William L. Hamilton

I am currently a Visiting Researcher at Facebook AI Research, and I will be joining McGill University as an Assistant Professor of Computer Science in January 2019. My research focuses on three key problems:

  1. Representation learning on graphs and complex networks.
  2. Social applications of machine learning (e.g., misinformation detection).
  3. Developing frameworks for socially-responsible machine learning.

Recent news
  • September 2018: Two papers accepted at NIPS 2018: One on hierarchical graph neural networks and the other on embedding logical queries on knowledge graphs.
  • May 2018: Our GraphRNN paper was accepted at ICML 2018. We develop a deep generative model for graph-structured data.
  • May 2018: Joint paper with Pinterest accepted at KDD 2018. We showcase the largest-ever application of graph neural networks, using them to power a production recommender system with billions of items.
  • May 2018: I will be joining McGill University's School of Computer Science as an Assistant Professor in January 2019!
  • April 2018: Our tutorial "Representation Learning on Graphs and Networks" was a big success at TheWebConf 2018 (aka WWW 2018)! Thanks to everyone who attended, and for those who could not make it, the slides are available on the tutorial website.
2018
Hierarchical Graph Representation Learning with Differentiable Pooling
Jiaxuan You, Rex Ying, Christopher Morris, Xiang Ren, William L. Hamilton, Jure Leskovec.  
Proceedings of NIPS (to appear). 2018.
pdf (arxiv)
Embedding Logical Queries on Knowledge Graphs
William L. Hamilton, Marinka Zitnik, Payal Bajaj, Dan Jurafsky, Jure Leskovec.  
Proceedings of NIPS (to appear). 2018.
GraphRNN: A Deep Generative Model for Graphs
Jiaxuan You, Rex Ying, Xiang Ren, William L. Hamilton, Jure Leskovec.  
Proceedings of ICML. 2018.
pdf (arxiv)
Graph Convolutional Neural Networks for Web-scale Recommender Systems
Rex Ying, Ruining He, Kaifeng Chen, Pong Eksombatchai,
William L. Hamilton, Jure Leskovec.  
Proceedings of KDD (to appear). 2018.
Community Interaction and Conflict on the Web
Srijan Kumar, William L. Hamilton, Jure Leskovec, Dan Jurafsky.      
Proceedings of The Web Conference (WWW). 2018.
pdf (arxiv)   project website (code + data)
2017
Representation Learning on Graphs: Methods and Applications
William L. Hamilton, Rex Ying, Jure Leskovec.                  
IEEE Data Engineering Bulletin. 2017.
pdf
Inductive Representation Learning on Large Graphs
William L. Hamilton*, Rex Ying*, Jure Leskovec.                
Proceedings of NIPS. 2017.
pdf     project website (code+data)
Community Identity and User Engagement in a
Multi-Community Landscape

Justine Zhang*, William L. Hamilton*, Cristian Danescu-Niculescu-Mizil,
Jure Leskovec, Dan Jurafsky.  
Proceedings of ICWSM. 2017.
pdf
Loyalty in Online Communities
William L. Hamilton*, Justine Zhang*, Cristian Danescu-Niculescu-Mizil,
Jure Leskovec, Dan Jurafsky.
Proceedings of ICWSM (short paper). 2017.
pdf
Language from Police Body Camera Footage Shows Racial Disparities in Officer Respect
Rob Voigt, Nicholas P. Camp, Vinod Prabhakaran, William L. Hamilton, Rebecca C. Hetey, Camilla M. Griffiths, David Jurgens, Dan Jurafsky, and Jennifer L. Eberhardt.
Proceedings of the National Academy of Science (PNAS). 2017.
pdf
2016
Inducing Domain-Specific Sentiment Lexicons from Unlabeled Corpora
William L. Hamilton, Kevin Clark, Jure Leskovec, Dan Jurafsky.
Proceedings of EMNLP. 2016.
pdf     project website (code+data)
Cultural Shift or Linguistic Drift? Comparing Two Computational Models of Semantic Change
William L. Hamilton, Jure Leskovec, Dan Jurafsky.
Proceedings of EMNLP. 2016.
pdf     project website (code+data)
Learning Linguistic Descriptors of User Roles in Online Communities
Alex Wang, William L. Hamilton, Jure Leskovec.
EMNLP Workshop on Computational Social Science (NLP+CSS). 2016.
pdf
Diachronic Word Embeddings Reveal Statistical Laws of Semantic Change
William L. Hamilton, Jure Leskovec, Dan Jurafsky.
Proceedings of ACL. 2016.
pdf     project website (code+data)
Predicting the Rise and Fall of Scientific Topics from Trends in their Rhetorical Framing
Vinodkumar Prabhakaran, William L. Hamilton, Dan McFarland, Dan Jurafsky.
Proceedings of ACL. 2016.
pdf
2014
Compressed Predictive State Representation: An Efficient Moment-Method for Sequence Prediction and Sequential Decision Making
William L. Hamilton
MSc Thesis. McGill University.
Canadian AI Association (CAIAC) 2014 MSc Thesis Award
pdf
Methods of Moments for Learning Stochastic Languages: Unified Presentation and Empirical Comparison
Borja Balle*, William L. Hamilton*, Joelle Pineau  
Proceedings of ICML. 2014.
pdf
Efficient Learning and Planning with Compressed Predictive States  
William L. Hamilton, Mahdi Milani Fard, Joelle Pineau.
Journal of Machine Learning Research (JMLR). 2014.
pdf  code
2013
Modelling Sparse Dynamical Systems with Compressed Predictive State Representations
William L. Hamilton, Mahdi Milani Fard, Joelle Pineau.
Proceedings of ICML. 2013.
pdf  code

William (Will) Hamilton is currently a Visiting Researcher at FAIR Montreal, and he will be joining McGill University as an Assistant Professor in Computer Science in January 2019. Will completed his PhD in Computer Science in Stanford University in 2018, working jointly in the NLP and SNAP groups, where he was co-advised by Dan Jurafsky and Jure Leskovec. His interests lie at the intersection of machine learning, network science, natural language processing, and computational social science. Will was the SAP Stanford Graduate Fellow, received the Cozzarelli Best Paper Award from the Proceedings of the National Academy of Sciences (PNAS) in 2017, and his work has been featured in numerous media outlets, including Wired, The New York Times, and The BBC.

Prior to Stanford, Will completed a BSc and MSc at McGill University, where he worked on reinforcement learning and machine learning theory in the Reasoning and Learning Lab under the supervision of Joelle Pineau. Will was awarded the Canadian AI MSc Thesis Award for his work at McGill and received an honorable mention for the CRA Undergraduate Researcher of the Year.

During the summers of 2013 and 2014, Will interned at Amazon as a software development engineer and research scientist, where he designed and implemented new algorithms to forecast demand for cloud computing services.


Stanford University Stanford NLP SNAP

Visiting Researcher
FAIR Montreal

wleif(at)stanford.edu


CV
Google Scholar


Many thanks to David Jurgens for the site template/inspiration