Explainable AI for ML jet taggers using expert variables and layerwise relevance propagation

A framework is presented to extract and understand decision-making information from a deep neural network classifier of jet substructure tagging techniques. There are two methods studied. The first is using expert variables that augment the inputs ("expert-augmented" variables, or XAUGs). These XAUGs are concatenated to the classifier steps immediately before the final decision. The second is layerwise relevance propagation (LRP). The results show that XAUG variables can be used to interpret classifier behavior, increase discrimination ability when combined with low-level features, and in some cases capture the behavior of the classifier completely. The LRP technique can be used to find relevant information the network is using, and when combined with the XAUG variables, can be used to rank features, allowing one to find a reduced set of features that capture part of the network performance. These XAUGs can also be added to low-level networks as a guide to improve performance.