44 citations · 223 across the 40 of their papers we have counts for
7 papers · 1 filter
Same Same, But Different: Conditional Multi-Task Learning for Demographic-Specific Toxicity Detection
Soumyajit Gupta, Sooyong Lee, Maria De-Arteaga +1
Algorithmic bias often arises as a result of differential subgroup validity, in which predictive relationships vary across groups. For example, in toxic language detection, comment…
Data Excellence for AI: Why Should You Care
Lora Aroyo, Matthew Lease, Praveen Paritosh +1
The efficacy of machine learning (ML) models depends on both algorithms and data. Training data defines what we want our models to learn, and testing data provides the means by whi…
Scalable Unidirectional Pareto Optimality for Multi-Task Learning with Constraints
Soumyajit Gupta, Gurpreet Singh, Raghu Bollapragada +1
Multi-objective optimization (MOO) problems require balancing competing objectives, often under constraints. The Pareto optimal solution set defines all possible optimal trade-offs…
A Hybrid 2-stage Neural Optimization for Pareto Front Extraction
Gurpreet Singh, Soumyajit Gupta, Matthew Lease +1
Classification, recommendation, and ranking problems often involve competing goals with additional constraints (e.g., to satisfy fairness or diversity criteria). Such optimization…
Towards Unbiased and Accurate Deferral to Multiple Experts
Vijay Keswani, Matthew Lease, Krishnaram Kenthapadi
Machine learning models are often implemented in cohort with humans in the pipeline, with the model having an option to defer to a domain expert in cases where it has low confidenc…
SCA-Net: A Self-Correcting Two-Layer Autoencoder for Hyper-spectral Unmixing
Gurpreet Singh, Soumyajit Gupta, Clint Dawson
Hyperspectral unmixing involves separating a pixel as a weighted combination of its constituent endmembers and corresponding fractional abundances, with the current state of the ar…
Evaluating Classifiers Without Expert Labels
Hyun Joon Jung, Matthew Lease
This paper considers the challenge of evaluating a set of classifiers, as done in shared task evaluations like the KDD Cup or NIST TREC, without expert labels. While expert labels…