Search Results for author:
Found 19 papers, 7 papers with code
Coherent energy and force uncertainty in deep learning force fields
In machine learning energy potentials for atomic systems, forces are commonly obtained as the negative derivative of the energy function with respect to atomic positions.
Multi-view self-supervised learning for multivariate variable-channel time series
However, for multivariate time series data, the set of input channels often varies between applications, and most existing work does not allow for transfer between datasets with different sets of input channels.
Synthetic data shuffling accelerates the convergence of federated learning under data heterogeneity
In this paper, we establish a precise and quantifiable correspondence between data heterogeneity and parameters in the convergence rate when a fraction of data is shuffled across clients.
Graph Neural Network Interatomic Potential Ensembles with Calibrated Aleatoric and Epistemic Uncertainty on Energy and Forces
The proposed method considers both epistemic and aleatoric uncertainty and the total uncertainties are recalibrated post hoc using a nonlinear scaling function to achieve good calibration on previously unseen data, without loss of predictive accuracy.
On the effectiveness of partial variance reduction in federated learning with heterogeneous data
In this paper, we first revisit the widely used FedAvg algorithm in a deep neural network to understand how data heterogeneity influences the gradient updates across the neural network layers.
Raman Spectrum Matching with Contrastive Representation Learning
We propose a new machine learning technique for Raman spectrum matching, based on contrastive representation learning, that requires no preprocessing and works with as little as a single reference spectrum from each class.
Calibrated Uncertainty for Molecular Property Prediction using Ensembles of Message Passing Neural Networks
In this work we extend a message passing neural network designed specifically for predicting properties of molecules and materials with a calibrated probabilistic predictive distribution.
Materials property prediction using symmetry-labeled graphs as atomic-position independent descriptors
The possibilities for prediction in a realistic computational screening setting is investigated on a dataset of 5976 ABSe$_3$ selenides with very limited overlap with the OQMD training set.
Probabilistic PARAFAC2
The PARAFAC2 is a multimodal factor analysis model suitable for analyzing multi-way data when one of the modes has incomparable observation units, for example because of differences in signal sampling or batch sizes.
Neural Message Passing with Edge Updates for Predicting Properties of Molecules and Materials
Neural message passing on molecular graphs is one of the most promising methods for predicting formation energy and other properties of molecules and materials.
Ranked #3 on
Formation Energy
on Materials Project
Scalable Group Level Probabilistic Sparse Factor Analysis
Many data-driven approaches exist to extract neural representations of functional magnetic resonance imaging (fMRI) data, but most of them lack a proper probabilistic formulation.
Completely random measures for modelling block-structured sparse networks
Statistical methods for network data often parameterize the edge-probability by attributing latent traits such as block structure to the vertices and assume exchangeability in the sense of the Aldous-Hoover representation theorem.
Nonparametric Modeling of Dynamic Functional Connectivity in fMRI Data
We further investigate what drives dynamic states using the model on the entire data collated across subjects and task/rest.
Bayesian Dropout
Dropout has recently emerged as a powerful and simple method for training neural networks preventing co-adaptation by stochastically omitting neurons.
Completely random measures for modelling block-structured networks
Recently Caron and Fox (2014) proposed the use of a different notion of exchangeability due to Kallenberg (2009) and obtained a network model which admits power-law behaviour while retaining desirable statistical properties, however this model does not capture latent vertex traits such as block-structure.
Adaptive Reconfiguration Moves for Dirichlet Mixtures
Bayesian mixture models are widely applied for unsupervised learning and exploratory data analysis.
Non-parametric Bayesian modeling of complex networks
Modeling structure in complex networks using Bayesian non-parametrics makes it possible to specify flexible model structures and infer the adequate model complexity from the observed data.
The Infinite Degree Corrected Stochastic Block Model
On synthetic data we demonstrate that including the degree correction yields better performance both on recovering the true group structure and predicting missing links when degree heterogeneity is present, whereas performance is on par for data with no degree heterogeneity within clusters.
Nonparametric Bayesian models of hierarchical structure in complex networks
Analyzing and understanding the structure of complex relational data is important in many applications including analysis of the connectivity in the human brain.
