I specialize in building interpretable neural networks, demonstrating that with proper representation, a model can be both high-performing and transparent. My solutions are tailored for domain experts, using techniques like domain-guided losses and architectures to address complex tasks in machine learning, natural language processing, and computational sciences.
For my PhD, I worked on developing fair and accurate neural models for toxicity detection in natural language. I used Multi Task Learning models to learn how both shared and specific tones of toxicity vary across demographic groups. This goes beyond a “one-size-fits-all” model which most often overfits to majority groups and raises algorithmic fairness concerns.
My Submitted Works
Grouped by Type
Same Same, But Different: Conditional Multi-Task Learning for Demographic-Specific Toxicity Detection [pdf] Gupta, Lee, De-Arteaga, Lease. WWW 2023.
Learning a neural Pareto manifold extractor with constraints [pdf] Gupta, Singh, Bollapragada, Lease. UAI 2022.
Pareto Solutions vs Dataset Optima: Concepts and Methods for Optimizing Competing Objectives with Constraints in Retrieval [pdf] Gupta, Singh, Das, Lease. ICTIR 2022.
A Streaming model for Generalized Rayleigh with extensions to Minimum Noise Fraction [pdf] Gupta, Bajaj. IEEE International Conference on Big Data 2019.
Correlation, Prediction and Ranking of Evaluation Metrics in Information Retrieval [pdf] (Best Student Paper Award). Gupta, Lee, De-Arteaga, Lease. WWW 2023.
Efficient Clustering-based Noise Covariance Estimation for Maximum Noise Fraction [pdf] Gupta, Bajaj. NCVPRIPG, Springer 2017.
A GPU based real-time CUDA implementation for obtaining Visual Saliency [pdf] Agarwal, Gupta, Mukhopadhyay, Layek. ICVGIP, ACM 2014.
Psychovisual saliency in color images [pdf] Gupta, Agarwal, Layek, Mukhopadhyay. NCVPRIPG, IEEE 2013.
HOFS: Higher order mutual information approximation for feature selection in R [pdf] Gajowniczek, Wu, Gupta, Bajaj. SoftwareX, Elsevier 2022.
A Fully Automated, Faster Noise Rejection Approach to Increasing the Analytical Capability of Chemical Imaging for Digital Histopathology [pdf] Gupta, Mittal, Balla, Bhargava, Bajaj. PloS One 2019.
Tail-Net: Extracting Lowest Singular Triplets for Big Data Applications [pdf] Singh, Gupta. arXiv preprint 2021.
SCA-Net: A Self-Correcting Two-Layer Auto-encoder for Hyperspectral Unmixing [pdf] Singh, Gupta, Lease, Dawson. arXiv preprint 2021.
Hybrid Neural Pareto Front (HNPF): A Two-Stage Neural-Filter approach for Pareto Front Extraction [pdf] Gupta, Singh, Lease, Dawson. arXiv preprint 2021.
Streaming Singular Value Decomposition for Big Data Applications [pdf] Gupta, Singh, Lease, Dawson. arXiv preprint 2020.
Extracting Optimal Solution Manifolds using Constrained Neural Optimization [pdf] Gupta, Singh, Lease. arXiv preprint 2020.
Prevention is Better than Cure: Handling Basis Collapse and Transparency in Dense Networks [pdf] Gupta, Singh, Dawson. arXiv preprint 2020.
TIME: A Fully Convolutional Neural Network Architecture with Interpretable Kernels for Dynamic Physical Processes [pdf] Singh, Gupta, Lease, Dawson. arXiv preprint 2020.