Search Results for author: Patrick Gallinari

Found 74 papers, 35 papers with code

UP-dROM : Uncertainty-Aware and Parametrised dynamic Reduced-Order Model, application to unsteady flows

no code implementations29 Mar 2025 Ismaël Zighed, Nicolas Thome, Patrick Gallinari, Taraneh Sayadi

In this work, we present a nonlinear reduction strategy specifically designed for transient flows that incorporates parametrisation and uncertainty quantification.

Uncertainty Quantification Variational Inference

SCOPE: A Self-supervised Framework for Improving Faithfulness in Conditional Text Generation

no code implementations19 Feb 2025 Song Duong, Florian Le Bronnec, Alexandre Allauzen, Vincent Guigue, Alberto Lumbreras, Laure Soulier, Patrick Gallinari

This issue arises in typical conditional text generation tasks, such as text summarization and data-to-text generation, where the goal is to produce fluent text based on contextual input.

Conditional Text Generation Data-to-Text Generation +1

GEPS: Boosting Generalization in Parametric PDE Neural Solvers through Adaptive Conditioning

no code implementations31 Oct 2024 Armand Kassaï Koupaï, Jorge Mifsut Benet, Yuan Yin, Jean-Noël Vittaut, Patrick Gallinari

As existing adaptive conditioning methods do not scale well with respect to the number of parameters to adapt in the neural solver, we propose GEPS, a simple adaptation mechanism to boost GEneralization in Pde Solvers via a first-order optimization and low-rank rapid adaptation of a small set of context parameters.

Spatio-Temporal Forecasting

Learning a Neural Solver for Parametric PDE to Enhance Physics-Informed Methods

no code implementations9 Oct 2024 Lise Le Boudec, Emmanuel de Bezenac, Louis Serrano, Ramon Daniel Regueiro-Espino, Yuan Yin, Patrick Gallinari

Physics-informed deep learning often faces optimization challenges due to the complexity of solving partial differential equations (PDEs), which involve exploring large solution spaces, require numerous iterations, and can lead to unstable training.

Probing Language Models on Their Knowledge Source

1 code implementation8 Oct 2024 Zineddine Tighidet, Andrea Mogini, Jiali Mei, Benjamin Piwowarski, Patrick Gallinari

We evaluate this framework on various LLMs of different sizes and demonstrate that mid-layer activations, particularly those related to relations in the input, are crucial in predicting knowledge source selection, paving the way for more reliable models capable of handling knowledge conflicts effectively.

Probing Language Models

Zebra: In-Context and Generative Pretraining for Solving Parametric PDEs

no code implementations4 Oct 2024 Louis Serrano, Armand Kassaï Koupaï, Thomas X Wang, Pierre Erbacher, Patrick Gallinari

Solving time-dependent parametric partial differential equations (PDEs) is challenging, as models must adapt to variations in parameters such as coefficients, forcing terms, and boundary conditions.

In-Context Learning Meta-Learning +1

MEXMA: Token-level objectives improve sentence representations

1 code implementation19 Sep 2024 João Maria Janeiro, Benjamin Piwowarski, Patrick Gallinari, Loïc Barrault

Current pre-trained cross-lingual sentence encoders approaches use sentence-level objectives only.

Sentence

AROMA: Preserving Spatial Structure for Latent PDE Modeling with Local Neural Fields

1 code implementation4 Jun 2024 Louis Serrano, Thomas X Wang, Etienne Le Naour, Jean-Noël Vittaut, Patrick Gallinari

We present AROMA (Attentive Reduced Order Model with Attention), a framework designed to enhance the modeling of partial differential equations (PDEs) using local neural fields.

Decoder

ML4PhySim : Machine Learning for Physical Simulations Challenge (The airfoil design)

no code implementations3 Mar 2024 Mouadh Yagoubi, Milad Leyli-Abadi, David Danan, Jean-Patrick Brunet, Jocelyn Ahmed Mazari, Florent Bonnet, Asma Farjallah, Marc Schoenauer, Patrick Gallinari

The aim of this competition is to encourage the development of new ML techniques to solve physical problems using a unified evaluation framework proposed recently, called Learning Industrial Physical Simulations (LIPS).

Physical Simulations

INFINITY: Neural Field Modeling for Reynolds-Averaged Navier-Stokes Equations

no code implementations25 Jul 2023 Louis Serrano, Leon Migus, Yuan Yin, Jocelyn Ahmed Mazari, Patrick Gallinari

For numerical design, the development of efficient and accurate surrogate models is paramount.

Time Series Continuous Modeling for Imputation and Forecasting with Implicit Neural Representations

1 code implementation9 Jun 2023 Etienne Le Naour, Louis Serrano, Léon Migus, Yuan Yin, Ghislain Agoua, Nicolas Baskiotis, Patrick Gallinari, Vincent Guigue

We introduce a novel modeling approach for time series imputation and forecasting, tailored to address the challenges often encountered in real-world data, such as irregular samples, missing data, or unaligned measurements from multiple sensors.

Imputation Meta-Learning +1

Adversarial Sample Detection Through Neural Network Transport Dynamics

no code implementations7 Jun 2023 Skander Karkar, Patrick Gallinari, Alain Rakotomamonjy

We propose a detector of adversarial samples that is based on the view of neural networks as discrete dynamic systems.

Stability of implicit neural networks for long-term forecasting in dynamical systems

no code implementations26 May 2023 Leon Migus, Julien Salomon, Patrick Gallinari

We develop a theory based on the stability definition of schemes to ensure the stability in forecasting of this network.

Exemplars and Counterexemplars Explanations for Image Classifiers, Targeting Skin Lesion Labeling

no code implementations18 Jan 2023 Carlo Metta, Riccardo Guidotti, Yuan Yin, Patrick Gallinari, Salvatore Rinzivillo

We propose a use case study, for skin lesion diagnosis, illustrating how it is possible to provide the practitioner with explanations on the decisions of a state of the art deep neural network classifier trained to characterize skin lesions from examples.

AirfRANS: High Fidelity Computational Fluid Dynamics Dataset for Approximating Reynolds-Averaged Navier-Stokes Solutions

3 code implementations15 Dec 2022 Florent Bonnet, Ahmed Jocelyn Mazari, Paola Cinnella, Patrick Gallinari

Surrogate models are necessary to optimize meaningful quantities in physical dynamics as their recursive numerical resolutions are often prohibitively expensive.

HMOE: Hypernetwork-based Mixture of Experts for Domain Generalization

no code implementations15 Nov 2022 Jingang Qu, Thibault Faney, Ze Wang, Patrick Gallinari, Soleiman Yousef, Jean-Charles de Hemptinne

This paper presents a novel DG method, called HMOE: Hypernetwork-based Mixture of Experts (MoE), which does not rely on domain labels and is more interpretable.

Domain Generalization Mixture-of-Experts

Block-wise Training of Residual Networks via the Minimizing Movement Scheme

no code implementations3 Oct 2022 Skander Karkar, Ibrahim Ayed, Emmanuel de Bézenac, Patrick Gallinari

End-to-end backpropagation has a few shortcomings: it requires loading the entire model during training, which can be impossible in constrained settings, and suffers from three locking problems (forward locking, update locking and backward locking), which prohibit training the layers in parallel.

Continuous PDE Dynamics Forecasting with Implicit Neural Representations

1 code implementation29 Sep 2022 Yuan Yin, Matthieu Kirchmeyer, Jean-Yves Franceschi, Alain Rakotomamonjy, Patrick Gallinari

Effective data-driven PDE forecasting methods often rely on fixed spatial and / or temporal discretizations.

Multi-scale Physical Representations for Approximating PDE Solutions with Graph Neural Operators

1 code implementation29 Jun 2022 Léon Migus, Yuan Yin, Jocelyn Ahmed Mazari, Patrick Gallinari

In this work, we study three multi-resolution schema with integral kernel operators that can be approximated with \emph{Message Passing Graph Neural Networks} (MPGNNs).

PTFlash : A deep learning framework for isothermal two-phase equilibrium calculations

no code implementations6 May 2022 Jingang Qu, Thibault Faney, Jean-Charles de Hemptinne, Soleiman Yousef, Patrick Gallinari

Phase equilibrium calculations are an essential part of numerical simulations of multi-component multi-phase flow in porous media, accounting for the largest share of the computational time.

Vocal Bursts Valence Prediction

Generalizing to New Physical Systems via Context-Informed Dynamics Model

1 code implementation1 Feb 2022 Matthieu Kirchmeyer, Yuan Yin, Jérémie Donà, Nicolas Baskiotis, Alain Rakotomamonjy, Patrick Gallinari

Data-driven approaches to modeling physical systems fail to generalize to unseen systems that share the same general dynamics with the learning domain, but correspond to different physical contexts.

Explainable Deep Image Classifiers for Skin Lesion Diagnosis

no code implementations22 Nov 2021 Carlo Metta, Andrea Beretta, Riccardo Guidotti, Yuan Yin, Patrick Gallinari, Salvatore Rinzivillo, Fosca Giannotti

A key issue in critical contexts such as medical diagnosis is the interpretability of the deep learning models adopted in decision-making systems.

Decision Making Explainable artificial intelligence +2

Mapping conditional distributions for domain adaptation under generalized target shift

1 code implementation ICLR 2022 Matthieu Kirchmeyer, Alain Rakotomamonjy, Emmanuel de Bezenac, Patrick Gallinari

We consider the problem of unsupervised domain adaptation (UDA) between a source and a target domain under conditional and label shift a. k. a Generalized Target Shift (GeTarS).

Unsupervised Domain Adaptation

Constrained Physical-Statistics Models for Dynamical System Identification and Prediction

no code implementations ICLR 2022 Jérémie Dona, Marie Déchelle, Patrick Gallinari, Marina Levy

A common practice to identify the respective parameters of the physical and ML components is to formulate the problem as supervised learning on observed trajectories.

Unsupervised domain adaptation with non-stochastic missing data

1 code implementation16 Sep 2021 Matthieu Kirchmeyer, Patrick Gallinari, Alain Rakotomamonjy, Amin Mantrach

Moreover, we compare the target error of our Adaptation-imputation framework and the "ideal" target error of a UDA classifier without missing target components.

Classification Imputation +1

Differentiable Feature Selection, a Reparameterization Approach

no code implementations21 Jul 2021 Jérémie Dona, Patrick Gallinari

The second one corresponds to the elimination of redundant information by selecting variables in a correlated fashion which requires modeling the covariance of the binary distribution.

feature selection

A Neural Tangent Kernel Perspective of GANs

1 code implementation10 Jun 2021 Jean-Yves Franceschi, Emmanuel de Bézenac, Ibrahim Ayed, Mickaël Chen, Sylvain Lamprier, Patrick Gallinari

We propose a novel theoretical framework of analysis for Generative Adversarial Networks (GANs).

LEADS: Learning Dynamical Systems that Generalize Across Environments

1 code implementation NeurIPS 2021 Yuan Yin, Ibrahim Ayed, Emmanuel de Bézenac, Nicolas Baskiotis, Patrick Gallinari

Both are sub-optimal: the former disregards the discrepancies between environments leading to biased solutions, while the latter does not exploit their potential commonalities and is prone to scarcity problems.

Data-QuestEval: A Referenceless Metric for Data-to-Text Semantic Evaluation

2 code implementations EMNLP 2021 Clément Rebuffel, Thomas Scialom, Laure Soulier, Benjamin Piwowarski, Sylvain Lamprier, Jacopo Staiano, Geoffrey Scoutheeten, Patrick Gallinari

QuestEval is a reference-less metric used in text-to-text tasks, that compares the generated summaries directly to the source text, by automatically asking and answering questions.

Data-to-Text Generation Question Generation +1

QuestEval: Summarization Asks for Fact-based Evaluation

1 code implementation EMNLP 2021 Thomas Scialom, Paul-Alexis Dray, Patrick Gallinari, Sylvain Lamprier, Benjamin Piwowarski, Jacopo Staiano, Alex Wang

Summarization evaluation remains an open research problem: current metrics such as ROUGE are known to be limited and to correlate poorly with human judgments.

Question Answering

Controlling Hallucinations at Word Level in Data-to-Text Generation

1 code implementation4 Feb 2021 Clément Rebuffel, Marco Roberti, Laure Soulier, Geoffrey Scoutheeten, Rossella Cancelliere, Patrick Gallinari

Specifically, we propose a Multi-Branch Decoder which is able to leverage word-level labels to learn the relevant parts of each training instance.

Data-to-Text Generation Decoder +2

Stochastic sparse adversarial attacks

3 code implementations24 Nov 2020 Manon Césaire, Lucas Schott, Hatem Hajri, Sylvain Lamprier, Patrick Gallinari

This paper introduces stochastic sparse adversarial attacks (SSAA), standing as simple, fast and purely noise-based targeted and untargeted attacks of neural network classifiers (NNC).

Transductive Zero-Shot Learning using Cross-Modal CycleGAN

no code implementations13 Nov 2020 Patrick Bordes, Eloi Zablocki, Benjamin Piwowarski, Patrick Gallinari

We show the efficiency of our Cross-Modal CycleGAN model (CM-GAN) on the ImageNet T-ZSL task where we obtain state-of-the-art results.

Sentence Zero-Shot Learning

Augmenting Physical Models with Deep Networks for Complex Dynamics Forecasting

2 code implementations ICLR 2021 Yuan Yin, Vincent Le Guen, Jérémie Dona, Emmanuel de Bézenac, Ibrahim Ayed, Nicolas Thome, Patrick Gallinari

In this work, we introduce the APHYNITY framework, a principled approach for augmenting incomplete physical dynamics described by differential equations with deep data-driven models.

Let's Stop Incorrect Comparisons in End-to-end Relation Extraction!

3 code implementations EMNLP 2020 Bruno Taillé, Vincent Guigue, Geoffrey Scoutheeten, Patrick Gallinari

Despite efforts to distinguish three different evaluation setups (Bekoulis et al., 2018), numerous end-to-end Relation Extraction (RE) articles present unreliable performance comparison to previous work.

Articles Language Modeling +4

A Principle of Least Action for the Training of Neural Networks

1 code implementation17 Sep 2020 Skander Karkar, Ibrahim Ayed, Emmanuel de Bézenac, Patrick Gallinari

From this observation, we reformulate the learning problem as follows: finding neural networks which solve the task while transporting the data as efficiently as possible.

Learning Theory

PDE-Driven Spatiotemporal Disentanglement

1 code implementation ICLR 2021 Jérémie Donà, Jean-Yves Franceschi, Sylvain Lamprier, Patrick Gallinari

A recent line of work in the machine learning community addresses the problem of predicting high-dimensional spatiotemporal phenomena by leveraging specific tools from the differential equations theory.

Disentanglement

Incorporating Visual Semantics into Sentence Representations within a Grounded Space

no code implementations IJCNLP 2019 Patrick Bordes, Eloi Zablocki, Laure Soulier, Benjamin Piwowarski, Patrick Gallinari

To overcome this limitation, we propose to transfer visual information to textual representations by learning an intermediate representation space: the grounded space.

Sentence

Contextualized Embeddings in Named-Entity Recognition: An Empirical Study on Generalization

1 code implementation22 Jan 2020 Bruno Taillé, Vincent Guigue, Patrick Gallinari

Contextualized embeddings use unsupervised language model pretraining to compute word representations depending on their context.

Language Modeling Language Modelling +3

Unsupervised Adversarial Image Inpainting

1 code implementation18 Dec 2019 Arthur Pajot, Emmanuel de Bezenac, Patrick Gallinari

This allows us sampling from the latent component in order to generate a distribution of images associated to an observation.

Image Inpainting Imputation

Unsupervised domain adaptation with imputation

no code implementations25 Sep 2019 Matthieu Kirchmeyer, Patrick Gallinari, Alain Rakotomamonjy, Amin Mantrach

Motivated by practical applications, we consider unsupervised domain adaptation for classification problems, in the presence of missing data in the target domain.

Classification Imputation +1

Unsupervised Spatiotemporal Data Inpainting

no code implementations25 Sep 2019 Yuan Yin, Arthur Pajot, Emmanuel de Bézenac, Patrick Gallinari

We tackle the problem of inpainting occluded area in spatiotemporal sequences, such as cloud occluded satellite observations, in an unsupervised manner.

Generative Adversarial Network

Optimal Unsupervised Domain Translation

no code implementations4 Jun 2019 Emmanuel de Bézenac, Ibrahim Ayed, Patrick Gallinari

Domain Translation is the problem of finding a meaningful correspondence between two domains.

Translation

Benchmarking Regression Methods: A comparison with CGAN

1 code implementation30 May 2019 Karan Aggarwal, Matthieu Kirchmeyer, Pranjul Yadav, S. Sathiya Keerthi, Patrick Gallinari

Such a real world situation is best represented using an implicit model in which an extra noise vector, $z$ is included with $x$ as input.

Benchmarking Inductive Learning +1

Unsupervised Adversarial Image Reconstruction

1 code implementation ICLR 2019 Arthur Pajot, Emmanuel de Bezenac, Patrick Gallinari

We address the problem of recovering an underlying signal from lossy, inaccurate observations in an unsupervised setting.

Image Reconstruction

Context-Aware Zero-Shot Learning for Object Recognition

no code implementations24 Apr 2019 Eloi Zablocki, Patrick Bordes, Benjamin Piwowarski, Laure Soulier, Patrick Gallinari

Zero-Shot Learning (ZSL) aims at classifying unlabeled objects by leveraging auxiliary knowledge, such as semantic representations.

Object Object Recognition +1

Learning Dynamical Systems from Partial Observations

no code implementations26 Feb 2019 Ibrahim Ayed, Emmanuel de Bézenac, Arthur Pajot, Julien Brajard, Patrick Gallinari

We consider the problem of forecasting complex, nonlinear space-time processes when observations provide only partial information of on the system's state.

Spatio-Temporal Neural Networks for Space-Time Series Forecasting and Relations Discovery

no code implementations23 Apr 2018 Ali Ziat, Edouard Delasalles, Ludovic Denoyer, Patrick Gallinari

We introduce a dynamical spatio-temporal model formalized as a recurrent neural network for forecasting time series of spatial processes, i. e. series of observations sharing temporal and spatial dependencies.

Decoder Epidemiology +3

A Distributed Frank-Wolfe Framework for Learning Low-Rank Matrices with the Trace Norm

1 code implementation20 Dec 2017 Wenjie Zheng, Aurélien Bellet, Patrick Gallinari

We consider the problem of learning a high-dimensional but low-rank matrix from a large-scale dataset distributed over several machines, where low-rankness is enforced by a convex trace norm constraint.

Deep Learning for Physical Processes: Incorporating Prior Scientific Knowledge

2 code implementations ICLR 2018 Emmanuel de Bezenac, Arthur Pajot, Patrick Gallinari

We consider the use of Deep Learning methods for modeling complex phenomena like those occurring in natural physical processes.

Deep Learning

Learning Multi-Modal Word Representation Grounded in Visual Context

no code implementations9 Nov 2017 Éloi Zablocki, Benjamin Piwowarski, Laure Soulier, Patrick Gallinari

Representing the semantics of words is a long-standing problem for the natural language processing community.

Word Embeddings

OCReP: An Optimally Conditioned Regularization for Pseudoinversion Based Neural Training

no code implementations25 Aug 2015 Rossella Cancelliere, Mario Gai, Patrick Gallinari, Luca Rubini

In this paper we consider the training of single hidden layer neural networks by pseudoinversion, which, in spite of its popularity, is sometimes affected by numerical instability issues.

Diagnostic

Extended Recommendation Framework: Generating the Text of a User Review as a Personalized Summary

no code implementations17 Dec 2014 Mickaël Poussevin, Vincent Guigue, Patrick Gallinari

We propose to augment rating based recommender systems by providing the user with additional information which might help him in his choice or in the understanding of the recommendation.

Recommendation Systems

Deep Sequential Neural Network

no code implementations2 Oct 2014 Ludovic Denoyer, Patrick Gallinari

Instead of considering global transformations, like in classical multilayer networks, this model allows us for learning a set of local transformations.

Reinforcement Learning

Learning States Representations in POMDP

no code implementations20 Dec 2013 Gabriella Contardo, Ludovic Denoyer, Thierry Artieres, Patrick Gallinari

We propose to deal with sequential processes where only partial observations are available by learning a latent representation space on which policies may be accurately learned.

Learning Information Spread in Content Networks

no code implementations20 Dec 2013 Cédric Lagnier, Simon Bourigault, Sylvain Lamprier, Ludovic Denoyer, Patrick Gallinari

We introduce a model for predicting the diffusion of content information on social media.

Cannot find the paper you are looking for? You can Submit a new open access paper.