Stephen Mussmann

Machine Learning Researcher, Coactive AI

Incoming Assistant Professor (Fall '24), Georgia Tech SCS

My research aims to make machine learning a more practical tool for humans to analyze information and to build into intelligent systems. I use a mixture of experimental and theoretical techniques to bring clarity to data aspects of machine learning: identifying what data is best suited to train performant systems.

Most of my current and previous work falls into one of two categories:

Active Labeling/Learning: human supervision and interaction with nature (experiments) can be expensive. Can we design efficient algorithms to iteratively choose data to label for use cases where collecting labels is expensive so that we can significantly decrease the cost and effort of labeling?
Data Selection: given increasingly large and noisy data sets, training on all available data can be expensive and can yield sub-optimal performance for specific tasks. Can we efficiently select training data that yield more accurate predictors?

I am looking to work with students at Georgia Tech starting August 2024: please feel free to reach out if you are interested in working with me!

Previously, I was an IFDS postdoc at the University of Washington Computer Science working with Kevin Jamieson and Ludwig Schmidt. I received my PhD in 2021 from Stanford University Computer Science advised by Percy Liang.

Personal Email: somussmann@gmail.com

Georgia Tech Email: mussmann@gatech.edu

Google Scholar

Preprints

LabelBench: A Comprehensive Framework for Benchmarking Label-Efficient Learning

Jifan Zhang, Yifang Chen, Gregory Canal, Stephen Mussmann, Yinglun Zhu, Simon Shaolei Du, Kevin Jamieson, Robert D Nowak

June, 2023

Data Subset Selection via Machine Teaching

Stephen Mussmann, Alex Fang, Ludwig Schmidt, Kevin Jamieson

October, 2022

Publications

VOCALExplore: Pay-as-You-Go Video Data Exploration and Model Building

Maureen Daum, Enhao Zhang, Dong He, Stephen Mussmann, Brandon Haynes, Ranjay Krishna, Magdalena Balazinska

Conference on Very Large Data Bases (VLDB), 2024 (to appear)

DataComp: In search of the next generation of multimodal datasets

Samir Yitzhak Gadre*, Gabriel Ilharco*, Alex Fang*, Jonathan Hayase, Georgios Smyrnis, Thao Nguyen, Ryan Marten, Mitchell Wortsman, Dhruba Ghosh, Jieyu Zhang, Eyal Orgad, Rahim Entezari, Giannis Daras, Sarah Pratt, Vivek Ramanujan, Yonatan Bitton, Kalyani Marathe, Stephen Mussmann, Richard Vencu, Mehdi Cherti, Ranjay Krishna, Pang Wei Koh, Olga Saukh, Alexander Ratner, Shuran Song, Hannaneh Hajishirzi, Ali Farhadi, Romain Beaumont, Sewoong Oh, Alex Dimakis, Jenia Jitsev, Yair Carmon, Vaishaal Shankar, and Ludwig Schmidt

Neural Information Processing Systems (NeurIPS) Track on Datasets and Benchmarks, 2023

Constants Matter: The Performance Gains of Active Learning

Stephen Mussmann, Sanjoy Dasgupta

International Conference on Machine Learning (ICML), 2022

Comparing the Value of Labeled and Unlabeled Data in Method-of-Moments Latent Variable Estimation

Mayee Chen, Benjamin Cohen-Wang, Stephen Mussmann, Frederic Sala, Christopher Re

International Conference on Artificial Intelligence and Statistics (AISTATS), 2021

On the Importance of Adaptive Data Collection for Extremely Imbalanced Pairwise Tasks

Stephen Mussmann*, Robin Jia*, Percy Liang

Findings of Empirical Methods in Natural Language Processing (EMNLP), 2020

Concept Bottleneck Models

Pang Wei Koh*, Thao Nguyen*, Yew Siang Tang*, Stephen Mussmann, Emma Pierson, Been Kim, Percy Liang