Johan Ugander

Assistant Professor
Management Science & Engineering (MS&E)
Institute for Computational & Mathematical Engineering (ICME)
School of Engineering
Stanford University

My research develops algorithmic and statistical frameworks for analyzing social networks, social systems, and other large-scale data-rich contexts. I am particularly interested in the challenges of causal inference and experimentation in these complex domains. My work commonly falls at the intersections of machine learning, probability theory, statistics, optimization, graph theory, and algorithm design.

Within MS&E I am a member of the Social Algorithms Lab (SOAL). I am also among the faculty co-directors of the RAIN Seminar. At Stanford I am also affiliated with the Institute for Computational & Mathematical Engineering (ICME) and the Center for Computational Social Science. At the undergraduate level I also advise students from the Symbolic Systems (SymSys) and Mathematical and Computational Science (MCS) majors.

I obtained my Ph.D. in Applied Mathematics from Cornell University in 2014, advised by Jon Kleinberg. I also hold degrees from the University of Cambridge and Lund University; before that I attended Deep Springs College. From 2010-14 I held an affiliation with the Facebook Data Science team. In 2014-15 I spent one year as a post-doctoral researcher at Microsoft Research, hosted by Eric Horvitz. I joined the Stanford faculty in September 2015.

Since joining the Stanford faculty my research has been generously supported by the National Science Foundation (NSF), the Army Research Office (ARO), a David Morgenthaler II Faculty Fellowship (2015), a Hellman Faculty Fellowship (2019), the Stanford Thailand Research Consortium, the Stanford King Center on Global Development, the Stanford Program on Democracy and the Internet, the Koret Foundation, and Facebook. My Ph.D. students have individually received further external fellowship support from the NSF Graduate Research Fellowship and National Defense Science and Engineering Graduate (NDSEG) Fellowship programs.
[third person bio] [serious photo]

Contact me: jugander {at} stanford.edu
Visiting address: Huang Engineering Center 357, 475 Via Ortega, Stanford, CA 94305-4121
See also: twitter, medium, research blog

News

• Winter 2021:Teaching MS&E135: Networks at the undergraduate level and MS&E234: Data Privacy and Ethics at the masters level.
• December 2020: New work at NeurIPS on rich ranking distributions.
• Fall 2020: Zoom talks at Cornell University (9/25), University of Michigan (10/1).
• August 2020: Two papers at KDD, on graph partitioning and scaling choice models.
• June 2020: New paper on structural diversity wins Best Paper Award at ICWSM 2020.
• June 2020: New paper on closure coefficients out in Network Science.
• August 2019: I did an interview as part of a early-career researcher profile with Nature about my research.
• Summer 2019: One paper at ICML, one paper at EC!
• May 2019: Daughter Noa born!
• April 23, 2019: Talk at Stanford/Berkeley Causal Inference Meeting.
• Spring 2019: Three papers acceped at WWW!
• February 22, 2019: Talk at Google Research, Mountain View.
• January 2019: Recieved an ARO Young Investigator Award. Thanks ARO!

Ph.D. students and post-docs

• Izzy Aguiar, ICME
• Amel Awadelkarim, ICME
• Serina Chang, CS (co-advised w/ Jure Leskovec)
• Jenny Hong, MS&E
• Samir Khan, Statistics
• Martin Saveski, Post-doc

Former students: Jan Overgoor (PhD MS&E, 2021), Arjun Seshadri (PhD EE, 2021), Imanol Arrieta-Ibarra (PhD MS&E, 2020), Kristen Altenburger (PhD MS&E, 2020), Stephen Ragain (PhD MS&E, 2019), Alex Chin (PhD Statistics, 2019).

Publications

See also my Google Scholar profile.

Preprints:

• J Ugander, H Yin
  Randomized Graph Cluster Randomization
  arXiv:2009.02297, last updated September 2020.
  [twitter thread]
  
  
• S Ragain, J Ugander
  Choosing to Rank
  arXiv:1809.05139, last updated January 2019.
  
  
• S Ragain, A Peysakhovich, J Ugander
  Improving pairwise comparison models using Empirical Bayes shrinkage
  arXiv:1807.09236, last updated July 2018.
  
  

Publications:

• K Tomlinson, J Ugander, A Benson
  Choice Set Confounding in Discrete Choice
  to appear, KDD 2021.
  
  
• K Altenburger, J Ugander
  Which Node Attribute Prediction Task Are We Solving? Within-Network, Across-Network, or Across-Layer Tasks
  Proceedings of International AAAI Conference on Web and Social Media (ICWSM), 2021.
  (Outstanding Problem-Solution Paper Award)
  [code]
  
  
• W Cai, J Ugander
  Experience-Driven Peer Effects: Evidence from a Large Natural Experiment
  Proceedings of International AAAI Conference on Web and Social Media (ICWSM), 2021.
  [code]
  
  
• A Chin, D Eckles, J Ugander
  Evaluating stochastic seeding strategies in networks
  Management Science, 2021.
  [arxiv pre-print] [code] [twitter thread]
  
  
• A Seshadri, S Ragain, J Ugander
  Learning Rich Rankings
  Advances in Neural Information Processing Systems (NeurIPS) 33, 2020.
  [code] [twitter thread]
  
  
• J Overgoor, G Supaniratisai, J Ugander
  Scaling Choice Models of Relational Social Data
  Proc. 26th ACM SIGKDD Int'l Conf. on Knowledge Discovery and Data Mining (KDD), 2020.
  [talk slides, SIAMNS by Jan Overgoor] [code] [twitter thread]
  
  
• A Awadelkarim, J Ugander
  Prioritized Restreaming Algorithms for Balanced Graph Partitioning
  Proc. 26th ACM SIGKDD Int'l Conf. on Knowledge Discovery and Data Mining (KDD), 2020.
  [talk slides, SIAMNS by Amel Awadelkarim] [code] [twitter thread]
  
  
• J Su, K Kamath, A Sharma, J Ugander, S Goel
  An Experimental Study of Structural Diversity in Social Networks
  Proceedings of International AAAI Conference on Web and Social Media (ICWSM), 2020.
  (Best Paper Award)
  [talk slides, CODE@MIT17 by Jessica Su] [arXiv pre-print] [twitter thread]
  
  
• H Yin, A Benson, J Ugander
  Measuring Directed Triadic Closure with Closure Coefficients
  Network Science, 2020.
  [code] [arXiv pre-print]
  
  
• A Seshadri, J Ugander
  Fundamental Limits of Testing the Independence of Irrelevant Alternatives in Discrete Choice
  Extended abstract, ACM Conference on Economics and Computation (EC), 2019.
  [talk video, EC] [talk slides, EC by Arjun Seshadri] [twitter thread]
  
  
• A Seshadri, A Peysakhovich, J Ugander
  Discovering Context Effects from Raw Choice Data
  International Conference on Machine Learning (ICML), 2019.
  [talk slides, ICML by Arjun Seshardi] [code] [twitter thread]
  
  
• J Overgoor, A Benson, J Ugander
  Choosing To Grow a Graph: Modeling Network Formation as Discrete Choice
  Proceedings of the World Wide Web Conference (WWW), 2019.
  [talk slides, NetSci19 by Austin Benson] [code] [twitter thread]
  
  
• A Chin, Y Chen, KM Altenburger, J Ugander
  Decoupled smoothing on graphs
  Proceedings of the World Wide Web Conference (WWW), 2019.
  [talk slides, WWW by Yatong Chen] [code]
  
  
• R Makhijani, J Ugander
  Parametric Models for Intransitivity in Pairwise Rankings
  Proceedings of the World Wide Web Conference (WWW), 2019.
  
  
• I Arrieta-Ibarra, J Ugander
  A Personalized BDM Mechanism for Efficient Market Intervention Experiments
  Proc. 19th ACM Conf. on Economics and Computation (EC), 2018.
  [talk slides, EC by Imanol Arrieta-Ibarra] [code]
  
  
• KM Altenburger, J Ugander
  Monophily in social networks introduces similarity among friends-of-friends
  Nature Human Behaviour 2:284–290, 2018.
  [Supplementary Information] [NHB page] [arXiv pre-print] [code]
  
  
• B Fosdick, D Larremore, J Nishimura, J Ugander
  Configuring Random Graph Models with Fixed Degree Sequences
  SIAM Review 60(2):315–355, 2018.
  [talk slides, NetSci17 by Dan Larremore] [arXiv pre-print] [code]
  
  
• J Kleinberg, S Mullainathan, J Ugander
  Comparison-Based Choices
  Proc. 18th ACM Conf. on Economics and Computation (EC), 2017.
  [talk slides, EC] [talk video, EC]
  
  
• D Eckles, B Karrer, J Ugander
  Design and analysis of experiments in networks: Reducing bias from interference
  Journal of Causal Inference 5(1):1-23, 2017.
  [arXiv pre-print] [talk slides, CODE@MIT14]
  
  
• I Kloumann, J Ugander, J Kleinberg
  Block models and personalized PageRank
  Proceedings of the National Academy of Sciences (PNAS) 114(1):33-38, 2017.
  [talk slides, Google Research] [arXiv pre-print]
  
  
• S Ragain, J Ugander
  Pairwise Choice Markov Chains
  Advances in Neural Information Processing Systems (NeurIPS) 29, 2016.
  [talk slides, CODE@MIT17] [Code and data]
  
  
• J Ugander, R Drapeau, C Guestrin
  The Wisdom of Multiple Guesses
  Proc. 16th ACM Conf. on Economics and Computation (EC), 2015.
  [talk slides, EC] [Code and data]
  
  
• AZ Jacobs, SF Way, J Ugander, A Clauset
  Assembling thefacebook: Using Heterogeneity to Understand Online Social Network Assembly
  Proc. 7th ACM Int'l Conf. on Web Science (WebSci), 2015.
  [talk slides, ICCSS16 by Abigail Jacobs] [Supplementary data]
  
  
• J Ugander, B Karrer, L Backstrom, J Kleinberg
  Graph Cluster Randomization: Network Exposure to Multiple Universes
  Proc. 19th ACM SIGKDD Int'l Conf. on Knowledge Discovery and Data Mining (KDD), 2013.
  [talk video, KDD]
  
  
• J Nishimura, J Ugander
  Restreaming Graph Partitioning: Simple Versatile Algorithms for Advanced Balancing
  Proc. 19th ACM SIGKDD Int'l Conf. on Knowledge Discovery and Data Mining (KDD), 2013.
  [Cython implementation by Justin Vincent]
  
  
• J Ugander, L Backstrom, J Kleinberg
  Subgraph Frequencies: Mapping the Empirical and Extremal Geography of Large Graph Collections
  Proc. 22nd Int'l World Wide Web Conf. (WWW), 2013.
  [talk slides, WWW] [Summary and R code] [talk video by Jon Kleinberg]
  
  
• DM Romero, C Tan, and J Ugander
  On the Interplay Between Social and Topical Structure
  Proc. 7th AAAI Int'l Conf. on Weblogs and Social Media (ICWSM), 2013.
  [talk slides, ICWSM by Chenhao Tan]
  
  
• J Ugander, L Backstrom
  Balanced Label Propagation for Partitioning Massive Graphs
  Proc. 6th ACM Int'l Conf. on Web Search and Data Mining (WSDM), 2013.
  (Best Student Paper Award)
  [talk slides, WSDM]
  
  
• J Ugander, L Backstrom, C Marlow, J Kleinberg
  Structural Diversity in Social Contagion
  Proceedings of the National Academy of Sciences (PNAS), 109(16) 5962-5966, 17 April 2012.
  [talk slides, NetSci]
  
  
• J Ugander, B Karrer, L Backstrom, C Marlow
  The Anatomy of the Facebook Social Graph.
  arXiv, 2011.
  
  
• L Backstrom, P Boldi, M Rosa, J Ugander, S Vigna
  Four Degrees of Separation
  Proc. 4th ACM Int'l Conf. on Web Science (WebSci), 2012.
  (Best Paper Award)
  [HyperANF metadata and degree distributions]
  
  
• M Larsson, J Ugander
  A Concave Regularization Technique for Sparse Mixture Models
  Advances in Neural Information Processing Systems (NeurIPS) 24, 2011.
  [NIPS poster]
  
  
• J Ugander, MJ Dunlop, RM Murray
  Analysis of a Digital Clock for Molecular Computing
  Proc. 2007 American Control Conference (ACC), New York, July 2007. p. 1595-1599.

Theses:

• Computational Perspectives on Large-Scale Social Networks
  Ph.D. Thesis, Center for Applied Mathematics, Cornell University, August 2014.
  
  
• Efficiency and Fragility in Loss Networks
  Part III Essay, University of Cambridge, May 2009.
  
  
• Delay-dependent Stability of Genetic Regulatory Networks
  M.Sc. Thesis, Department of Automatic Control, Lund University, July 2008.

Teaching

• MS&E 135: Networks (Winter 2021)
  Previous versions: Winter 2020, Winter 2019, Spring 2018, Winter 2017, Spring 2016
  This course provides an introduction to how networks underly our social, technological, and natural worlds, with an emphasis on developing intuitions for broadly applicable concepts in network analysis. The course will include: an introduction to graph theory and graph concepts; social networks; information networks; the aggregate behavior of markets and crowds; network dynamics; information diffusion; the implications of popular concepts such as "six degrees of separation", the "friendship paradox", and the "wisdom of crowds".
  
  
• MS&E 234: Data Privacy and Ethics (Winter 2021)
  Previous versions: Winter 2020, Winter 2019, Spring 2018
  This course engages with ethical challenges in the modern practice of data science. The three main focuses are data privacy, personalization and targeting algorithms, and online experimentation. The focus on privacy raises both practical and theoretical considerations. As part of the module on experimentation, students are required to complete the Stanford IRB training for social and behavioral research. The course assumes a strong technical familiarity with the practice of machine learning and data science. Recommended: 221, 226, CS 161, or equivalents.
  
  
• MS&E 334: Topics in Social Data (Fall 2018)
  Previous versions: Fall 2017, Fall 2016, Fall 2015
  This course provides a in-depth survey of methods research for the analysis of large-scale social and behavioral data. There will be a particular focus on recent developments in discrete choice theory and preference learning. Connections will be made to graph-theoretic investigations common in the study of social networks. Topics will include random utility models, item-response theory, ranking and learning to rank, centrality and ranking on graphs, and random graphs. The course is intended for Ph.D. students, but masters students with an interested in research topics are welcome. Recommended: 221, 226, CS161, or equivalents. One-off lecture notes:

Spectral theory for planar graphs, including the Spielman-Teng partitioning result. (9/29/2011)

Grant/project pages

• Army Research Office (ARO) Young Investigator Award (2019-2021): Models and algorithms for higher order network inference (Award #73348-NS-YIP)
• National Science Foundation (NSF) CRII (2017-2019): Algorithms for Causal Inference on Networks (Award #1657104)

Activities

I have organized or co-chaired the following workshops:

• 2018: Fifth Annual SIAM Workshop on Network Science (SIAM NS)
• 2016: IPAM Cultural Analytics Workshop on Cultural Patterns
• 2016: NIPS Workshop on Networks in the Social and Information Sciences
• 2015: JMM Special Session on Network Science
• 2014: NIPS Workshop on Networks: From Graphs to Rich Data

I am serving/have served on the Program Committee of the following conferences/workshops:

• 2020: ACM WSDM, WWW, GraphEx
• 2019: ACM WSDM, WWW, ACM EC (senior PC), ICCSS, SIAM NS, GraphEx
• 2018: ACM WSDM, WWW, ACM EC, SIAM NS (co-chair), Black in AI
• 2017: ACM WSDM, WWW (senior PC), NIPS (reviewer)
• 2016: WWW, ACM EC, ICCSS, ACM KDD, SIAM NS, AAAI IJCAI, AAAI ICWSM (senior PC), SIAM SDM
• 2015: WWW, ACM EC, ICCSS, ACM KDD, SIAM SDM
• 2014: WWW, SocInfo, ACM CIKM, AAAI ICWSM
• 2013: WebSci

I have also served as a reviewer for the following journals:

• Proceedings of the National Academy of Sciences; Science; SIAM Review; Network Science (CUP); Journal of Complex Networks (Oxford); Journal of the American Statistical Association; Annals of Applied Statistics (IMS); Management Science (INFORMS); Transactions on Network Science & Engineering (IEEE); Social Network Analysis and Mining (Springer); Scientific Reports (NPG); PLOS One; Physical Review X.

Figure 2. The summit of Fairview Dome, Yosemite National Park, July 2012.

Selected press coverage

• Nature, August 2019: Spotlight on Early-Career Researchers interview
• Scientific American, June 2018: Friends of Friends Can Reveal Hidden Information about a Person
• BBC Radio 4: Digital Human, May 2016: Lost and Found
• MIT Technology Review (blog), April 2015: Network Archaeologists Discover Two Types of Social Network Growth
• Wall Street Journal (blog), June 2014: Studying Your Users: Facebook's Greatest Hits
• Facebook Engineering Blog, April 2014: Large-scale graph partitioning with Apache Giraph
• Wired (blog), April 2013: Exploring the Space of Human Interaction
• SmartPlanet, October 2012: Q&A: Why you have fewer friends than your friends on Facebook
• NY Times Opinionator, September 2012: Friends You Can Count On
• Nature, August 2012: Computational Social Science: Making the Links
• American Mathematical Society, July 2012: SIAM Annual Meeting 2012 Highlights
• Science Now, April 2012: How Facebook "Contagion" Spreads
• New Scientist, April 2012: Variety, Not Viral Spread, is Key to Facebook Growth
• The Economist, April 2012: Social Contagion: Conflicting Ideas
• The Economist Daily Chart, March 2012: The Sun Never Sets
• The Telegraph, March 2012: Facebook: British Empire Still Shapes Friendship Patterns
• NPR (on-air interview), November 2011: 4.74 Degrees of Separation
• Wired, Novemeber 2011: Facebook Study: It's a Small(er) World After All
• TechCrunch, Novemeber 2011: 4.74 - Facebook Wins By Getting Us Closer Than Six Degrees
• NY Times, November 2011: Between You and Me? 4.74 Degrees

Bookmarklets

• scholarfy: a bookmarklet I wrote to transfer search queries to Google Scholar.
• JSTORpdf: a bookmarklet I wrote to access PDFs faster on JSTOR.
• googURL: a bookmarklet I wrote to circumvent some paywalls using Google.

Climbing

My wife and I spend a lot of our free time climbing. Sometimes we write trip reports.

First ascents:

• West Maiden, Southwest Face And Other Climbs, Arrigetch Peaks, Brooks Range, Alaska, American Alpine Journal, 2016.

Other trip reports:

• Ingalls Peak Traverse, Cascade Range, Washington, October 2014.
• Backbone Ridge, Dragontail Peak, Cascade Range, Washington, June 2014.
• Rio de Janeiro, Brazil, May 2013.

I also enjoy trail running. Very occasionally I'll run competitively.

Misc

• National Weather Service probabilistic snow forecasts, also known as "Where is it dumping powder?" (only active during North American winter).
• OpenSnow Tahoe blog, with detailed discussions of Tahoe snow forecasts.
• ForecastAdvisor.com for Palo Alto, which tracks the accuracy of different weather forecasts.