Hello, I’m Mayee!
I am a PhD student in Computer Science at Stanford University, advised by Prof. Christopher Ré and part of the Hazy Research Lab.
I’m interested in using theoretical tools to understand and improve on modern machine learning techniques. Recently, I’ve been focused on data-centric AI, working on understanding the role of data through weak supervision and data selection, in particular for foundation models. I’m also interested in the representation geometry of neural networks and how to induce desirable geometries.
Previously, I graduated summa cum laude from Princeton University in 2019 with a concentration in Operations Research and Financial Engineering (ORFE) and a certificate in Applications of Computing, where I worked with Prof. Elad Hazan and Prof. Miklos Racz.
Publications and Preprints
Anomaly Detection with Multiple Reference Datasets
Mayee F. Chen, Benjamin Nachman, Frederic Sala. Machine Learning and the Physical Sciences (ML4PS) Workshop at NeurIPS, 2022.
paper | codeAsk Me Anything: A simple strategy for prompting language models
Simran Arora*, Avanika Narayan*, Mayee F. Chen, Laurel J. Orr, Neel Guha, Kush Bhatia, Ines Chami, Frederic Sala, Christopher Ré. International Conference on Learning Representations (ICLR), 2023.
paper | codeReducing Reliance on Spurious Features in Medical Image Classification with Spatial Specificity.
Khaled Saab, Sarah M. Hooper, Mayee F. Chen, Michael Zhang, Daniel Rubin, Christopher Ré. Machine Learning for Healthcare (MLHC), 2022.
paper | codeShoring Up the Foundations: Fusing Model Embeddings and Weak Supervision
Mayee F. Chen*, Daniel Y. Fu*, Dyah Adila, Michael Zhang, Frederic Sala, Kayvon Fatahalian, and Christopher Ré. Uncertainty in Artificial Intelligence (UAI), 2022. Best Student Paper Runner-Up Award, Oral Presentation.
paper | code slides | blog | Snorkel talkPerfectly Balanced: Improving Transfer and Robustness of Supervised Contrastive Learning
Mayee F. Chen*, Daniel Y. Fu*, Avanika Narayan, Michael Zhang, Zhao Song, Kayvon Fatahalian, and Christopher Ré. International Conference on Machine Learning (ICML), 2022.
paper | code | blogTABi: Type-Aware Bi-encoders for End-to-End Entity Retrieval
Megan E. Leszczynski, Daniel Y. Fu, Mayee F. Chen, and Christopher Ré. To Appear in the Findings of the Association for Computational Linguistics (ACL), 2022.
paper | code | blogThe Details Matter: Preventing Class Collapse in Supervised Contrastive Learning
Mayee F. Chen*, Daniel Y. Fu*, Michael Zhang, Kayvon Fatahalian, and Christopher Ré. AAAI Workshop on Artificial Intelligence with Biased or Scarce Data, 2022. Best Paper Award.
paper | codeMandoline: Model Evaluation under Distribution Shift
Mayee F. Chen*, Karan Goel*, Nimit Sohoni*, Fait Poms, Kayvon Fatahalian, and Christopher Ré. International Conference on Machine Learning (ICML), 2021.
paper | code | slides | MedAI talkComparing the Value of Labeled and Unlabeled Data in Method-of-Moments Latent Variable Estimation.
Mayee F. Chen*, Benjamin Cohen-Wang*, Steve Mussmann, Frederic Sala, and Christopher Ré. Artificial Intelligence and Statistics (AISTATS), 2021.
paper | slidesFast and Three-rious: Speeding Up Weak Supervision with Triplet Methods.
Daniel Y. Fu*, Mayee F. Chen*, Frederic Sala, Sarah M. Hooper, Kayvon Fatahalian, and Christopher Ré. International Conference on Machine Learning (ICML), 2020.
paper | code | video | blog
Older
- An Adversarial Model of Network Disruption: Maximizing Disagreement and Polarization in Social Networks.
Mayee F. Chen and Miklos Z. Racz. IEEE Transactions on Network Science and Engineering (TNSE), 2021.
paper | code
Effect of Rotational Grazing on Plant and Animal Production.
Mayee F. Chen and Junping Shi. Journal of Mathematical Biosciences and Engineering, vol. 15, no. 2. 2018.
paper | slidesEfficient GCD Computation for Big Integers on Xeon Phi Coprocessor.
Jie Chen, William Watson, and Mayee F. Chen. IEEE Conference on Networking, Architecture, and Storage (NAS). 2014.
paper | slides