Search Results for author:
Found 53 papers, 27 papers with code
End-to-end Supervised Prediction of Arbitrary-size Graphs with Partially-Masked Fused Gromov-Wasserstein Matching
We present a novel end-to-end deep learning-based approach for Supervised Graph Prediction (SGP).
Distributional Reduction: Unifying Dimensionality Reduction and Clustering with Gromov-Wasserstein Projection
Unsupervised learning aims to capture the underlying structure of potentially large and high-dimensional datasets.
Weakly supervised covariance matrices alignment through Stiefel matrices estimation for MEG applications
This paper introduces a novel domain adaptation technique for time series data, called Mixing model Stiefel Adaptation (MSA), specifically addressing the challenge of limited labeled signals in the target dataset.
Interpolating between Clustering and Dimensionality Reduction with Gromov-Wasserstein
We present a versatile adaptation of existing dimensionality reduction (DR) objectives, enabling the simultaneous reduction of both sample and feature sizes.
Properties of Discrete Sliced Wasserstein Losses
We investigate the regularity and optimisation properties of this energy, as well as its Monte-Carlo approximation $\mathcal{E}_p$ (estimating the expectation in SW using only $p$ samples) and show convergence results on the critical points of $\mathcal{E}_p$ to those of $\mathcal{E}$, as well as an almost-sure uniform convergence and a uniform Central Limit result on the process $\mathcal{E}_p(Y)$.
Convolutional Monge Mapping Normalization for learning on sleep data
In many machine learning applications on signals and biomedical data, especially electroencephalogram (EEG), one major challenge is the variability of the data across subjects, sessions, and hardware devices.
Entropic Wasserstein Component Analysis
Dimension reduction (DR) methods provide systematic approaches for analyzing high-dimensional data.
Aligning individual brains with Fused Unbalanced Gromov-Wasserstein
We demonstrate that FUGW is well-suited for whole-brain landmark-free alignment.
Template based Graph Neural Network with Optimal Transport Distances
Current Graph Neural Networks (GNN) architectures generally rely on two important components: node features embedding through message passing, and aggregation with a specialized form of pooling.
Ranked #1 on
Graph Classification
on NCI1
Unbalanced CO-Optimal Transport
With this result in hand, we provide empirical evidence of this robustness for the challenging tasks of heterogeneous domain adaptation with and without varying proportions of classes and simultaneous alignment of samples and features across single-cell measurements.
Wind power predictions from nowcasts to 4-hour forecasts: a learning approach with variable selection
We study short-term prediction of wind speed and wind power (every 10 minutes up to 4 hours ahead).
Learning to Predict Graphs with Fused Gromov-Wasserstein Barycenters
This paper introduces a novel and generic framework to solve the flagship task of supervised labeled graph prediction by leveraging Optimal Transport tools.
Semi-relaxed Gromov-Wasserstein divergence with applications on graphs
To this end, the Gromov-Wasserstein (GW) distance, based on Optimal Transport (OT), has proven to be successful in handling the specific nature of the associated objects.
Factored couplings in multi-marginal optimal transport via difference of convex programming
Optimal transport (OT) theory underlies many emerging machine learning (ML) methods nowadays solving a wide range of tasks such as generative modeling, transfer learning and information retrieval.
Semi-relaxed Gromov-Wasserstein divergence and applications on graphs
To this end, the Gromov-Wasserstein (GW) distance, based on Optimal Transport (OT), has proven to be successful in handling the specific nature of the associated objects.
Unbalanced Optimal Transport through Non-negative Penalized Linear Regression
In particular, we consider majorization-minimization which leads in our setting to efficient multiplicative updates for a variety of penalties.
Unbalanced minibatch Optimal Transport; applications to Domain Adaptation
Optimal transport distances have found many applications in machine learning for their capacity to compare non-parametric probability distributions.
Online Graph Dictionary Learning
Dictionary learning is a key tool for representation learning, that explains the data as linear combination of few basic elements.
Ranked #1 on
Graph Classification
on BZR
Minibatch optimal transport distances; analysis and applications
We notably argue that the minibatch strategy comes with appealing properties such as unbiased estimators, gradients and a concentration bound around the expectation, but also with limits: the minibatch OT is not a distance.
Representation Transfer by Optimal Transport
We use optimal transport to quantify the match between two representations, yielding a distance that embeds some invariances inherent to the representation of deep networks.
Provably Convergent Working Set Algorithm for Non-Convex Regularized Regression
Owing to their statistical properties, non-convex sparse regularizers have attracted much interest for estimating a sparse linear model from high dimensional data.
Multi-source Domain Adaptation via Weighted Joint Distributions Optimal Transport
The problem of domain adaptation on an unlabeled target dataset using knowledge from multiple labelled source datasets is becoming increasingly important.
Optimal Transport for Conditional Domain Matching and Label Shift
We address the problem of unsupervised domain adaptation under the setting of generalized target shift (joint class-conditional and label shifts).
Time Series Alignment with Global Invariances
Multivariate time series are ubiquitous objects in signal processing.
CO-Optimal Transport
Optimal transport (OT) is a powerful geometric and probabilistic tool for finding correspondences and measuring similarity between two distributions.
Learning with minibatch Wasserstein : asymptotic and gradient properties
Optimal transport distances are powerful tools to compare probability distributions and have found many applications in machine learning.
Large scale Lasso with windowed active set for convolutional spike sorting
Spike sorting is a fundamental preprocessing step in neuroscience that is central to access simultaneous but distinct neuronal activities and therefore to better understand the animal or even human brain.
Concentration bounds for linear Monge mapping estimation and optimal transport domain adaptation
This article investigates the quality of the estimator of the linear Monge mapping between distributions.
Sliced Gromov-Wasserstein
Recently used in various machine learning contexts, the Gromov-Wasserstein distance (GW) allows for comparing distributions whose supports do not necessarily lie in the same metric space.
Wasserstein Adversarial Regularization (WAR) on label noise
Noisy labels often occur in vision datasets, especially when they are obtained from crowdsourcing or Web scraping.
Fused Gromov-Wasserstein distance for structured objects: theoretical foundations and mathematical properties
Optimal transport theory has recently found many applications in machine learning thanks to its capacity for comparing various machine learning objects considered as distributions.
An Entropic Optimal Transport Loss for Learning Deep Neural Networks under Label Noise in Remote Sensing Images
The state-of-the-art performances of deep neural networks are conditioned to the availability of large number of accurately labeled samples.
Optimal Transport for structured data with application on graphs
This work considers the problem of computing distances between structured objects such as undirected graphs, seen as probability distributions in a specific metric space.
Ranked #3 on
Graph Classification
on NCI1
DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptation
In computer vision, one is often confronted with problems of domain shifts, which occur when one applies a classifier trained on a source dataset to target data sharing similar characteristics (e. g. same classes), but also different latent data structures (e. g. different acquisition conditions).
Ranked #2 on
Domain Adaptation
on MNIST-to-MNIST-M
Optimal Transport for Multi-source Domain Adaptation under Target Shift
In this paper, we propose to tackle the problem of reducing discrepancies between multiple domains referred to as multi-source domain adaptation and consider it under the target shift assumption: in all domains we aim to solve a classification problem with the same output classes, but with labels' proportions differing across them.
Distance Measure Machines
This paper presents a distance-based discriminative framework for learning with probability distributions.
On reducing the communication cost of the diffusion LMS algorithm
While these data may be processed in a centralized manner, it is often more suitable to consider distributed strategies such as diffusion as they are scalable and can handle large amounts of data by distributing tasks over networked agents.
Large-Scale Optimal Transport and Mapping Estimation
We prove two theoretical stability results of regularized OT which show that our estimations converge to the OT plan and Monge map between the underlying continuous measures.
Learning Wasserstein Embeddings
Our goal is to alleviate this problem by providing an approximation mechanism that allows to break its inherent complexity.
Joint Distribution Optimal Transportation for Domain Adaptation
This paper deals with the unsupervised domain adaptation problem, where one wants to estimate a prediction function $f$ in a given target domain without any labeled sample by exploiting the knowledge available from a source domain where labels are known.
Multi-frequency image reconstruction for radio-interferometry with self-tuned regularization parameters
Image reconstruction algorithms for radio interferometry are challenged to scale well with TeraByte image sizes never seen before.
Astronomical image reconstruction with convolutional neural networks
State of the art methods in astronomical image reconstruction rely on the resolution of a regularized or constrained optimization problem.
Mapping Estimation for Discrete Optimal Transport
Most of the computational approaches of Optimal Transport use the Kantorovich relaxation of the problem to learn a probabilistic coupling $\mgamma$ but do not address the problem of learning the underlying transport map $\funcT$ linked to the original Monge problem.
Optimal spectral transportation with application to music transcription
Many spectral unmixing methods rely on the non-negative decomposition of spectral data onto a dictionary of spectral templates.
Wasserstein Discriminant Analysis
Wasserstein Discriminant Analysis (WDA) is a new supervised method that can improve classification of high-dimensional data by computing a suitable linear map onto a lower dimensional subspace.
Multiclass feature learning for hyperspectral image classification: sparse and hierarchical solutions
In this paper, we tackle the question of discovering an effective set of spatial filters to solve hyperspectral classification problems.
Importance sampling strategy for non-convex randomized block-coordinate descent
As the number of samples and dimensionality of optimization problems related to statistics an machine learning explode, block coordinate descent algorithms have gained popularity since they reduce the original problem to several smaller ones.
Generalized conditional gradient: analysis of convergence and applications
The objectives of this technical report is to provide additional results on the generalized conditional gradient methods introduced by Bredies et al. [BLM05].
Optimal Transport for Domain Adaptation
Domain adaptation from one data space (or domain) to another is one of the most challenging tasks of modern data analytics.
Non-convex Regularizations for Feature Selection in Ranking With Sparse SVM
Feature selection in learning to rank has recently emerged as a crucial issue.
Distributed image reconstruction for very large arrays in radio astronomy
Current and future radio interferometric arrays such as LOFAR and SKA are characterized by a paradox.
Mixed-norm Regularization for Brain Decoding
This framework is extended to the multi-task learning situation where several similar classification tasks related to different subjects are learned simultaneously.
Decoding finger movements from ECoG signals using switching linear models
As a witness of the BCI community increasing interest toward such a problem, the fourth BCI Competition provides a dataset which aim is to predict individual finger movements from ECoG signals.
