论文标题
可靠网络解释中网络压缩中的归因保存
Attribution Preservation in Network Compression for Reliable Network Interpretation
论文作者
论文摘要
嵌入安全敏感应用中的神经网络，例如自动驾驶汽车和可穿戴健康监测器，依赖于两种重要技术：用于后视分析和网络压缩的输入归因，以减少其用于边缘计算的大小。在本文中，我们表明这些看似无关的技术相互冲突，因为网络压缩变形了所产生的归因，这可能会导致对关键任务应用程序的可怕后果。由于传统网络压缩方法仅保留网络的预测，而忽略了归因的质量，因此出现了这种现象。为了解决归因不一致问题，我们提出了一个框架，可以在压缩网络时保留归属。通过采用加权折叠归因匹配的正常化程序，我们将被压缩的网络的归因图与其预压的前自我匹配。我们在定量和质量上都在各种压缩方法上证明了算法的有效性。
Neural networks embedded in safety-sensitive applications such as self-driving cars and wearable health monitors rely on two important techniques: input attribution for hindsight analysis and network compression to reduce its size for edge-computing. In this paper, we show that these seemingly unrelated techniques conflict with each other as network compression deforms the produced attributions, which could lead to dire consequences for mission-critical applications. This phenomenon arises due to the fact that conventional network compression methods only preserve the predictions of the network while ignoring the quality of the attributions. To combat the attribution inconsistency problem, we present a framework that can preserve the attributions while compressing a network. By employing the Weighted Collapsed Attribution Matching regularizer, we match the attribution maps of the network being compressed to its pre-compression former self. We demonstrate the effectiveness of our algorithm both quantitatively and qualitatively on diverse compression methods.
