Hi, I'm Joey Bose,

About Me

Joey Bose is a Post-Doctoral Fellow at University of Oxford working with Michael Bronstein and an ML scientist at Dreamfold. He completed his PhD at McGill/Mila under the supervision of Will Hamilton, Gauthier Gidel, and Prakash Panagaden. His research interests span Generative Modelling, Differential Geometry for Machine Learning with a current emphasis on understanding symmetries, equivariances and invariances in data. Previously, he completed his Bachelors and Master’s degrees from the University of Toronto working on adversarial attacks against face detection and is the President and CEO of FaceShield Inc an educational platform for digital privacy for facial data. His work has been featured in Forbes, CBC, VentureBeat and other media outlets and is generously supported by the IVADO PhD Fellowship.

Research Interests

Generative Models
Normalizing Flows
Equivariant Networks
Adversarial Attacks
Graph Neural Networks
Pytorch
Pytorch-Geometric
Fall 2022 COMP760 Geometry and Generative Models

Education & Experience

For more information, have a look at my curriculum vitae .

Publications and Pre-Prints

arxiv

arxiv

arxiv

arxiv

arxiv
Generative Models Equivariance

arxiv
Generative Models

arxiv
Strong Lottery Tickets Equivariant Networks Pruning

arxiv
Diffusion Models Riemmanian Geometry Generative Models

arxiv
Causality Generative Models

Equivariant Normalizing Flows Generative Models

arxiv
Continuous Normalizing Flows Generative Models

arxiv
Adversarial Attacks Online Algorithms k-secretary

arxiv
Hallucination Dialogue Systems Knowledge Graphs

arxiv git blog
Adversarial Attacks Game Theory

arxiv git
Knowledge Graphs Negative Sampling

arxiv git blog
Normalizing Flows Hyperbolic Geometry

arxiv git
Link Prediction Graph Neural Networks Meta-Learning

arxiv git
Graph Neural Networks Fairness Node Embeddings

arxiv
Policy Gradient off-policy actor-critic continuous relaxation

arxiv
Coherence Modelling NLP

arxiv
Adversarial Attacks Face Detection

arxiv
Negative Sampling Embeddings Adversarial Sampling

Contact

If you like what I do and want to potentially collaborate feel free to reach out via email. Note for prospective students interested in joining Mila/McGill I cannot assess your candidacy and will not be able to help you get an interview with my advisor. But, I can offer general advice about applying to grad school and the culture of our lab.