9 accepted papers
Data is pooled across entities (individuals or enterprises) to create machine learning models, and sometimes, the entities that contribute the data also benefit from the models. Consider for instance a recommender system (e.g. Spotify, Instagram or YouTube), a health care app that predicts the risk…
We study the problem of multi-task learning under user-level differential privacy, in which n users contribute data to m tasks, each involving a subset of users. One important aspect of the problem, that can significantly impact quality, is the distribution skew among tasks. Tasks that have much few…
The ability to identify influential training examples enables us to debug training data and explain model behavior. Existing techniques to do so are based on the flow of training data influence through the model parameters. For large models in NLP applications, it is often computationally infeasible…
We study the attribution problem for deep networks applied to perception tasks. For vision tasks, attribution techniques attribute the prediction of a network to the pixels of the input image. We propose a new technique called Blur Integrated Gradients (Blur IG). This technique has several advantage…
We introduce a method called TracIn that computes the influence of a training example on a prediction made by the model. The idea is to trace how the loss on the test point changes during the training process whenever the training example of interest was utilized. We provide a scalable implementatio…
The Shapley value has become the basis for several methods that attribute the prediction of a machine-learning model on an input to its base features. The use of the Shapley value is justified by citing the uniqueness result from \cite{Shapley53}, which shows that it is the only method that satisfie…
The attribution problem, that is the problem of attributing a model’s prediction to its base features, is well-studied. We extend the notion of attribution to also apply to feature interactions. The Shapley value is a commonly used method to attribute a model’s prediction to its base features. We pr…
The problem of attributing a deep network’s prediction to its input/base features is well-studied (cf. Simonyan et al. (2013)). We introduce the notion of conductance to extend the notion of attribution to understanding the importance of hidden units. Informally, the conductance of a hidden unit of…
We study the problem of attributing the prediction of a deep network to its input features, a problem previously studied by several other works. We identify two fundamental axioms—Sensitivity and Implementation Invariance that attribution methods ought to satisfy. We show that they are not satisfied…