Linked Data Classification using Neurochaos Learning

• URL: http://arxiv.org/abs/2602.16204v1
• Date: Wed, 18 Feb 2026 05:55:59 GMT
• Title: Linked Data Classification using Neurochaos Learning
• Authors: Pooja Honna, Ayush Patravali, Nithin Nagaraj, Nanjangud C. Narendra,
• Abstract summary: 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.<n>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.<n>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.
• Score: 0.6999740786886536
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• 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.

Related papers

• It Takes a Graph to Know a Graph: Rewiring for Homophily with a Reference Graph [19.222317334613162]
  Graph Neural Networks (GNNs) excel at analyzing graph-structured data but struggle on heterophilic graphs, where connected nodes often belong to different classes.<n>We provide theoretical foundations linking edge homophily, GNN embedding smoothness, and node classification performance.<n>We introduce a rewiring framework that increases graph homophily using a reference graph, with theoretical guarantees on the homophily of the rewired graph.
  arXiv  Detail & Related papers  (2025-05-18T13:28:56Z)
• The Heterophilic Graph Learning Handbook: Benchmarks, Models, Theoretical Analysis, Applications and Challenges [101.83124435649358]
  Homophily principle, ie nodes with the same labels or similar attributes are more likely to be connected. Recent work has identified a non-trivial set of datasets where GNN's performance compared to the NN's is not satisfactory.
  arXiv  Detail & Related papers  (2024-07-12T18:04:32Z)
• Breaking the Entanglement of Homophily and Heterophily in Semi-supervised Node Classification [25.831508778029097]
  We introduce AMUD, which quantifies the relationship between node profiles and topology from a statistical perspective. We also propose ADPA as a new directed graph learning paradigm for AMUD.
  arXiv  Detail & Related papers  (2023-12-07T07:54:11Z)
• Challenging the Myth of Graph Collaborative Filtering: a Reasoned and Reproducibility-driven Analysis [50.972595036856035]
  We present a code that successfully replicates results from six popular and recent graph recommendation models. We compare these graph models with traditional collaborative filtering models that historically performed well in offline evaluations. By investigating the information flow from users' neighborhoods, we aim to identify which models are influenced by intrinsic features in the dataset structure.
  arXiv  Detail & Related papers  (2023-08-01T09:31:44Z)
• Evolving Computation Graphs [20.094508902123778]
  Graph neural networks (GNNs) have demonstrated success in modeling relational data, especially for data that exhibits homophily. We propose Evolving Computation Graphs (ECGs), a novel method for enhancing GNNs on heterophilic datasets.
  arXiv  Detail & Related papers  (2023-06-22T14:58:18Z)
• Neural Graph Matching for Pre-training Graph Neural Networks [72.32801428070749]
  Graph neural networks (GNNs) have been shown powerful capacity at modeling structural data. We present a novel Graph Matching based GNN Pre-Training framework, called GMPT. The proposed method can be applied to fully self-supervised pre-training and coarse-grained supervised pre-training.
  arXiv  Detail & Related papers  (2022-03-03T09:53:53Z)
• Graph Neural Networks for Graphs with Heterophily: A Survey [98.45621222357397]
  We provide a comprehensive review of graph neural networks (GNNs) for heterophilic graphs. Specifically, we propose a systematic taxonomy that essentially governs existing heterophilic GNN models. We discuss the correlation between graph heterophily and various graph research domains, aiming to facilitate the development of more effective GNNs.
  arXiv  Detail & Related papers  (2022-02-14T23:07:47Z)
• Lifelong Learning on Evolving Graphs Under the Constraints of Imbalanced Classes and New Classes [2.870762512009438]
  We address two critical challenges of lifelong graph learning: dealing with new classes and tackling imbalanced class distributions. We show that the amount of unlabeled data does not influence the results, which is an essential prerequisite for lifelong learning. We propose the gDOC method to detect new classes under the constraint of having an imbalanced class distribution.
  arXiv  Detail & Related papers  (2021-12-20T14:29:39Z)
• Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods [16.170826632437183]
  New Graph Neural Networks (GNNs) have been developed that move beyond the homophily regime. We introduce diverse non-homophilous datasets from a variety of application areas. We show that existing scalable graph learning and graph minibatching techniques lead to performance degradation.
  arXiv  Detail & Related papers  (2021-10-27T14:02:41Z)
• Is Homophily a Necessity for Graph Neural Networks? [50.959340355849896]
  Graph neural networks (GNNs) have shown great prowess in learning representations suitable for numerous graph-based machine learning tasks. GNNs are widely believed to work well due to the homophily assumption ("like attracts like"), and fail to generalize to heterophilous graphs where dissimilar nodes connect. Recent works design new architectures to overcome such heterophily-related limitations, citing poor baseline performance and new architecture improvements on a few heterophilous graph benchmark datasets as evidence for this notion. In our experiments, we empirically find that standard graph convolutional networks (GCNs) can actually achieve better performance than
  arXiv  Detail & Related papers  (2021-06-11T02:44:00Z)
• Deep Reinforcement Learning of Graph Matching [63.469961545293756]
  Graph matching (GM) under node and pairwise constraints has been a building block in areas from optimization to computer vision. We present a reinforcement learning solver for GM i.e. RGM that seeks the node correspondence between pairwise graphs. Our method differs from the previous deep graph matching model in the sense that they are focused on the front-end feature extraction and affinity function learning.
  arXiv  Detail & Related papers  (2020-12-16T13:48:48Z)
• NodeNet: A Graph Regularised Neural Network for Node Classification [0.0]
  Most AI/ML techniques leave out the linkages among data points. Recent surge of interest in graph-based AI/ML techniques is aimed to leverage the linkages. We propose a model using NGL - NodeNet, to solve node classification task for citation graphs.
  arXiv  Detail & Related papers  (2020-06-16T09:41:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.