优化积分采样点，让神经网络归因更准更省力
Riemann Sum Optimization for Accurate Integrated Gradients Computation
- 用可优化的采样策略替代固定采样，提升积分精度
- 插入得分最高提升20%，计算量最多降低75%
- 适配多种归因方法，适合资源受限场景
集成梯度（IG）是用于将深度神经网络输出归因于输入特征的常用算法。由于深度学习模型缺乏闭式积分，通常使用不精确的黎曼和近似计算IG，这常导致噪声过高，产生误导性决策分析。本文提出RiemannOpt框架，通过优化黎曼和的采样点选择来最小化此类误差。该算法高度通用，适用于IG及其衍生方法如模糊梯度（Blur IG）和引导梯度（Guided IG）。实验表明，RiemannOpt在插入得分上最高提升20%；同时可将计算成本最多降低四倍，显著提升在资源受限环境下的实用性。
原文摘要 · Abstract (English)
Integrated Gradients (IG) is a widely used algorithm for attributing the outputs of a deep neural network to its input features. Due to the absence of closed-form integrals for deep learning models, inaccurate Riemann Sum approximations are used to calculate IG. This often introduces undesirable errors in the form of high levels of noise, leading to false insights in the model's decision-making process. We introduce a framework, RiemannOpt, that minimizes these errors by optimizing the sample point selection for the Riemann Sum. Our algorithm is highly versatile and applicable to IG as well as its derivatives like Blur IG and Guided IG. RiemannOpt achieves up to 20% improvement in Insertion Scores. Additionally, it enables its users to curtail computational costs by up to four folds, thereby making it highly functional for constrained 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。