Calgary ML Lab

The Calgary Machine Learning Lab is a research group led by Yani Ioannou within the Schulich School of Engineering at the University of Calgary. The lab has a research focus on improving Deep Neural Network (DNN) training and models, in particular for computer vision applications. Topics of research include: Sparse Neural Network Training, Bias and Robustness of Efficient Deep Learning methods and Domain-Agnostic Self-Supervised Learning.

We collaborate with other research groups within the university with the Artificial Intelligence Research Group, and broader, on applying machine learning and computer vision to novel problems.


Jul 13, 2022 Our workshop paper, (Golubeva et al., 2022), was accepted at the 2nd Sparsity in Neural Networks workshop.
Jun 13, 2022 Our workshop paper, (Adnan et al., 2022), was accepted at the ICML 2022 workshop on spurious correlations, invariance and stability.
Jan 12, 2022 Our paper, (Evci et al., 2022), has been accepted to be presented as an Oral at the 2022 AAAI Conference! The conference had a 15% acceptance rate for posters alone.
Sep 1, 2021 Yani Ioannou started as an Assistant Professor at the University of Calgary.

selected publications

  1. Gradient Flow in Sparse Neural Networks and How Lottery Tickets Win
    Evci, UtkuIoannou, Yani A.Keskin, Cem, and Dauphin, Yann
    In Proceedings of the 36th AAAI Conference on Artificial Intelligence, Vancouver, BC, Canada Feb 2022
  2. Domain-Agnostic Clustering with Self-Distillation
    Adnan, Mohammed,  Ioannou, Yani, Tsai, Chuan-Yung, and Taylor, Graham
    In 2nd NeurIPS Workshop on Self-Supervised Learning: Theory and Practice, Virtual Conference Nov 2021
  3. Condensing Sparse Layers
    Golubeva, Anna, Lasby, Mike,  Ioannou, Yani, and Nica, Mihai
    In 2nd Workshop on Sparsity in Neural Networks, Virtual Jul 2022
  4. ICML
    Monitoring Shortcut Learning using Mutual Information
    Adnan, Mohammed,  Ioannou, Yani, Tsai, Chuan-Yung, Galloway, Angus, Tizhoosh, H. R., and Taylor, Graham W.
    In ICML 2022 Workshop on Spurious Correlations, Invariance, and Stability, Baltimore, MD, USA Jul 2022