Our Research
We conduct human-AI interaction research across the disciplines of computer science, HCI and design. We focus on explainability, interpretability, fairness, data visualization, human-centered AI, and ML for scientific discovery.
You can also check out our publications on Google Research.
Papers | Interactive Blog Posts and Websites
Papers
2020
Expert Discussions Improve Comprehension of Difficult Cases in Medical Image Assessment
Mike Shaekerman, Carrie Cai, Abigail Huang, Rory Sayres - CHI
Novice-AI Music Co-Creation via AI-Steering Tools for Deep Generative Nets
Ryan Louie, Andy Coenen, Anna Huang, Michael Terry, Carrie Cai - CHI
2019
AI in Nigeria
Courtney Heldreth, Fernanda Viégas, Titi Akinsanmi, Diana Akrong
A Benchmark for Interpretability Methods in Deep Neural Networks
Sara Hooker, Dumitru Erhan, Pieter-Jan Kindermans, Been Kim - NeurIPS
"Hello AI": Uncovering the Onboarding Needs of Medical Practitioners for Human-AI Collaborative Decision-Making
Carrie J. Cai, Samantha Winter, David Steiner, Lauren Wilcox, Michael Terry - CSCW
Human Evaluation of Models Built for Interpretability
Isaac Lage, Emily Chen, Jeffrey He, Menaka Narayanan, Been Kim, Samuel Gershman and Finale Doshi-Velez - HCOMP
Software Developers Learning Machine Learning: Motivations, Hurdles, and Desires
Carrie J. Cai, Philip J. Guo - VLHCC
Debiasing Embeddings for Reduced Gender Bias in Text Classification
Flavien Prost, Nithum Thain, Tolga Bolukbasi - ACL
BIM: Towards Quantitative Evaluation of Interpretability Methods with Ground Truth
Mengjiao Yang, Been Kim
Building SMILY: a Human-centric, Similar-image Search Tool for Pathology
Narayan Hegde, Carrie J. Cai
The Bach Doodle: Approachable music composition with machine learning at scale
Cheng-Zhi Anna Huang, Curtis Hawthorne, Adam Roberts, Monica Dinculescu, James Wexler, Leon Hong, Jacob Howcroft
The What-If Tool: Interactive Probing of Machine Learning Models
James Wexler, Mahima Pushkarna, Tolga Bolukbasi, Martin Wattenberg, Fernanda Viégas, Jimbo Wilson - VAST
Similar Image Search for Histopathology: SMILY
Narayan Hegde, Jason D. Hipp, Yun Liu, Michael Emmert-Buck, Emily Reif, Daniel Smilkov, Michael Terry, Carrie J. Cai, Mahul B. Amin, Craig H. Mermel, Phil Q. Nelson, Lily H. Peng, Greg S. Corrado, Martin C. Stumpe - Nature
XRAI: Better Attributions Through Regions
Andrei Kapishnikov, Tolga Bolukbasi, Fernanda Viégas, Michael Terry - ICCV
Visualizing and Measuring the Geometry of BERT
Andy Coenen, Emily Reif, Ann Yuan, Been Kim, Adam Pearce, Fernanda Viégas, Martin Wattenberg - NeurIPS
Do Neural Networks Show Gestalt Phenomena? An Exploration of the Law of Closure
Been Kim, Emily Reif, Martin Wattenberg, Samy Bengio
The Effects of Example-based Explanations in a Machine Learning Interface
Carrie J Cai, Jonas Jongejan, Jess Holbrook - IUI
Human-Centered Tools for Coping with Imperfect Algorithms during Medical Decision-Making
Carrie J. Cai, Emily Reif, Narayan Hegde, Jason Hipp, Been Kim, Daniel Smilkov, Martin Wattenberg, Fernanda Viégas, Greg S. Corrado, Martin C. Stumpe, Michael Terry - CHI
Towards Automatic Concept-based Explanations
Amirata Ghorbani, James Wexler, James Zou, Been Kim - NeurIPS
Tensorflow.js: Machine learning for the web and beyond
Daniel Smilkov, Nikhil Thorat, Yannick Assogba, Ann Yuan, Nick Kreeger, Ping Yu, Kangyi Zhang, Shanqing Cai, Eric Nielsen, David Soergel, Stan Bileschi, Michael Terry, Charles Nicholson, Sandeep N. Gupta, Sarah Sirajuddin, D. Sculley, Rajat Monga, Greg Corrado, Fernanda B. Viégas, Martin Wattenberg - SysML
2018
Interpreting Black Box Predictions using Fisher Kernels
Rajiv Khanna, Been Kim, Joydeep Ghosh, Oluwasanmi Koyejo - AISTATS
ClinicalVis: Supporting Clinical Task-Focused Design Evaluation
Marzyeh Ghassemi, Mahima Pushkarna, James Wexler, Jesse Johnson, Paul Varghese
Sanity Checks for Saliency Maps
Julius Adebayo, Justin Gilmer, Michael Muelly, Ian Goodfellow, Moritz Hardt, Been Kim - NeurIPS
GAN Lab: Understanding Complex Deep Generative Models using Interactive Visual Experimentation
Minsuk Kahng, Nikhil Thorat, Duen Horng Chau, Fernanda Viégas, Martin Wattenberg - VAST
Deep learning of aftershock patterns following large earthquakes
Phoebe M. R. DeVries, Fernanda Viégas, Martin Wattenberg & Brendan J. Meade - Nature
To Trust Or Not To Trust A Classifier
Heinrich Jiang, Been Kim, Melody Y. Guan, Maya Gupta - NeurIPS
Human-in-the-Loop Interpretability Prior
Isaac Lage, Andrew Slavin Ross, Been Kim, Samuel J. Gershman, Finale Doshi-Velez - NeurIPS
Scalable and accurate deep learning with electronic health records
Alvin Rajkomar, Eyal Oren, Kai Chen, Andrew M. Dai, Nissan Hajaj, Michaela Hardt, Peter J. Liu, Xiaobing Liu, Jake Marcus, Mimi Sun, Patrik Sundberg, Hector Yee, Kun Zhang, Yi Zhang, Gerardo Flores, Gavin E. Duggan, Jamie Irvine, Quoc Le, Kurt Litsch, Alexander Mossin, Justin Tansuwan, De Wang, James Wexler, Jimbo Wilson, Dana Ludwig, Samuel L. Volchenboum, Katherine Chou, Michael Pearson, Srinivasan Madabushi, Nigam H. Shah, Atul J. Butte, Michael D. Howell, Claire Cui, Greg S. Corrado & Jeffrey Dean - Nature
2017
Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)
Been Kim, Martin Wattenberg, Justin Gilmer, Carrie Cai, James Wexler, Fernanda Viégas, Rory Sayres
Direct-Manipulation Visualization of Deep Networks
Daniel Smilkov, Shan Carter, D. Sculley, Fernanda B. Viégas, Martin Wattenberg
SmoothGrad: removing noise by adding noise
Daniel Smilkov, Nikhil Thorat, Been Kim, Fernanda Viégas, Martin Wattenberg
Visualizing Dataflow Graphs of Deep Learning Models in TensorFlow
Kanit Wongsuphasawat, Daniel Smilkov, James Wexler, Jimbo Wilson, Dandelion Mane, Doug Fritz, Dilip Krishnan, Fernanda B. Viégas, and Martin Wattenberg - IEEE TVCG
What Is Better Than Coulomb Failure Stress? A Ranking of Scalar Static Stress Triggering Mechanisms from 105 Mainshock-Aftershock Pairs
Brendan J. Meade, Phoebe M. R. DeVries, Jeremy Faller, Fernanda Viégas, Martin Wattenberg - Geophysical Research Letters
2016
Interactive Visualization of Spatially Amplified GNSS Time-Series Position Fields
Brendan J. Meade, William T. Freeman, James Wilson, Fernanda Viégas, and Martin Wattenberg
Embedding Projector: Interactive Visualization and Interpretation of Embeddings
Daniel Smilkov, Nikhil Thorat, Charles Nicholson, Emily Reif, Fernanda B. Viégas, Martin Wattenberg - NeurIPS
TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
Martín Abadi, Ashish Agarwal, Paul Barham, Eugene Brevdo, Zhifeng Chen, Craig Citro, Greg S. Corrado, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Ian Goodfellow, Andrew Harp, Geoffrey Irving, Michael Isard, Yangqing Jia, Rafal Jozefowicz, Lukasz Kaiser, Manjunath Kudlur, Josh Levenberg, Dan Mane, Rajat Monga, Sherry Moore, Derek Murray, Chris Olah, Mike Schuster, Jonathon Shlens, Benoit Steiner, Ilya Sutskever, Kunal Talwar, Paul Tucker, Vincent Vanhoucke, Vijay Vasudevan, Fernanda Viégas, Oriol Vinyals, Pete Warden, Martin Wattenberg, Martin Wicke, Yuan Yu, Xiaoqiang Zheng
Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation
Melvin Johnson, Mike Schuster, Quoc V. Le, Maxim Krikun, Yonghui Wu, Zhifeng Chen, Nikhil Thorat, Fernanda Viégas, Martin Wattenberg, Greg Corrado, Macduff Hughes, Jeffrey Dean - ACL
2014
Visualizing Statistical Mix Effects and Simpson's Paradox
Zan Armstrong, Martin Wattenberg - IEEE InfoVis
2013
Google+Ripples: a native visualization of information flow
Fernanda Viégas, Martin Wattenberg, Jack Hebert, Geoffrey Borggaard, Alison Cichowlas, Jonathan Feinberg, Jon Orwant, Christopher Wren - WWW
Ad Click Prediction: a View from the Trenches
H. Brendan McMahan, Gary Holt, D. Sculley, Michael Young, Dietmar Ebner, Julian Grady, Lan Nie, Todd Phillips, Eugene Davydov, Daniel Golovin, Sharat Chikkerur, Dan Liu, Martin Wattenberg, Arnar Mar Hrafnkelsson, Tom Boulos, Jeremy Kubica - ACM SIGKDD
2012
Through the looking glass: talking about the world with visualization
Fernanda Viégas & Martin Wattenberg - ACM
2011
Luscious
Fernanda Viégas & Martin Wattenberg
2010
Beautiful History: Visualizing Wikipedia
Fernanda Viégas & Martin Wattenberg
Interactive blogposts and websites
Communicating Model Uncertainty Over Space
Adam Pearce
What does BERT dream of? Deep Dreaming with BERT
Alex Bäuerle, James Wexler
Depth Predictions in Art
Ellen Jiang, Emily Reif, Been Kim
Understanding UMAP
Andy Coenen, Adam Pearce
Language, Context, and Geometry in Neural Networks
Andy Coenen, Emily Reif, Ann Yuan, Been Kim, Adam Pearce, Fernanda Viégas, Martin Wattenberg
Language, trees, and geometry in neural networks
Andy Coenen, Emily Reif, Ann Yuan, Been Kim, Adam Pearce, Fernanda Viégas, Martin Wattenberg
The Bach Doodle: Celebrating Johann Sebastian Bach
Cheng-Zhi Anna Huang, Curtis Hawthorne, Adam Roberts, Monica Dinculescu, James Wexler, Leon Hong, Jacob Howcroft
See How the World Draws
Reena Jana, Josh Lovejoy
How to Use t-SNE Effectively
Martin Wattenberg, Fernanda Viégas, Ian Johnson - Distill
Attacking discrimination with smarter machine learning
Martin Wattenberg, Fernanda Viégas, Moritz Hardt
Design and Redesign in Data Visualization
Fernanda Viégas, Martin Wattenberg
