10.8k citations
- Université de MontréalCA36 papers
- McGill UniversityCA26 papers
- Centre National de la Recherche ScientifiqueFR20 papers
- Stanford UniversityUS14 papers
- École de Technologie SupérieureCA13 papers
- Louisiana State UniversityUS13 papers
- Cornell UniversityUS12 papers
- Georgia Institute of TechnologyUS12 papers
- Sorbonne UniversitéFR12 papers
- Université Paris-SaclayFR12 papers
- University College LondonGB12 papers
- California Institute of TechnologyUS11 papers
14 papers · 2 filters
Models of Computational Profiles to Study the Likelihood of DNN Metamorphic Test Cases
Ettore Merlo, Mira Marhaba, Foutse Khomh +2
Neural network test cases are meant to exercise different reasoning paths in an architecture and used to validate the prediction outcomes. In this paper, we introduce "computationa…
Analytically Tractable Hidden-States Inference in Bayesian Neural Networks
Luong-Ha Nguyen, James-A. Goulet
With few exceptions, neural networks have been relying on backpropagation and gradient descent as the inference engine in order to learn the model parameters, because the closed-fo…
Causal Reinforcement Learning using Observational and Interventional Data
Maxime Gasse, Damien Grasset, Guillaume Gaudron +1
Learning efficiently a causal model of the environment is a key challenge of model-based RL agents operating in POMDPs. We consider here a scenario where the learning agent has the…
Optimal Counterfactual Explanations in Tree Ensembles
Axel Parmentier, Thibaut Vidal
Counterfactual explanations are usually generated through heuristics that are sensitive to the search's initial conditions. The absence of guarantees of performance and robustness…
Rethinking Graph Transformers with Spectral Attention
Devin Kreuzer, Dominique Beaini, William L. Hamilton +2
In recent years, the Transformer architecture has proven to be very successful in sequence processing, but its application to other data structures, such as graphs, has remained li…
Exploring dual information in distance metric learning for clustering
Rodrigo Randel, Daniel Aloise, Alain Hertz
Distance metric learning algorithms aim to appropriately measure similarities and distances between data points. In the context of clustering, metric learning is typically applied…