论文标题
限制流量：归因的信息瓶颈
Restricting the Flow: Information Bottlenecks for Attribution
论文作者
论文摘要
归因方法为人工神经网络等机器学习模型的决策提供了见解。对于给定的输入样本，它们为每个单独的输入变量（例如图像的像素）分配相关得分。在这项工作中，我们将信息瓶颈概念调整为归因。通过在中间特征地图中添加噪声，我们限制了信息流，并可以量化（位）图像区域提供了多少信息。我们使用VGG-16和Resnet-50上的三个不同指标将方法与十个基准进行比较，并发现我们的方法在六个设置中的五个基线中的表现都优于所有基线。该方法的信息理论基础为归因值（位）提供了绝对的参考框架，并保证了网络决策不需要接近零的区域。有关评论：https：//openreview.net/forum?id=s1xwh1rywb代码：https：//github.com/bioroboticslab/iba
Attribution methods provide insights into the decision-making of machine learning models like artificial neural networks. For a given input sample, they assign a relevance score to each individual input variable, such as the pixels of an image. In this work we adapt the information bottleneck concept for attribution. By adding noise to intermediate feature maps we restrict the flow of information and can quantify (in bits) how much information image regions provide. We compare our method against ten baselines using three different metrics on VGG-16 and ResNet-50, and find that our methods outperform all baselines in five out of six settings. The method's information-theoretic foundation provides an absolute frame of reference for attribution values (bits) and a guarantee that regions scored close to zero are not necessary for the network's decision. For reviews: https://openreview.net/forum?id=S1xWh1rYwB For code: https://github.com/BioroboticsLab/IBA
