Christian Gagné
About
Appointed Canada CIFAR AI Chair – 2019
Christian Gagné is a Canada CIFAR AI Chair at Mila and a full professor in the Department of Electrical and Computer Engineering and the director of Institute Intelligence and Data (IDD) at Université Laval.
Gagné’s research interests include method development for machine learning and stochastic optimization. In particular, he is interested in deep neural networks, learning and transfer of representations, meta-learning as well as multitask learning. He is also interested in optimization approaches based on probabilistic models as well as evolutionary algorithms, involving, for example, black box optimization, and automatic programming.
Awards
- Best Paper Award, Canadian AI, 2020
- Best Paper Award, GECCO, 2009
- Best Paper Award, GECCO, 2002
Relevant Publications
Changjian, S., Xu, G., Chen, Q., Li, J., Ling, C.X., Arbel, T., Wang, B., & Gagné, C. (2022). On learning fairness and accuracy on multiple subgroups. Advances in Neural Information Processing Systems 35:34121-34135.
Arman, A., Larochelle, H., Lalonde, J-F., & Gagné, C. (2022). Matching feature sets for few-shot image classification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9014-9024.
Afrasiyabi, A., Lalonde, J-F., & Gagné C. (2021). Mixture-Based Feature Space Learning for Few-Shot Image Classification. In International Conference on Computer Vision (ICCV).
Bouchard, C., Wiesner, T., Deschênes, A., Lavoie-Cardinal, F., & Gagné, C. (2021). Task-Assisted GAN for Resolution Enhancement and Modality Translation in Fluorescence Microscopy.
Shui, C., Li, Z., Li, J., Gagné, C., Ling, C., & Wang, B. (2021). Aggregating From Multiple Target-Shifted Sources.