I lead the Machine Learning Research Group at the University of Guelph. My research spans a number of topics in deep learning. I am interested in open problems such as how to effectively learn with less labeled data, and how to build human-centred AI systems. I am interested in methodologies such as generative modelling, graph representation learning and sequential decision making. I also pursue applied projects that leverage computer vision to mitigate biodiversity loss.

News

Brief Biography

I received my PhD in Computer Science from the University of Toronto in 2009, where I was advised by Geoffrey Hinton and Sam Roweis. I spent two years as a postdoc at the Courant Institute of Mathematical Sciences, New York University working with Chris Bregler, Rob Fergus, and Yann LeCun. In 2012, I joined the School of Engineering at the University of Guelph as an Assistant Professor. In 2017, I was promoted to Associate Professor and became a member of the Vector Institute for Artificial Intelligence. In 2018, I was honoured as one of Canada's Top 40 under 40. In 2019, I was named a Canada CIFAR AI Chair. I spent 2018-2019 as a Visiting Faculty member at Google Brain, Montreal. In 2021 I was promoted to Professor and I became the interim Research Director at the Vector Institute. In 2022 I became Vector's Research Director.

Research Highlights

A complete list of my publications is available on Google Scholar.

Cong Wei, Brendan Duke, Ruowei Jiang, Parham Aarabi, Graham Taylor, and Florian Shkurti. Sparsifiner: Learning Sparse Instance-Dependent Attention for Efficient Vision Transformers. In Conference on Computer Vision and Pattern Recognition (CVPR), 2023. [ bib | .pdf ]

Angus Galloway, Anna Golubeva, Mahmoud Salem, Mihai Nica, Yani Ioannou, and Graham Taylor. Bounding generalization error with input compression: An empirical study with infinite-width networks. Transactions on Machine Learning Research (TMLR), 2022. [ bib | http ]

Rylee Thompson, Boris Knyazev, Elahe Ghalebi, Jungtaek Kim, and Graham Taylor. On evaluation metrics for graph generative models. In International Conference on Learning Representations (ICLR), 2022. [ bib | http ]

Shashank Shekhar and Graham Taylor. Neural structure mapping for learning abstract visual analogies. In Neural Information Processing Systems (NeurIPS) Workshop on Shared Visual Representations in Human and Machine Intelligence, 2021. [ bib | http ]

Chuan-Yung Tsai and Graham Taylor. DeepRNG: Towards deep reinforcement learning-assisted generative testing of software. In Neural Information Processing Systems (NeurIPS) Workshop on Machine Learning for Systems, 2021. [ bib | .pdf ]

Michal Lisicki, Arash Afkanpour, and Graham Taylor. An empirical study of neural kernel bandits. In Neural Information Processing Systems (NeurIPS) Workshop on Bayesian Deep Learning, 2021. [ bib | http ]

Boris Knyazev, Michal Drozdzal, Graham Taylor, and Adriana Romero-Soriano. Parameter prediction for unseen deep architectures. In Neural Information Processing Systems (NeurIPS), 2021. [ bib | http ]

Hyunsoo Chung, Jungtaek Kim, Boris Knyazev, Jinhwi Lee, Graham Taylor, Jaesik Park, and Minsu Cho. Brick-by-brick: Combinatorial construction with deep reinforcement learning. In Neural Information Processing Systems (NeurIPS), 2021. [ bib | http ]

Terrance DeVries, Miguel Angel Bautista, Nitish Srivastava, Graham Taylor, and Joshua M. Susskind. Unconstrained scene generation with locally conditioned radiance fields. In International Conference on Computer Vision (ICCV), 2021. [ bib | http ]

Boris Knyazev, Harm de Vries, Cătălina Cangea, Graham Taylor, Aaron Courville, and Eugene Belilovsky. Generative compositional augmentations for scene graph prediction. In International Conference on Computer Vision (ICCV), 2021. [ bib | .pdf ]

Yichao Lu, Himanshu Rai, Cheng Chang, Boris Knyazev, Guangwei Yu, Shashank Shekhar, Graham Taylor, and Maksims Volkovs. Context-aware scene graph generation with Seq2Seq transformers. In International Conference on Computer Vision (ICCV), 2021. [ bib ]

Brendan Duke, Abdella Ahmed, Christian Wolf, Parham Aarabi, and Graham Taylor. SSTVOS: Sparse spatiotemporal transformers for video object segmentation. In Proc. of the 34th IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), 2021. [ bib | http ]

Rohit Saha, Brendan Duke, Florian Shkurti, Graham Taylor, and Parham Aarabi. LOHO: Latent optimization of hairstyles via orthogonalization. In Proc. of the 34th IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), 2021. [ bib | http ]

Group Members

Former Group Members