研究人员推出了一种新方法ProxySHAP，用于近似机器学习模型中的Shapley和Banzhaf交互。该方法结合了基于树的代理模型的效率和残差校正技术以提高准确性。ProxySHAP为计算树集成中的交互指数提供了多项式时间泛化，克服了先前与树深度相关的限制。基准测试表明，ProxySHAP在近似质量方面优于ProxySPEX和KernelSHAP-IQ等现有方法，即使对于具有众多特征的大规模应用也是如此，并增强了下游可解释性任务。 AI
影响 增强了复杂ML模型的可解释性和近似质量，可能提高信任度和调试能力。
排序理由 该集群包含一篇研究论文，详细介绍了近似机器学习中Shapley和Banzhaf交互的新方法。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 4 个来源。 我们如何撰写摘要 →
Shapley and Banzhaf interactions capture the complex dynamics inherent in modern machine learning applications. However, current estimators for these higher-order interactions trade off between speed and accuracy. To overcome this limitation, we introduce ProxySHAP. ProxySHAP rec…
arXiv:2605.22738v1 Announce Type: cross Abstract: Shapley and Banzhaf interactions capture the complex dynamics inherent in modern machine learning applications. However, current estimators for these higher-order interactions trade off between speed and accuracy. To overcome this…
Shapley and Banzhaf interactions capture the complex dynamics inherent in modern machine learning applications. However, current estimators for these higher-order interactions trade off between speed and accuracy. To overcome this limitation, we introduce ProxySHAP. ProxySHAP rec…
Shapley and Banzhaf interactions capture the complex dynamics inherent in modern machine learning applications. However, current estimators for these higher-order interactions trade off between speed and accuracy. To overcome this limitation, we introduce ProxySHAP. ProxySHAP rec…