97 citations · 379 across the 26 of their papers we have counts for
28 papers
Data-Driven Evidence-Based Syntactic Sugar Design
David OBrien, Robert Dyer, Tien N. Nguyen +1
Programming languages are essential tools for developers, and their evolution plays a crucial role in supporting the activities of developers. One instance of programming language…
Inferring Data Preconditions from Deep Learning Models for Trustworthy Prediction in Deployment
Shibbir Ahmed, Hongyang Gao, Hridesh Rajan
Deep learning models are trained with certain assumptions about the data during the development stage and then used for prediction in the deployment stage. It is important to reaso…
Mutation-based Fault Localization of Deep Neural Networks
Ali Ghanbari, Deepak-George Thomas, Muhammad Arbab Arshad +1
Deep neural networks (DNNs) are susceptible to bugs, just like other types of software systems. A significant uptick in using DNN, and its applications in wide-ranging areas, inclu…
What Kinds of Contracts Do ML APIs Need?
Samantha Syeda Khairunnesa, Shibbir Ahmed, Sayem Mohammad Imtiaz +2
Recent work has shown that Machine Learning (ML) programs are error-prone and called for contracts for ML code. Contracts, as in the design by contract methodology, help document A…
An Effective Data-Driven Approach for Localizing Deep Learning Faults
Mohammad Wardat, Breno Dantas Cruz, Wei Le +1
Deep Learning (DL) applications are being used to solve problems in critical domains (e.g., autonomous driving or medical diagnosis systems). Thus, developers need to debug their s…
Characterizing Bugs in Python and R Data Analytics Programs
Shibbir Ahmed, Mohammad Wardat, Hamid Bagheri +2
R and Python are among the most popular languages used in many critical data analytics tasks. However, we still do not fully understand the capabilities of these two languages w.r.…
Fix Fairness, Don't Ruin Accuracy: Performance Aware Fairness Repair using AutoML
Giang Nguyen, Sumon Biswas, Hridesh Rajan
Machine learning (ML) is increasingly being used in critical decision-making software, but incidents have raised questions about the fairness of ML predictions. To address this iss…
Fairify: Fairness Verification of Neural Networks
Sumon Biswas, Hridesh Rajan
Fairness of machine learning (ML) software has become a major concern in the recent past. Although recent research on testing and improving fairness have demonstrated impact on rea…
Decomposing a Recurrent Neural Network into Modules for Enabling Reusability and Replacement
Sayem Mohammad Imtiaz, Fraol Batole, Astha Singh +3
Can we take a recurrent neural network (RNN) trained to translate between languages and augment it to support a new natural language without retraining the model from scratch? Can…
Towards Understanding Fairness and its Composition in Ensemble Machine Learning
Usman Gohar, Sumon Biswas, Hridesh Rajan
Machine Learning (ML) software has been widely adopted in modern society, with reported fairness implications for minority groups based on race, sex, age, etc. Many recent works ha…
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…
On Scheduling Ring-All-Reduce Learning Jobs in Multi-Tenant GPU Clusters with Communication Contention
Menglu Yu, Bo Ji, Hridesh Rajan +1
Powered by advances in deep learning (DL) techniques, machine learning and artificial intelligence have achieved astonishing successes. However, the rapidly growing needs for DL al…
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…
DeepDiagnosis: Automatically Diagnosing Faults and Recommending Actionable Fixes in Deep Learning Programs
Mohammad Wardat, Breno Dantas Cruz, Wei Le +1
Deep Neural Networks (DNNs) are used in a wide variety of applications. However, as in any software application, DNN-based apps are afflicted with bugs. Previous work observed that…
Manas: Mining Software Repositories to Assist AutoML
Giang Nguyen, Md Johir Islam, Rangeet Pan +1
Today deep learning is widely used for building software. A software engineering problem with deep learning is that finding an appropriate convolutional neural network (CNN) model…
The Art and Practice of Data Science Pipelines: A Comprehensive Study of Data Science Pipelines In Theory, In-The-Small, and In-The-Large
Sumon Biswas, Mohammad Wardat, Hridesh Rajan
Increasingly larger number of software systems today are including data science components for descriptive, predictive, and prescriptive analytics. The collection of data science s…
Decomposing Convolutional Neural Networks into Reusable and Replaceable Modules
Rangeet Pan, Hridesh Rajan
Training from scratch is the most common way to build a Convolutional Neural Network (CNN) based model. What if we can build new CNN models by reusing parts from previously build C…
A global convergence theory for deep ReLU implicit networks via over-parameterization
Tianxiang Gao, Hailiang Liu, Jia Liu +2
Implicit deep learning has received increasing attention recently due to the fact that it generalizes the recursive prediction rules of many commonly used neural network architectu…
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…
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…
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)…
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…
Do the Machine Learning Models on a Crowd Sourced Platform Exhibit Bias? An Empirical Study on Model Fairness
Sumon Biswas, Hridesh Rajan
Machine learning models are increasingly being used in important decision-making software such as approving bank loans, recommending criminal sentencing, hiring employees, and so o…
What Do Developers Ask About ML Libraries? A Large-scale Study Using Stack Overflow
Md Johirul Islam, Hoan Anh Nguyen, Rangeet Pan +1
Modern software systems are increasingly including machine learning (ML) as an integral component. However, we do not yet understand the difficulties faced by software developers w…