochaos Learning to linked data, specifically knowledge graphs, by implementing node aggregation and using ChaosNet, showing better performance on homophilic graphs than heterophilic graphs.
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.