Advancing Out-of-Distribution Detection via Local Neuroplasticity

TL;DR

This paper introduces a novel out-of-distribution detection method using Kolmogorov-Arnold Networks' local neuroplasticity, outperforming existing techniques in image and medical data benchmarks.

Contribution

It proposes leveraging KANs' local plasticity for OOD detection, a novel approach that improves robustness and performance over traditional methods.

Findings

Superior OOD detection accuracy on benchmark datasets

Enhanced robustness in medical and image domains

Demonstrated effectiveness of local neuroplasticity in KANs

Abstract

In the domain of machine learning, the assumption that training and test data share the same distribution is often violated in real-world scenarios, requiring effective out-of-distribution (OOD) detection. This paper presents a novel OOD detection method that leverages the unique local neuroplasticity property of Kolmogorov-Arnold Networks (KANs). Unlike traditional multilayer perceptrons, KANs exhibit local plasticity, allowing them to preserve learned information while adapting to new tasks. Our method compares the activation patterns of a trained KAN against its untrained counterpart to detect OOD samples. We validate our approach on benchmarks from image and medical domains, demonstrating superior performance and robustness compared to state-of-the-art techniques. These results underscore the potential of KANs in enhancing the reliability of machine learning systems in diverse environments.