SPADE：深度神经网络的稀疏性引导调试
SPADE: Sparsity-Guided Debugging for Deep Neural Networks
AI总结：
SPADE通过样本定向剪枝将稀疏性融入解释过程，提升图像显著性图准确性和神经元可视化，助力深度神经网络调试。
摘要：
众所周知，稀疏性可以提高深度神经网络的可解释性。然而，该领域的现有方法要么要求网络预先以稀疏性约束进行训练，要么在事后施加稀疏性，从而改变网络的整体行为。在本文中，我们首次证明，稀疏性可以被纳入解释过程本身，作为样本特定的预处理步骤。与以往工作不同，这种我们称之为SPADE的方法不对训练好的模型施加约束，并且在推理过程中不影响其对样本的行为。给定一个训练好的模型和一个目标样本，SPADE使用样本定向剪枝来提供网络在该样本上执行的“轨迹”，在计算解释之前将网络缩减到最重要的连接。我们证明，使用SPADE进行预处理显著提高了多种可解释性方法下图像显著性图的准确性。此外，SPADE还改善了神经元可视化的有用性，帮助人类推理网络行为。我们的代码可在https://github.com/IST-DASLab/SPADE获取。
英文摘要：
It is known that sparsity can improve interpretability for deep neural networks. However, existing methods in the area either require networks that are pre-trained with sparsity constraints, or impose sparsity after the fact, altering the network's general behavior. In this paper, we demonstrate, for the first time, that sparsity can instead be incorporated into the interpretation process itself, as a sample-specific preprocessing step. Unlike previous work, this approach, which we call SPADE, does not place constraints on the trained model and does not affect its behavior during inference on the sample. Given a trained model and a target sample, SPADE uses sample-targeted pruning to provide a "trace" of the network's execution on the sample, reducing the network to the most important connections prior to computing an interpretation. We demonstrate that preprocessing with SPADE significantly increases the accuracy of image saliency maps across several interpretability methods. Additionally, SPADE improves the usefulness of neuron visualizations, aiding humans in reasoning about network behavior. Our code is available at https://github.com/IST-DASLab/SPADE.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
