activity
20162026
most citedModel Agnostic Contrastive Explanations for Structured Data

29 citations · 99 across the 19 of their papers we have counts for

collaborators
Showing 2022Show all

12 papers · 1 filter

cs.CV2022

When Neural Networks Fail to Generalize? A Model Sensitivity Perspective

Jiajin Zhang, Hanqing Chao, Amit Dhurandhar +4

Domain generalization (DG) aims to train a model to perform well in unseen domains under different distributions. This paper considers a more realistic yet more challenging scenari…

cs.LG2022★ 6 cited

On the Safety of Interpretable Machine Learning: A Maximum Deviation Approach

Dennis Wei, Rahul Nair, Amit Dhurandhar +3

Interpretable and explainable machine learning has seen a recent surge of interest. We focus on safety as a key motivation behind the surge and make the relationship between interp…

q-bio.BM2022★ 9 cited

Reprogramming Pretrained Language Models for Antibody Sequence Infilling

Igor Melnyk, Vijil Chenthamarakshan, Pin-Yu Chen +4

Antibodies comprise the most versatile class of binding molecules, with numerous applications in biomedicine. Computational design of antibodies involves generating novel and diver…

cs.CL2022★ 1 cited

PainPoints: A Framework for Language-based Detection of Chronic Pain and Expert-Collaborative Text-Summarization

Shreyas Fadnavis, Amit Dhurandhar, Raquel Norel +6

Chronic pain is a pervasive disorder which is often very disabling and is associated with comorbidities such as depression and anxiety. Neuropathic Pain (NP) is a common sub-type w…

cs.LG2022★ 6 cited

Anomaly Attribution with Likelihood Compensation

Tsuyoshi Idé, Amit Dhurandhar, Jiří Navrátil +2

This paper addresses the task of explaining anomalous predictions of a black-box regression model. When using a black-box model, such as one to predict building energy consumption…

cs.CY2022★ 1 cited

Atomist or Holist? A Diagnosis and Vision for More Productive Interdisciplinary AI Ethics Dialogue

Travis Greene, Amit Dhurandhar, Galit Shmueli

In response to growing recognition of the social impact of new AI-based technologies, major AI and ML conferences and journals now encourage or require papers to include ethics imp…