Osmar Zaïane’s research encompasses fundamental as well as applied research, particularly in precision health, but also in industry such as machine failure prediction and machine adaptation with reinforcement learning. In supervised learning, he is interested in associative classifiers which learn rule-based interpretable models. His work centers on making them even more competitive and to harness them as a surrogate model around black boxes for explainable AI. In Social Network Analysis, he investigates new and efficient approaches for community search and mining, as well as link prediction in attributed and probabilistic graphs. He is also captivated by automatic response generation for conversational agents. He is exploring ways to express emotions in text, force a discussion to stay on topic, or ground a response on existing knowledge graphs using new architectures of deep learning with attention mechanisms and graph neural networks.
- Great Supervisor Award, University of Alberta, 2018
- ACM – SGKDD Service Award, 2010
- Killam Annual Professorship, 2009
- IEEE – ICDM Outstanding Service Award, 2009
- McCalla Research Professorship, 2008
- Jiang, H., Cao, P., Xu, M., Yang, J., & Zaïane, O. (2020). Hi-GCN: A hierarchical graph convolution network for graph embedding learning of brain network and brain disorders prediction. Computers in Biology and Medicine, 127, 104096.
- Gharaghooshi, S. Z., Zaïane, O. R., Largeron, C., Zafarmand, M., & Liu, C. (2020, April). Addressing the resolution limit and the field of view limit in community mining. In International Symposium on Intelligent Data Analysis (pp. 210-222). Springer, Cham.
- Bellinger, C., Sharma, S., Japkowicz, N., & Zaïane, O. R. (2019). Framework for extreme imbalance classification: SWIM—Sampling with the majority class. Knowledge and Information Systems, 1-26.
- Farruque, N., Zaïane, O., & Goebel, R. (2019, September). Augmenting Semantic Representation of Depressive Language: From Forums to Microblogs. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases (pp. 359-375). Springer, Cham.
- Huang, C., Zaïane, O. R., Trabelsi, A., & Dziri, N. (2018, June). Automatic dialogue generation with expressed emotions. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers) (pp. 49-54).
CIFAR is a registered charitable organization supported by the governments of Canada, Alberta, Ontario, and Quebec as well as foundations, individuals, corporations, and international partner organizations.