106 citations · 307 across the 18 of their papers we have counts for
11 papers · 1 filter
A Minimalist Prompt for Zero-Shot Policy Learning
Meng Song, Xuezhi Wang, Tanay Biradar +2
Transformer-based methods have exhibited significant generalization ability when prompted with target-domain demonstrations or example solutions during inference. Although demonstr…
What Are Effective Labels for Augmented Data? Improving Calibration and Robustness with AutoLabel
Yao Qin, Xuezhi Wang, Balaji Lakshminarayanan +2
A wide breadth of research has devised data augmentation approaches that can improve both accuracy and generalization performance for neural networks. However, augmented data can e…
Understanding and Improving Robustness of Vision Transformers through Patch-based Negative Augmentation
Yao Qin, Chiyuan Zhang, Ting Chen +3
We investigate the robustness of vision transformers (ViTs) through the lens of their special patch-based architectural structure, i.e., they process an image as a sequence of imag…
Understanding and Improving Fairness-Accuracy Trade-offs in Multi-Task Learning
Yuyan Wang, Xuezhi Wang, Alex Beutel +3
As multi-task models gain popularity in a wider range of machine learning applications, it is becoming increasingly important for practitioners to understand the fairness implicati…
Measuring Model Fairness under Noisy Covariates: A Theoretical Perspective
Flavien Prost, Pranjal Awasthi, Nick Blumm +7
In this work we study the problem of measuring the fairness of a machine learning model under noisy information. Focusing on group fairness metrics, we investigate the particular b…
Evaluating Fairness of Machine Learning Models Under Uncertain and Incomplete Information
Pranjal Awasthi, Alex Beutel, Matthaeus Kleindessner +2
Training and evaluation of fair classifiers is a challenging problem. This is partly due to the fact that most fairness metrics of interest depend on both the sensitive attribute i…
Measuring Recommender System Effects with Simulated Users
Sirui Yao, Yoni Halpern, Nithum Thain +6
Imagine a food recommender system -- how would we check if it is \emph{causing} and fostering unhealthy eating habits or merely reflecting users' interests? How much of a user's ex…
Improving Calibration through the Relationship with Adversarial Robustness
Yao Qin, Xuezhi Wang, Alex Beutel +1
Neural networks lack adversarial robustness, i.e., they are vulnerable to adversarial examples that through small perturbations to inputs cause incorrect predictions. Further, trus…
Fairness without Demographics through Adversarially Reweighted Learning
Preethi Lahoti, Alex Beutel, Jilin Chen +5
Much of the previous machine learning (ML) fairness literature assumes that protected features such as race and sex are present in the dataset, and relies upon them to mitigate fai…
Practical Compositional Fairness: Understanding Fairness in Multi-Component Recommender Systems
Xuezhi Wang, Nithum Thain, Anu Sinha +4
How can we build recommender systems to take into account fairness? Real-world recommender systems are often composed of multiple models, built by multiple teams. However, most res…
Transfer of Machine Learning Fairness across Domains
Candice Schumann, Xuezhi Wang, Alex Beutel +3
If our models are used in new or unexpected cases, do we know if they will make fair predictions? Previously, researchers developed ways to debias a model for a single problem doma…