Vincent Sunn Chen

I'm a graduate student at Stanford with a concentration in machine learning and a minor in creative writing. I'm interested in shaping datasets to make machine learning systems more accesible to domain experts in fields like medical imaging.

I'm currently a research assistant in the Stanford AI Lab with Chris Ré, building multi-task/weak supervision systems in Snorkel.
Most recently, I worked on the data engine for training neural networks on the Autopilot vision team at Tesla.
In the past, I worked at Sift Science to fight fraud with machine learning, Xbox to build virtual reality experiences, and EMGuidance to build point-of-care healthcare tools.
At Stanford, I had the pleasure of co-directing TreeHacks, the university's flagship hackathon.

I also love reading, writing, and photography!

Slice-based Learning: A Programming Model for Residual Learning in Critical Data Slices

Vincent S Chen, Zhenzhen Weng, Alexander Ratner, Christopher Ré

ML models can achieve high quality performance on coarse-grained metrics (e.g., F1-score, overall accuracy), but they may underperform on critical data subsets, or slices. We introduce Slice-based Learning, a new programming model in which practitioners use slicing functions to specify critical data subsets for which the model should pay attention.

In NeurIPS 2019. [blog] [slides] [paper] [code]

Scene Graph Prediction with Limited Labels

Vincent S Chen, Paroma Varma, Ranjay Krishna, Michael Bernstein, Christopher Ré, Li Fei-Fei

Scene graphs have emerged as useful in a number of computer vision tasks, including visual question answering — however, most scene graph datasets are sparse due to annotator error. This work attempts to overcome limitations of human annotators using a semi-supervised method, taking advantage of both limited labels and unlabeled data, to generate training datasets for scene graphs.

In ICCV 2019. [paper] [code] [poster]

Powerful Abstractions for Programming Your Training Data

Sen Wu, Vincent S. Chen, Braden Hancock, Alex Ratner, Chris Ré, and other members of Hazy Lab

We leverage key abstractions in Snorkel to achieve state-of-the-art scores on the SuperGLUE benchmark: (1) weak supervision (2) data augmentation (3) data slicing.

SuperGLUE Benchmark. [blog] [code]

Massive Multi-Task Learning: Bringing More Supervision to Bear

Braden Hancock, Clara McCreery, Ines Chami, Vincent S. Chen, Sen Wu, Jared Dunnmon, Paroma Varma, Max Lam, and Chris Ré

We incorporate a number of supervision sources, from traditional supervision, transfer learning, multi-task learning, weak supervision, and ensembling, to achieve state-of-the-art scores on the GLUE benchmark.

GLUE Benchmark. [blog]

Weakly supervised classification of rare aortic valve malformations using unlabeled cardiac MRI sequences

Jason A Fries, Paroma Varma, Vincent S Chen, Ke Xiao, Heliodoro Tejeda, Priyanka Saha, Jared Dunnmon, Henry Chubb, Shiraz Maskatia, Madalina Fiterau, Scott Delp, Euan Ashley, Christopher Ré, James Priest

Bicuspid aortic valve (BAV) is the most common congenital malformation of the heart — obtaining training data is a tremendous practical roadblock to building ML models for detecting this malformation. We collaborate with cardiologists from Stanford Medicine to write labeling functions over geometric features of heart MRIs to produce probabilistic training labels.

In Nature Communications. [paper] [code]

Automated Training Set Generation for Aortic Valve Classification

Vincent Chen, Paroma Varma, Madalina Fiterau, James Priest and Christopher Ré.

Using weak-supervision, we learn probabilistic training labels for aortic valve MRIs.

In NeurIPS 2017, ML4H Workshop. [poster]

vincent sunn chen

projects