Improving Generalizability of Kolmogorov-Arnold Networks via Error-Correcting Output Codes

• URL: http://arxiv.org/abs/2505.05798v1
• Date: Fri, 09 May 2025 05:31:10 GMT
• Title: Improving Generalizability of Kolmogorov-Arnold Networks via Error-Correcting Output Codes
• Authors: Youngjoon Lee, Jinu Gong, Joonhyuk Kang,
• Abstract summary: We integrate Error-Correcting Output Codes (ECOC) into the Kolmogorov-Arnold Networks (KAN) framework to transform multi-class classification into binary tasks.<n>Our proposed KAN with ECOC method outperforms vanilla KAN on a challenging blood cell classification dataset.<n>This is the first integration of ECOC with KAN for enhancing multi-class medical image classification performance.
• Score: 3.536605202672355
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Kolmogorov-Arnold Networks (KAN) offer universal function approximation using univariate spline compositions without nonlinear activations. In this work, we integrate Error-Correcting Output Codes (ECOC) into the KAN framework to transform multi-class classification into multiple binary tasks, improving robustness via Hamming-distance decoding. Our proposed KAN with ECOC method outperforms vanilla KAN on a challenging blood cell classification dataset, achieving higher accuracy under diverse hyperparameter settings. Ablation studies further confirm that ECOC consistently enhances performance across FastKAN and FasterKAN variants. These results demonstrate that ECOC integration significantly boosts KAN generalizability in critical healthcare AI applications. To the best of our knowledge, this is the first integration of ECOC with KAN for enhancing multi-class medical image classification performance.

Related papers

• Self-Classification Enhancement and Correction for Weakly Supervised Object Detection [113.51483527300496]
  weakly supervised object detection (WSOD) has attracted much attention due to its low labeling cost.<n>In this work, we introduce a novel WSOD framework to ameliorate these two issues.<n>For one thing, we propose a self-classification enhancement module that integrates intra-class binary classification (ICBC) to bridge the gap between the two distinct MCC tasks.<n>For another, we propose a self-classification correction algorithm during inference, which combines the results of both MCC tasks to effectively reduce the mis-classified predictions.
  arXiv  Detail & Related papers  (2025-05-22T06:45:58Z)
• A Unified Benchmark of Federated Learning with Kolmogorov-Arnold Networks for Medical Imaging [3.536605202672355]
  Kolmogorov-Arnold Networks (KAN) can effectively replace Federated Learning (FL)<n>KAN is a promising alternative for privacy-preserving medical imaging applications in distributed healthcare.
  arXiv  Detail & Related papers  (2025-04-28T09:53:05Z)
• Comparative Analysis of Unsupervised and Supervised Autoencoders for Nuclei Classification in Clear Cell Renal Cell Carcinoma Images [1.3329051855548553]
  This study explores the application of supervised and unsupervised autoencoders (AEs) to automate nuclei classification in clear cell renal cell carcinoma (ccRCC) images.<n>We evaluate various AE architectures, including standard AEs, contractive AEs, and discriminative AEs.<n>Results show significant improvements in identifying aggressive ccRCC grades by leveraging the classification capability of AE.
  arXiv  Detail & Related papers  (2025-04-04T03:52:32Z)
• A Genetic Algorithm-Based Approach for Automated Optimization of Kolmogorov-Arnold Networks in Classification Tasks [8.669319624657701]
  Kolmogorov-Arnold Networks (KANs) are introduced in 2024 to address the issue of interpretability in multilayer perceptrons.<n>This paper proposes GA-KAN, a genetic-based approach that automates the optimization of KANs, requiring no human intervention in the design process.<n>GA-KAN is validated on two toy datasets, achieving optimal results without the manual tuning required by the original KAN.
  arXiv  Detail & Related papers  (2025-01-29T04:32:36Z)
• Deep Negative Correlation Classification [82.45045814842595]
  Existing deep ensemble methods naively train many different models and then aggregate their predictions. We propose deep negative correlation classification (DNCC) DNCC yields a deep classification ensemble where the individual estimator is both accurate and negatively correlated.
  arXiv  Detail & Related papers  (2022-12-14T07:35:20Z)
• Orthogonal SVD Covariance Conditioning and Latent Disentanglement [65.67315418971688]
  Inserting an SVD meta-layer into neural networks is prone to make the covariance ill-conditioned. We propose Nearest Orthogonal Gradient (NOG) and Optimal Learning Rate (OLR) Experiments on visual recognition demonstrate that our methods can simultaneously improve covariance conditioning and generalization.
  arXiv  Detail & Related papers  (2022-12-11T20:31:31Z)
• Improving Covariance Conditioning of the SVD Meta-layer by Orthogonality [65.67315418971688]
  Nearest Orthogonal Gradient (NOG) and Optimal Learning Rate (OLR) are proposed. Experiments on visual recognition demonstrate that our methods can simultaneously improve the covariance conditioning and generalization.
  arXiv  Detail & Related papers  (2022-07-05T15:39:29Z)
• Adversarial Feature Augmentation and Normalization for Visual Recognition [109.6834687220478]
  Recent advances in computer vision take advantage of adversarial data augmentation to ameliorate the generalization ability of classification models. Here, we present an effective and efficient alternative that advocates adversarial augmentation on intermediate feature embeddings. We validate the proposed approach across diverse visual recognition tasks with representative backbone networks.
  arXiv  Detail & Related papers  (2021-03-22T20:36:34Z)
• Common Spatial Generative Adversarial Networks based EEG Data Augmentation for Cross-Subject Brain-Computer Interface [4.8276709243429]
  Cross-subject application of EEG-based brain-computer interface (BCI) has always been limited by large individual difference and complex characteristics that are difficult to perceive. We propose a cross-subject EEG classification framework with a generative adversarial networks (GANs) based method named common spatial GAN (CS-GAN) Our framework provides a promising way to deal with the cross-subject problem and promote the practical application of BCI.
  arXiv  Detail & Related papers  (2021-02-08T10:37:03Z)
• Deep N-ary Error Correcting Output Codes [66.15481033522343]
  Data-independent ensemble methods like Error Correcting Output Codes (ECOC) attract increasing attention. N-ary ECOC decomposes the original multi-class classification problem into a series of independent simpler classification subproblems. We propose three different variants of parameter sharing architectures for deep N-ary ECOC.
  arXiv  Detail & Related papers  (2020-09-22T11:35:03Z)
• Repulsive Mixture Models of Exponential Family PCA for Clustering [127.90219303669006]
  The mixture extension of exponential family principal component analysis ( EPCA) was designed to encode much more structural information about data distribution than the traditional EPCA. The traditional mixture of local EPCAs has the problem of model redundancy, i.e., overlaps among mixing components, which may cause ambiguity for data clustering. In this paper, a repulsiveness-encouraging prior is introduced among mixing components and a diversified EPCA mixture (DEPCAM) model is developed in the Bayesian framework.
  arXiv  Detail & Related papers  (2020-04-07T04:07:29Z)

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.