53 citations · 91 across the 11 of their papers we have counts for
11 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…
Parallel MCMC Without Embarrassing Failures
Daniel Augusto de Souza, Diego Mesquita, Samuel Kaski +1
Embarrassingly parallel Markov Chain Monte Carlo (MCMC) exploits parallel computing to scale Bayesian inference to large datasets by using a two-step approach. First, MCMC is run i…
Rethinking pooling in graph neural networks
Diego Mesquita, Amauri H. Souza, Samuel Kaski
Graph pooling is a central component of a myriad of graph neural network (GNN) architectures. As an inheritance from traditional CNNs, most approaches formulate graph pooling as a…
Federated Stochastic Gradient Langevin Dynamics
Khaoula El Mekkaoui, Diego Mesquita, Paul Blomstedt +1
Stochastic gradient MCMC methods, such as stochastic gradient Langevin dynamics (SGLD), employ fast but noisy gradient estimates to enable large-scale posterior sampling. Although…
Meta-analysis of Bayesian analyses
Paul Blomstedt, Diego Mesquita, Omar Rivasplata +4
Meta-analysis aims to generalize results from multiple related statistical analyses through a combined analysis. While the natural outcome of a Bayesian study is a posterior distri…
Embarrassingly parallel MCMC using deep invertible transformations
Diego Mesquita, Paul Blomstedt, Samuel Kaski
While MCMC methods have become a main work-horse for Bayesian inference, scaling them to large distributed datasets is still a challenge. Embarrassingly parallel MCMC strategies ta…