Perouz Taslakian

Research Lead

Low Data Learning

Perouz Taslakian is a Research Scientist and the Research Lead of the Low Data Learning Program at ServiceNow Research. She holds a Ph.D. in Computer Science from McGill University, where Professors Luc Devroye and Godfried Toussaint supervised her. Her academic background is in discrete and computational geometry. She spent time as a professor and the chair of the computational sciences program at the American University of Armenia before moving to the industry, where she focused her research efforts on AI. Perouz’s research interests include learning from graph-like data, reasoning over knowledge bases, and integrating causality in machine learning models.

Publications

Object-centric Compositional Imagination for Visual Abstract Reasoning. Rim Assouel, Perouz Taslakian, David Vazquez, Pau Rodriguez, Yoshua Bengio. At Workshop at the International Conference on Learning Representations (ICLR), 2022.

PDF Cite

Typing assumptions improve identification in causal discovery - theory and algorithms. Philippe Brouillard, Perouz Taslakian, Alexandre Lacoste, Sébastien Lachapelle, Alexandre Drouin. At Causal Learning and Reasoning (CLeaR), 2022.

PDF Cite Code

Typing assumptions improve identification in causal discovery - Report and comments on future directions. Philippe Brouillard, Perouz Taslakian, Alexandre Lacoste, Sébastien Lachapelle, Alexandre Drouin. At Workshop at the Neural Information Processing Systems (NeurIPS), 2021.

PDF Cite Code

Typing assumptions improve identification in causal discovery. Philippe Brouillard, Perouz Taslakian, Alexandre Lacoste, Sébastien Lachapelle, Alexandre Drouin. At Workshop at the International Conference on Machine Learning (ICML), 2021.

PDF Cite Code

Knowledge Hypergraphs: Prediction Beyond Binary Relations. Bahare Fatemi, Perouz Taslakian, David Vazquez, David Poole. At International Join Conference on Artificial Intelligence (IJCAI), 2020.

PDF Cite Code

Knowledge Hypergraphs: Prediction Beyond Binary Relations. Bahare Fatemi, Perouz Taslakian, David Vazquez, David Poole. At Workshop at the Association for the Advancement of Artificial Intelligence (AAAI), 2020.

PDF Cite Code

Knowledge Hypergraphs: Prediction Beyond Binary Relations. Bahare Fatemi, Perouz Taslakian, David Vazquez, David Poole. At Women in Machine Learning (WiML), 2019.

PDF Cite Code

Context-Aware Visual Compatibility Prediction. Guillem Cucurull, Perouz Taslakian, David Vazquez. At Computer Vision and Pattern Recognition (CVPR), 2019.

PDF Cite Code

Efficient Multi-Robot Coverage of a Known Environment. Nare Karapetyan, Kelly Benson, Chris McKinney, Perouz Taslakian, Ioannis Rekleitis. At International Conference on Intelligent Robots and Systems (IROS), 2017.

PDF Cite

Continuous Yao Graphs. Luis Barba, Prosenjit Bose, Jean-Lou De Carufel, Mirela Damian, Rolf Fagerberg, André van Renssen, Perouz Taslakian, Sander Verdonschot. At Journal on Computational Geometry, 2017.

PDF Cite