Department of Computer Science
University of Toronto
Mengye Ren is a PhD student in the machine learning group of the Department of Computer Science at the University of Toronto, working with Prof. Richard Zemel. From 2017 to 2021, he was also a research scientist at Uber Advanced Technologies Group (ATG), working with Prof. Raquel Urtasun. His research focuses on making machines learn in more natural environments with less labeled data.
Areas: machine learning, computer vision, meta-learning, representation learning, few-shot learning, brain & cognitively inspired learning, robot learning, self-driving vehicles
My key research question is: how do we enable human-like, agent-based machine intelligence to continually learn, reason, and adapt in naturalistic environments? Towards this goal of building a more general and flexible AI, my research has centered on developing meta-learning and representation learning algorithms.
Some recent research highlights include:
SketchEmbedNet: Learning novel concepts by imitating drawings. Alexander Wang
*, Mengye Ren
*, Richard Zemel. ICML, 2021. [arxiv]
Self-supervised representation learning from flow equivariance. Yuwen Xiong, Mengye Ren, Wenyuan Zeng, Raquel Urtasun. arXiv preprint 2101.06553, 2021. [arxiv]
Flexible few-shot learning of contextual similarity. Mengye Ren
*, Eleni Triantafillou
*, Kuan-Chieh Wang
*, James Lucas
*, Jake Snell, Xaq Pitkow, Andreas S. Tolias, Richard Zemel. arXiv preprint 2012.05895, 2020. [arxiv]
LoCo: Local contrastive representation learning. Yuwen Xiong, Mengye Ren, Raquel Urtasun. NeurIPS, 2020. [arxiv]
Graph hypernetworks for neural architecture search. Chris Zhang, Mengye Ren, Raquel Urtasun. ICLR, 2019. [arxiv]
Meta-learning for semi-supervised few-shot classification. Mengye Ren, Eleni Triantafillou
*, Sachin Ravi
*, Jake Snell, Kevin Swersky, Joshua B. Tenenbaum, Hugo Larochelle, Richard S. Zemel. ICLR, 2018. [link][arxiv] [code]
Towards continual and compositional few-shot learning. Stanford University. Stanford, CA, USA. 2020/10.
Towards continual and compositional few-shot learning. Brown University. Providence, RI, USA. 2020/09.
Towards continual and compositional few-shot learning. MIT. Cambridge, MA, USA. 2020/09.
Towards continual and compositional few-shot learning. Mila. Montréal, Québec, Canada. 2020/08.
Meta-learning for more human-like learning algorithms. Columbia University. New York, NY, USA. 2019/10. [slides]
Meta-learning for weakly supervised learning. INRIA Grenoble Rhône-Alpes. Grenoble, France. 2018/07. [slides]
Meta-learning and learning to reweight examples. Max Planck Institute for Intelligent Systems. Tübingen, Germany. 2018/06. [slides]
Meta-learning for weakly supervised learning. NEC Laboratories America. Princeton, NJ, USA. 2018/06. [slides]