2.9k citations · 3.3k across the 26 of their papers we have counts for
11 papers · 1 filter
Multi-Task Differential Privacy Under Distribution Skew
Walid Krichene, Prateek Jain, Shuang Song +3
We study the problem of multi-task learning under user-level differential privacy, in which users contribute data to tasks, each involving a subset of users. One important…
Attributing AUC-ROC to Analyze Binary Classifier Performance
Arya Tafvizi, Besim Avci, Mukund Sundararajan
Area Under the Receiver Operating Characteristic Curve (AUC-ROC) is a popular evaluation metric for binary classifiers. In this paper, we discuss techniques to segment the AUC-ROC…
Reciprocity in Machine Learning
Mukund Sundararajan, Walid Krichene
Machine learning is pervasive. It powers recommender systems such as Spotify, Instagram and YouTube, and health-care systems via models that predict sleep patterns, or the risk of…
First is Better Than Last for Language Data Influence
Chih-Kuan Yeh, Ankur Taly, Mukund Sundararajan +2
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 d…
The Penalty Imposed by Ablated Data Augmentation
Frederick Liu, Amir Najmi, Mukund Sundararajan
There is a set of data augmentation techniques that ablate parts of the input at random. These include input dropout, cutout, and random erasing. We term these techniques ablated d…
Estimating Training Data Influence by Tracing Gradient Descent
Garima Pruthi, Frederick Liu, Mukund Sundararajan +1
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…
A Note about: Local Explanation Methods for Deep Neural Networks lack Sensitivity to Parameter Values
Mukund Sundararajan, Ankur Taly
Local explanation methods, also known as attribution methods, attribute a deep network's prediction to its input (cf. Baehrens et al. (2010)). We respond to the claim from Adebayo…
How Important Is a Neuron?
Kedar Dhamdhere, Mukund Sundararajan, Qiqi Yan
The problem of attributing a deep network's prediction to its \emph{input/base} features is well-studied. We introduce the notion of \emph{conductance} to extend the notion of attr…
It was the training data pruning too!
Pramod Kaushik Mudrakarta, Ankur Taly, Mukund Sundararajan +1
We study the current best model (KDG) for question answering on tabular data evaluated over the WikiTableQuestions dataset. Previous ablation studies performed against this model a…
Axiomatic Attribution for Deep Networks
Mukund Sundararajan, Ankur Taly, Qiqi Yan
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-…
Gradients of Counterfactuals
Mukund Sundararajan, Ankur Taly, Qiqi Yan
Gradients have been used to quantify feature importance in machine learning models. Unfortunately, in nonlinear deep networks, not only individual neurons but also the whole networ…