5 papers
Learning Invariant Graph Representations Through Redundant Information
Barproda Halder, Pasan Dissanayake, Sanghamitra Dutta
Learning invariant graph representations for out-of-distribution (OOD) generalization remains challenging because the learned representations often retain spurious components. To a…
Towards Formalizing Spuriousness of Biased Datasets Using Partial Information Decomposition
Barproda Halder, Faisal Hamman, Pasan Dissanayake +3
Spuriousness arises when there is an association between two or more variables in a dataset that are not causally related. In this work, we propose an explainability framework to p…
VISION: Robust and Interpretable Code Vulnerability Detection Leveraging Counterfactual Augmentation
David Egea, Barproda Halder, Sanghamitra Dutta
Automated detection of vulnerabilities in source code is an essential cybersecurity challenge, underpinning trust in digital systems and services. Graph Neural Networks (GNNs) have…
Quantifying Knowledge Distillation Using Partial Information Decomposition
Pasan Dissanayake, Faisal Hamman, Barproda Halder +3
Knowledge distillation deploys complex machine learning models in resource-constrained environments by training a smaller student model to emulate internal representations of a com…
An Optimized YOLOv5 Based Approach For Real-time Vehicle Detection At Road Intersections Using Fisheye Cameras
Md. Jahin Alam, Muhammad Zubair Hasan, Md Maisoon Rahman +8
Real time vehicle detection is a challenging task for urban traffic surveillance. Increase in urbanization leads to increase in accidents and traffic congestion in junction areas r…