利用KAN的局部可塑性提升分布外样本检测效果
Advancing Out-of-Distribution Detection via Local Neuroplasticity
- 通过对比训练前后KAN的激活模式识别分布外数据
- 在图像与医疗数据集上优于现有主流方法
- 适合需要高可靠性的实际应用场景
机器学习中常假设训练与测试数据同分布，但真实场景中此假设常被打破，需有效的分布外（OOD）检测。本文提出一种新方法，利用柯尔莫戈洛夫-阿诺德网络（KAN）独特的局部可塑性。与传统多层感知机不同，KAN具备保留已有知识并适应新任务的能力。本方法通过比较已训练KAN与其未训练版本的激活模式，实现对分布外样本的检测。我们在图像与医疗领域的多个基准上验证了该方法，结果表明其性能与鲁棒性均优于当前最优技术。这些发现凸显了KAN在提升机器学习系统在多样化环境中的可靠性方面的潜力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。