Search Results for author: Hridesh Rajan

Found 16 papers, 9 papers with code

Inferring Data Preconditions from Deep Learning Models for Trustworthy Prediction in Deployment

1 code implementation26 Jan 2024 Shibbir Ahmed, Hongyang Gao, Hridesh Rajan

In this work, we propose a novel technique that uses rules derived from neural network computations to infer data preconditions for a DNN model to determine the trustworthiness of its predictions.

What Kinds of Contracts Do ML APIs Need?

no code implementations26 Jul 2023 Samantha Syeda Khairunnesa, Shibbir Ahmed, Sayem Mohammad Imtiaz, Hridesh Rajan, Gary T. Leavens

The software engineering community could employ existing contract mining approaches to mine these contracts to promote an increased understanding of ML APIs.

Fix Fairness, Don't Ruin Accuracy: Performance Aware Fairness Repair using AutoML

2 code implementations15 Jun 2023 Giang Nguyen, Sumon Biswas, Hridesh Rajan

In order to demonstrate the effectiveness of our approach, we evaluated our approach on four fairness problems and 16 different ML models, and our results show a significant improvement over the baseline and existing bias mitigation techniques.

AutoML Decision Making +1

Decomposing a Recurrent Neural Network into Modules for Enabling Reusability and Replacement

no code implementations9 Dec 2022 Sayem Mohammad Imtiaz, Fraol Batole, Astha Singh, Rangeet Pan, Breno Dantas Cruz, Hridesh Rajan

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?

Math

Towards Understanding Fairness and its Composition in Ensemble Machine Learning

1 code implementation8 Dec 2022 Usman Gohar, Sumon Biswas, Hridesh Rajan

Furthermore, studies have shown that hyperparameters influence the fairness of ML models.

Fairness

Fairify: Fairness Verification of Neural Networks

1 code implementation8 Dec 2022 Sumon Biswas, Hridesh Rajan

In this paper, we proposed Fairify, an SMT-based approach to verify individual fairness property in neural network (NN) models.

Decision Making Fairness

DeepDiagnosis: Automatically Diagnosing Faults and Recommending Actionable Fixes in Deep Learning Programs

1 code implementation7 Dec 2021 Mohammad Wardat, Breno Dantas Cruz, Wei Le, Hridesh Rajan

Also, it can provide actionable insights for fix whereas DeepLocalize can only report faults that lead to numerical errors during training.

Fault Detection Fault localization

Manas: Mining Software Repositories to Assist AutoML

2 code implementations6 Dec 2021 Giang Nguyen, Md Johir Islam, Rangeet Pan, Hridesh Rajan

Recent work on AutoML, more precisely neural architecture search (NAS), embodied by tools like Auto-Keras aims to solve this problem by essentially viewing it as a search problem where the starting point is a default CNN model, and mutation of this CNN model allows exploration of the space of CNN models to find a CNN model that will work best for the problem.

Image Classification Neural Architecture Search

Decomposing Convolutional Neural Networks into Reusable and Replaceable Modules

no code implementations11 Oct 2021 Rangeet Pan, Hridesh Rajan

Also, building a model by reusing or replacing modules can be done with a 2. 3% and 0. 5% average loss of accuracy.

Image Classification

A global convergence theory for deep ReLU implicit networks via over-parameterization

no code implementations ICLR 2022 Tianxiang Gao, Hailiang Liu, Jia Liu, Hridesh Rajan, Hongyang Gao

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 architectures.

Do the Machine Learning Models on a Crowd Sourced Platform Exhibit Bias? An Empirical Study on Model Fairness

2 code implementations21 May 2020 Sumon Biswas, Hridesh Rajan

Then, we have applied 7 mitigation techniques on these models and analyzed the fairness, mitigation results, and impacts on performance.

Attribute BIG-bench Machine Learning +3

What Do Developers Ask About ML Libraries? A Large-scale Study Using Stack Overflow

no code implementations27 Jun 2019 Md Johirul Islam, Hoan Anh Nguyen, Rangeet Pan, Hridesh Rajan

Last and somewhat surprisingly, a tug of war between providing higher levels of abstractions and the need to understand the behavior of the trained model is prevalent.

Software Engineering

A Comprehensive Study on Deep Learning Bug Characteristics

no code implementations3 Jun 2019 Md Johirul Islam, Giang Nguyen, Rangeet Pan, Hridesh Rajan

The key findings of our study include: data bug and logic bug are the most severe bug types in deep learning software appearing more than 48% of the times, major root causes of these bugs are Incorrect Model Parameter (IPS) and Structural Inefficiency (SI) showing up more than 43% of the times.

Identifying Classes Susceptible to Adversarial Attacks

no code implementations30 May 2019 Rangeet Pan, Md Johirul Islam, Shibbir Ahmed, Hridesh Rajan

Based on the distance among original classes, we create mapping among original classes and adversarial classes that helps to reduce the randomness of a model to a significant amount in an adversarial setting.

Adversarial Attack

Cannot find the paper you are looking for? You can Submit a new open access paper.