Florence Regol

A PhD student from Montreal

About

Welcome to my personal webpage!
I am a PhD candidate at McGill University in Montréal, QC under the supervision of Prof. Mark Coates.

Research Interests

Learning uncertainty (generative models, evaluating generative models, Bayesian inference).

Efficient inference (dynamic networks, theory of dynamic networks).

Machine learning on graphs (node classification/regression, graph sampling, generative graph model, recommender system).

Active learning.

Mostly anything.

Links

CV
Link to participate in my experiment: active learning for humans

Publications

• F. Regol, J. Cotnareanu, T. Glavas, & M. Coates. (2025). Is the Acquisition Worth the Cost? Surrogate Losses for Consistent Two-Stage Classifiers. Proc. Advances in Neural Information Processing Systems (NeurIPS) (Spotlight).
• F. Regol, L. Schwinn, K. Sprague, M. Coates, & T. Markovich. (2025). When to Retrain a Machine Learning Model. Submitted to Proc. Int. Conf. Machine Learning (ICML).
• F. Regol, J. Chataoui, & M. Coates. (2024). Jointly-Learned Exit and Inference for a Dynamic Neural Network. Proc. Int. Conf. Learning Representations (ICLR).
• F. Regol & M. Coates. (2024). Categorical Generative Model Evaluation via Synthetic Distribution Coarsening. Proc. Int. Conf. on Artificial Intelligence and Statistics (AISTATS).
• T. Glavas, J. Chataoui, F. Regol, W. Jabbour, A. Valkanas, B. Oreshkin, & M. Coates. (2024). Dynamic Layer Selection in Decoder-Only Transformers. NeurIPS Efficient Natural Language and Speech Processing Workshop (ENLSP).
• Mai Zeng, F. Regol, & M. Coates. (2024). Interacting Diffusion Processes for Event Sequence Forecasting. Proc. Int. Conf. Machine Learning (ICML).
• F. Regol & M. Coates. (2023). Diffusing Gaussian Mixtures for Generating Categorical Data. Proc. AAAI Conf. on Artificial Intelligence (AAAI).
• F. Regol, S. Pal, J. Sun, Y. Zhang, Y. Geng, & M. Coates. (2022). Node Copying: A Random Graph Model for Effective Graph Sampling. Signal Processing, 192.
• S. Pal, A. Valkanas, F. Regol, & M. Coates. (2022). Bag Graph: Multiple Instance Learning using Bayesian Graph Neural Networks. Proc. AAAI Conf. on Artificial Intelligence.
• Y. Zhang, F. Regol, S. Pal, S. Khan, L. Ma, & M. Coates. (2021). Detection and Defense of Topological Adversarial Attacks on Graphs. Proc. Int. Conf. on Artificial Intelligence and Statistics (AISTATS).
• Sun, J., Guo, W., Zhang, D., Zhang, Y., F. Regol, Hu, Y., … Coates, M. (2020). A Framework for Recommending Accurate and Diverse Items Using Bayesian Graph Convolutional Neural Networks. KDD.
• F. Regol, S. Pal, Y. Zhang, & M. Coates. (2020). Active Learning on Attributed Graphs via Graph Cognizant Logistic Regression and Preemptive Query Generation. Proc. Int. Conf. Machine Learning (ICML).
• S. Pal, S. Malekmohammadi, F. Regol, Y. Zhang, Y. Xu, & M. Coates. (2020). Non-Parametric Graph Learning for Bayesian Graph Neural Networks. Proc. Uncertainty in Artificial Intelligence (UAI).
• F. Regol, S. Pal, & M. Coates. (2019). Node Copying for Protection Against Graph Neural Network Topology Attacks. Proc. IEEE Computational Advances in Multi-Sensor Adaptive Process (CAMSAP).
• S. Pal, F. Regol, & M. Coates. (2019a). Bayesian Graph Convolutional Neural Networks Using Node Copying. Proc. Learning and Reasoning with Graph-Structured Representations Workshop (ICLR).
• S. Pal, F. Regol, & M. Coates. (2019b). Bayesian Graph Convolutional Neural Networks Using Non-Parametric Graph Learning. Proc. Representation Learning on Graphs and Manifolds Workshop (ICML).

Affiliation

Department of Electrical and Computer Engineering
McGill University
McConnell Engineering Building
3480 Rue University, Montréal, QC H3A 0E9

Contact

Email:

florence.robert-regol[at]mail.mcgill.ca