16 citations · 25 across the 7 of their papers we have counts for
8 papers
Embarrassingly Parallel GFlowNets
Tiago da Silva, Luiz Max Carvalho, Amauri Souza +2
GFlowNets are a promising alternative to MCMC sampling for discrete compositional random variables. Training GFlowNets requires repeated evaluations of the unnormalized target dist…
In-n-Out: Calibrating Graph Neural Networks for Link Prediction
Erik Nascimento, Diego Mesquita, Samuel Kaski +1
Deep neural networks are notoriously miscalibrated, i.e., their outputs do not reflect the true probability of the event we aim to predict. While networks for tabular or image data…
Expert-Aided Causal Discovery of Ancestral Graphs
Tiago da Silva, Bruna Bazaluk, Eliezer de Souza da Silva +6
Causal discovery (CD) is an important component of many scientific applications, yet most techniques produce unreliable point estimates that often contradict expert knowledge. To m…
Locking and Quacking: Stacking Bayesian model predictions by log-pooling and superposition
Yuling Yao, Luiz Max Carvalho, Diego Mesquita +1
Combining predictions from different models is a central problem in Bayesian inference and machine learning more broadly. Currently, these predictive distributions are almost exclu…
Distill n' Explain: explaining graph neural networks using simple surrogates
Tamara Pereira, Erik Nascimento, Lucas E. Resck +2
Explaining node predictions in graph neural networks (GNNs) often boils down to finding graph substructures that preserve predictions. Finding these structures usually implies back…
Provably expressive temporal graph networks
Amauri H. Souza, Diego Mesquita, Samuel Kaski +1
Temporal graph networks (TGNs) have gained prominence as models for embedding dynamic interactions, but little is known about their theoretical underpinnings. We establish fundamen…