Cross-Loss Influence Functions to Explain Deep Network Representations. (arXiv:2012.01685v2 [cs.LG] UPDATED)

As machine learning is increasingly deployed in the real world, it is
paramount that we develop the tools necessary to analyze the decision-making of
the models we train and deploy to end-users. Recently, researchers have shown
that influence functions, a statistical measure of sample impact, can
approximate the effects of training samples on classification accuracy for deep
neural networks. However, this prior work only applies to supervised learning,
where training and testing share an objective function. No approaches currently
exist …

arxiv influence loss network