Search Results for author:
Found 37 papers, 15 papers with code
GeoFormer: A Multi-Polygon Segmentation Transformer
In remote sensing there exists a common need for learning scale invariant shapes of objects like buildings.
MolMiner: Transformer architecture for fragment-based autoregressive generation of molecular stories
Enforcing chemical rules in the stories guarantees the chemical validity of the generated molecules, the discrete sequential steps of a molecular story makes the process transparent improving interpretability, and the autoregressive nature of the approach allows the size of the molecule to be a decision of the model.
EB-NeRD: A Large-Scale Dataset for News Recommendation
Personalized content recommendations have been pivotal to the content experience in digital media from video streaming to social networks.
RecSys Challenge 2024: Balancing Accuracy and Editorial Values in News Recommendations
Additionally, the challenge embraces normative complexities, investigating the effects of recommender systems on news flow and their alignment with editorial values.
Variance reduction of diffusion model's gradients with Taylor approximation-based control variate
Score-based models, trained with denoising score matching, are remarkably effective in generating high dimensional data.
Navigating Uncertainty in Medical Image Segmentation
We address the selection and evaluation of uncertain segmentation methods in medical imaging and present two case studies: prostate segmentation, illustrating that for minimal annotator variation simple deterministic models can suffice, and lung lesion segmentation, highlighting the limitations of the Generalized Energy Distance (GED) in model selection.
von Mises Quasi-Processes for Bayesian Circular Regression
The need for regression models to predict circular values arises in many scientific fields.
Scalable physical source-to-field inference with hypernetworks
We present a generative model that amortises computation for the field around e. g. gravitational or magnetic sources.
A Continuous Relaxation for Discrete Bayesian Optimization
To optimize efficiently over discrete data and with only few available target observations is a challenge in Bayesian optimization.
Polygonizer: An auto-regressive building delineator
In geospatial planning, it is often essential to represent objects in a vectorized format, as this format easily translates to downstream tasks such as web development, graphics, or design.
That Label's Got Style: Handling Label Style Bias for Uncertain Image Segmentation
Segmentation uncertainty models predict a distribution over plausible segmentations for a given input, which they learn from the annotator variation in the training set.
Laplacian Segmentation Networks Improve Epistemic Uncertainty Quantification
Image segmentation relies heavily on neural networks which are known to be overconfident, especially when making predictions on out-of-distribution (OOD) images.
Learning to Generate 3D Representations of Building Roofs Using Single-View Aerial Imagery
We present a novel pipeline for learning the conditional distribution of a building roof mesh given pixels from an aerial image, under the assumption that roof geometry follows a set of regular patterns.
Internal-Coordinate Density Modelling of Protein Structure: Covariance Matters
After the recent ground-breaking advances in protein structure prediction, one of the remaining challenges in protein machine learning is to reliably predict distributions of structural states.
Explainability as statistical inference
The model parameters can be learned via maximum likelihood, and the method can be adapted to any predictor network architecture and any type of prediction problem.
SolarDK: A high-resolution urban solar panel image classification and localization dataset
The body of research on classification of solar panel arrays from aerial imagery is increasing, yet there are still not many public benchmark datasets.
Exploring Predictive Uncertainty and Calibration in NLP: A Study on the Impact of Method & Data Scarcity
We investigate the problem of determining the predictive confidence (or, conversely, uncertainty) of a neural classifier through the lens of low-resource languages.
deep-significance - Easy and Meaningful Statistical Significance Testing in the Age of Neural Networks
A lot of Machine Learning (ML) and Deep Learning (DL) research is of an empirical nature.
Model-agnostic out-of-distribution detection using combined statistical tests
These techniques, based on classical statistical tests, are model-agnostic in the sense that they can be applied to any differentiable generative model.
Adaptive Cholesky Gaussian Processes
We present a method to approximate Gaussian process regression models for large datasets by considering only a subset of the data.
Benchmarking Generative Latent Variable Models for Speech
Stochastic latent variable models (LVMs) achieve state-of-the-art performance on natural image generation but are still inferior to deterministic models on speech.
Uphill Roads to Variational Tightness: Monotonicity and Monte Carlo Objectives
Inspired by this simple monotonicity theorem, we present a series of nonasymptotic results that link properties of Monte Carlo estimates to tightness of MCOs.
Bounds all around: training energy-based models with bidirectional bounds
Energy-based models (EBMs) provide an elegant framework for density estimation, but they are notoriously difficult to train.
Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimation
Popular approaches for quantifying predictive uncertainty in deep neural networks often involve distributions over weights or multiple models, for instance via Markov Chain sampling, ensembling, or Monte Carlo dropout.
How to deal with missing data in supervised deep learning?
To address supervised deep learning with missing values, we propose to marginalize over missing values in a joint model of covariates and outcomes.
Towards Generative Latent Variable Models for Speech
While stochastic latent variable models (LVMs) now achieve state-of-the-art performance on natural image generation, they are still inferior to deterministic models on speech.
Hierarchical VAEs Know What They Don't Know
Deep generative models have been demonstrated as state-of-the-art density estimators.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Sequential Neural Posterior and Likelihood Approximation
We introduce the sequential neural posterior and likelihood approximation (SNPLA) algorithm.
not-MIWAE: Deep Generative Modelling with Missing not at Random Data
When a missing process depends on the missing values themselves, it needs to be explicitly modelled and taken into account while doing likelihood-based inference.
(q,p)-Wasserstein GANs: Comparing Ground Metrics for Wasserstein GANs
We contribute to the WGAN literature by introducing the family of $(q, p)$-Wasserstein GANs, which allow the use of more general $p$-Wasserstein metrics for $p\geq 1$ in the GAN learning procedure.
Partially Exchangeable Networks and Architectures for Learning Summary Statistics in Approximate Bayesian Computation
We present a novel family of deep neural architectures, named partially exchangeable networks (PENs) that leverage probabilistic symmetries.
MIWAE: Deep Generative Modelling and Imputation of Incomplete Data
Our approach, called MIWAE, is based on the importance-weighted autoencoder (IWAE), and maximises a potentially tight lower bound of the log-likelihood of the observed data.
Leveraging the Exact Likelihood of Deep Latent Variable Models
Finally, we describe an algorithm for missing data imputation using the exact conditional likelihood of a deep latent variable model.
Spherical convolutions and their application in molecular modelling
We show that the models are capable of learning non-trivial functions in these molecular environments, and that our spherical convolutions generally outperform standard 3D convolutions in this setting.
Comparative Study of Inference Methods for Bayesian Nonnegative Matrix Factorisation
In this paper, we study the trade-offs of different inference approaches for Bayesian matrix factorisation methods, which are commonly used for predicting missing values, and for finding patterns in the data.
Fast Bayesian Non-Negative Matrix Factorisation and Tri-Factorisation
We present a fast variational Bayesian algorithm for performing non-negative matrix factorisation and tri-factorisation.
The Multivariate Generalised von Mises distribution: Inference and applications
First we introduce a new multivariate distribution over circular variables, called the multivariate Generalised von Mises (mGvM) distribution.
