Professor and Canada Research Chair in Machine Learning
School of Engineering, University of Guelph
Faculty Member and Canada CIFAR AI Chair
Vector Institute for Artificial Intelligence
Academic Director, NextAI
Richards Building, Room 3515
Guelph, Ontario, N1G 2W1
To contact me by email or phone, please visit the University of Guelph Directory.
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.
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. At the end of 2023, I concluded my tenure as the Research Director at the Vector Institute to focus more on my research.
A complete list of my publications is available on Google Scholar.
Zahra Gharaee, ZeMing Gong, Nicholas Pellegrino, Iuliia Zarubiieva, Joakim Bruslund Haurum, Scott C Lowe, Jaclyn TA McKeown, Chris CY Ho, Joschka McLeod, Yi-Yun C Wei, Jireh Agda, Sujeevan Ratnasingham, Dirk Steinke, Angel X Chang, Graham Taylor, and Paul W. Fieguth. A step towards worldwide biodiversity assessment: The BIOSCAN-1M insect dataset. In Advances in Neural Information Processing Systems, 2023. [ bib | http ]
Michal Lisicki, Mihai Nica, and Graham Taylor. Bandit-driven batch selection for robust learning under label noise. In Neural Information Processing Systems (NeurIPS) Workshop on Optimization for Machine Learning, 2023. [ bib | http ]
Joakim Bruslund Haurum, Sergio Escalera, Graham Taylor, and Thomas Moeslund. Which tokens to use? investigating token reduction in vision transformers. In International Conference on Computer Vision (ICCV) Workshop on New Ideas in Vision Transformers, 2023. [ bib ]
Kevin Kasa and Graham Taylor. Empirically validating conformal prediction on modern vision architectures under distribution shift and long-tailed data. In International Conference on Machine Learning (ICML) Workshop on Structured Probabilistic Inference & Generative Modeling, 2023. [ bib ]
Mateusz Jurewicz, Graham Taylor, and Leon Derczynski. The Catalog Problem: Clustering and Ordering Variable-Sized Sets. In International Conference on Machine Learning (ICML), 2023. [ bib ]
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 ]