There has been a surge in Explainable-AI (XAI) methods that provide insights into the workings of Deep Neural Network (DNN) models. Integrated Gradients (IG) is a popular XAI algorithm that attributes relevance scores to input features commensurate with their contribution to the model's output. However, it requires multiple forward \& backward passes through the model. Thus, compared to a single forward-pass inference, there is a significant computational overhead to generate the explanation which hinders real-time XAI. This work addresses the aforementioned issue by accelerating IG with a hardware-aware algorithm optimization. We propose a novel non-uniform interpolation scheme to compute the IG attribution scores which replaces the baseline uniform interpolation. Our algorithm significantly reduces the total interpolation steps required without adversely impacting convergence. Experiments on the ImageNet dataset using a pre-trained InceptionV3 model demonstrate \textit{2.6-3.6}$\times$ performance speedup on GPU systems for iso-convergence. This includes the minimal \textit{0.2-3.2}\% latency overhead introduced by the pre-processing stage of computing the non-uniform interpolation step-sizes.
翻译:解析- AI (XAI) 方法激增, 深入了解深神经网络(DNN) 模型的运作模式。 集成梯度( IG) 是一种流行的 XAI 算法, 将相关评分与输入特性相适应, 与其对模型输出的贡献相称。 但是, 它需要通过模型的多个前方 ⁇ ⁇ 向后传。 因此, 与单一的前方通路推论相比, 有大量的计算间接费用来产生阻碍实时 XAI 的解释。 这项工作通过硬件觉悟算法优化来加速 IG 的运行, 解决上述问题。 我们提出了一个新的非统一化的内推法, 以计算IG 属性评分, 取代基线统一内推法。 我们的算法大大降低了所需的全部内推步骤, 而不会对趋同产生不利影响。 使用事先经过培训的 InceptionV3 模型对图像网络数据集进行实验, 显示了用于同化的 GPUPU 系统绩效加速度 。 我们提议了一个最小的非文本 {0.2- 3. 2 平调前的系统。