activity
20182022
most citedFair Preprocessing: Towards Understanding Compositional Fairness of Data Transformers in Machine Learning Pipeline

97 citations · 220 across the 10 of their papers we have counts for

collaborators

12 papers

cs.SE20221 cited

An Empirical Study on the Bugs Found while Reusing Pre-trained Natural Language Processing Models

Rangeet Pan, Sumon Biswas, Mohna Chakraborty +2

In NLP, reusing pre-trained models instead of training from scratch has gained popularity; however, NLP models are mostly black boxes, very large, and often require significant res…

cs.DC2022

GADGET: Online Resource Optimization for Scheduling Ring-All-Reduce Learning Jobs

Menglu Yu, Ye Tian, Bo Ji +3

Fueled by advances in distributed deep learning (DDL), recent years have witnessed a rapidly growing demand for resource-intensive distributed/parallel computing to process DDL com…

cs.LG202197 cited

Fair Preprocessing: Towards Understanding Compositional Fairness of Data Transformers in Machine Learning Pipeline

Sumon Biswas, Hridesh Rajan

In recent years, many incidents have been reported where machine learning models exhibited discrimination among people based on race, sex, age, etc. Research has been conducted to…

cs.SE20211 cited

DeepLocalize: Fault Localization for Deep Neural Networks

Mohammad Wardat, Wei Le, Hridesh Rajan

Deep neural networks (DNNs) are becoming an integral part of most software systems. Previous work has shown that DNNs have bugs. Unfortunately, existing debugging techniques do not…

cs.SE20202 cited

BCFA: Bespoke Control Flow Analysis for CFA at Scale

Ramanathan Ramu, Ganesha B Upadhyaya, Hoan Anh Nguyen +1

Many data-driven software engineering tasks such as discovering programming patterns, mining API specifications, etc., perform source code analysis over control flow graphs (CFGs)…

cs.SE20208 cited

Repairing Deep Neural Networks: Fix Patterns and Challenges

Md Johirul Islam, Rangeet Pan, Giang Nguyen +1

Significant interest in applying Deep Neural Network (DNN) has fueled the need to support engineering of software that uses DNNs. Repairing software that uses DNNs is one such unmi…