Neel Guha PhD Candidate, Department of Computer Science, Stanford University JD Candidate, Stanford Law School CV / Google Scholar Email: nguha [at] cs (dot) stanford (dot) edu

About me

I'm a first year JD-PhD student in Computer Science at Stanford University. I'm affiliated with the Hazy Research Lab, RegLab and Magic Lab. I graduated with a MS in Machine Learning from Carnegie Mellon University ('19) and a BSH in Computer Science from Stanford University ('18).

My CS interests center on machine learning techniques that better incorporate structured forms of reasoning. My legal interests focus on the intersection of machine learning and law, especially as it relates to legal tech, liability, and privacy.

Recent News

• [June 2021] Our work on legal pretraining and the CaseHOLD benchmark won the Carole Hafner Best Paper Award at ICAIL 2021! Thank you to everyone who helped us on this.

• [April 2021] Our work on legal pretraining and the CaseHOLD benchmark was accepted to ICAIL 2021!

• [April 2021] Our mobility dataset work was featured in the Wall Street Journal!

• [December 2020] Our work on detecting bias in mobility datasets used in COVID-19 response was accepted to FAccT 2021.

• [October 2020] Bootleg is live! We designed a self-supervised NED system for rare entities (getting state-of-the-art on an array of benchmarks in the process). Checkout the blog post, paper, and code.

• [August 2020] Excited to be starting as a 1L at Stanford Law!

Resources

• simple-wikidata-db: a simple library for triplifying the Wikidata dump and extracting triples
• legal-ml-datasets: a collection of pointers to datasets at the intersection of machine learning and law

Publications

• When Does Pretraining Help? Assessing Self-Supervised Learning for Law and the CaseHOLD Dataset
  Lucia Zheng, Neel Guha, Brandon R. Anderson, Peter Henderson, Daniel E. Ho
  In ICAIL: International Conference on Artificial Intelligence and Law, June 2021.
  [Blogpost] [Code]
  Oral Presentation / Carole Hafner Best Paper Award
  

• Leveraging Administrative Data for Bias Audits: Assessing Disparate Coverage with Mobility Data for COVID-19 Policy
  Amanda Coston, Neel Guha, Derek Ouyang, Lisa Lu, Alexandra Chouldechova, Daniel E. Ho.
  In FAccT: ACM Conference on Fairness, Accountability, and Transparency, March 2021.
  [HAI Blogpost] [Wall Street Journal Article]
  

• Bootleg: Chasing the Tail with Self-Supervised Named Entity Disambiguation
  Laurel Orr, Megan Leszczynski, Simran Arora, Sen Wu, Neel Guha, Xiao Ling, Christopher Re.
  In CIDR: Conference on Innovative Data Systems Research, January 2021.
  [Code] [Blogpost] [Website]
  

• Machine Learning for AC Optimal Power Flow
  Neel Guha, Zhecheng Wang, Matt Wytock, Arun Majumdar.
  In Climate Change Workshop (ICML), June 2019.
  Oral Presentation / Honorable Mention for Best Paper

• One-Shot Federated Learning
  Neel Guha, Ameet Talkwalkar, Virginia Smith
  In Workshop on Machine Learning on the Phone and other Consumer Devices (NeurIPs), December 2018.
  Oral Presentation

• Knowledge Aggregation via Epsilon Model Spaces
  Neel Guha
  In Workshop on Common Model Infrastructure Workshop (ACM SIGKDD), August 2018.
  Oral Presentation

• Medtree: A Search Engine for Medical Professionals
  Neel Guha, Errol Ozdalga, Matthew Wytock
  In International Symposium on Web AlGorithms, June 2015.
  Short Paper

• Spy Watch: a tool for transparency in web tracking.
  Neel Guha
  In Privacy Online Workshop (ISWC), September 2013.
  Oral Presentation

Service

• Program Committee: Adaptive & Multitask Learning Workshop (ICML '19), Climate Change Workshop (NeurIPs '19, '20), Knowledge Representation & Reasoning Meets Machine Learning Workshop (NeurIPS '19), AI + Humanitarian Assistance and Disaster Response Workshop (NeurIPs '20)

• I also served as a student representative on the Stanford ResX Task Force in 2018. See our final report!

Misc

Outside of school, I've spent time at Google, Laserlike, the Federal Communications Commission, and Harvard's Institute for Quantative Social Science.