2.9k citations · 3.2k across the 15 of their papers we have counts for
13 papers · 1 filter
An Efficient Rehearsal Scheme for Catastrophic Forgetting Mitigation during Multi-stage Fine-tuning
Andrew Bai, Chih-Kuan Yeh, Cho-Jui Hsieh +1
Incrementally fine-tuning foundational models on new tasks or domains is now the de facto approach in NLP. A known pitfall of this approach is the \emph{catastrophic forgetting} of…
Interpretable Mixture of Experts
Aya Abdelsalam Ismail, Sercan Ö. Arik, Jinsung Yoon +3
The need for reliable model explanations is prominent for many machine learning applications, particularly for tabular and time-series data as their use cases often involve high-st…
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…
Local Explanations via Necessity and Sufficiency: Unifying Theory and Practice
David Watson, Limor Gultchin, Ankur Taly +1
Necessity and sufficiency are the building blocks of all successful explanations. Yet despite their importance, these notions have been conceptually underdeveloped and inconsistent…
The Explanation Game: Explaining Machine Learning Models Using Shapley Values
Luke Merrick, Ankur Taly
A number of techniques have been proposed to explain a machine learning model's prediction by attributing it to the corresponding input features. Popular among these are techniques…
Explainable Machine Learning in Deployment
Umang Bhatt, Alice Xiang, Shubham Sharma +7
Explainable machine learning offers the potential to provide stakeholders with insights into model behavior by using various methods such as feature importance scores, counterfactu…
Property Inference for Deep Neural Networks
Divya Gopinath, Hayes Converse, Corina S. Pasareanu +1
We present techniques for automatically inferring formal properties of feed-forward neural networks. We observe that a significant part (if not all) of the logic of feed forward ne…
Using Attribution to Decode Dataset Bias in Neural Network Models for Chemistry
Kevin McCloskey, Ankur Taly, Federico Monti +2
Deep neural networks have achieved state of the art accuracy at classifying molecules with respect to whether they bind to specific protein targets. A key breakthrough would occur…
Counterfactual Fairness in Text Classification through Robustness
Sahaj Garg, Vincent Perot, Nicole Limtiaco +3
In this paper, we study counterfactual fairness in text classification, which asks the question: How would the prediction change if the sensitive attribute referenced in the exampl…
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…
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…