activity
20162026
most citedIdentifying and Correcting Label Bias in Machine Learning

117 citations · 148 across the 16 of their papers we have counts for

collaborators
Showing 2021Show all

6 papers · 1 filter

cs.LG2021

Active Covering

Heinrich Jiang, Afshin Rostamizadeh

We analyze the problem of active covering, where the learner is given an unlabeled dataset and can sequentially label query examples. The objective is to label query all of the pos…

cs.LG2021

SCARF: Self-Supervised Contrastive Learning using Random Feature Corruption

Dara Bahri, Heinrich Jiang, Yi Tay +1

Self-supervised contrastive representation learning has proved incredibly successful in the vision and natural language domains, enabling state-of-the-art performance with orders o…

cs.LG2021

Churn Reduction via Distillation

Heinrich Jiang, Harikrishna Narasimhan, Dara Bahri +2

In real-world systems, models are frequently updated as more data becomes available, and in addition to achieving high accuracy, the goal is to also maintain a low difference in pr…

cs.CV2021★ 2 cited

MeanShift++: Extremely Fast Mode-Seeking With Applications to Segmentation and Object Tracking

Jennifer Jang, Heinrich Jiang

MeanShift is a popular mode-seeking clustering algorithm used in a wide range of applications in machine learning. However, it is known to be prohibitively slow, with quadratic run…

cs.LG2021

Label Smoothed Embedding Hypothesis for Out-of-Distribution Detection

Dara Bahri, Heinrich Jiang, Yi Tay +1

Detecting out-of-distribution (OOD) examples is critical in many applications. We propose an unsupervised method to detect OOD samples using a -NN density estimate with respect…

cs.LG2021

Locally Adaptive Label Smoothing for Predictive Churn

Dara Bahri, Heinrich Jiang

Training modern neural networks is an inherently noisy process that can lead to high \emph{prediction churn} -- disagreements between re-trainings of the same model due to factors…