no code implementations • COLING (TextGraphs) 2020 • Mariana Vargas-Vieyra, Aurélien Bellet, Pascal Denis
Graph-based semi-supervised learning is appealing when labels are scarce but large amounts of unlabeled data are available.
no code implementations • 22 Oct 2024 • Rémi Khellaf, Aurélien Bellet, Julie Josse
We study Federated Causal Inference, an approach to estimate treatment effects from decentralized data across centers.
no code implementations • 23 May 2024 • Tudor Cebere, Aurélien Bellet, Nicolas Papernot
Machine learning models can be trained with formal privacy guarantees via differentially private optimizers such as DP-SGD.
no code implementations • 23 May 2024 • Gaurav Maheshwari, Aurélien Bellet, Pascal Denis, Mikaela Keller
In this paper, we introduce a data augmentation approach specifically tailored to enhance intersectional fairness in classification tasks.
1 code implementation • 21 May 2024 • Pierre Humbert, Batiste Le Bars, Aurélien Bellet, Sylvain Arlot
Our experiments confirm that our algorithms return prediction sets with coverage and length similar to those obtained in a centralized setting.
1 code implementation • 15 Feb 2024 • Abdellah El Mrini, Edwige Cyffers, Aurélien Bellet
Decentralized Gradient Descent (D-GD) allows a set of users to perform collaborative learning without sharing their data by iteratively averaging local model updates with their neighbors in a network graph.
1 code implementation • 12 Feb 2024 • Edwige Cyffers, Aurélien Bellet, Jalaj Upadhyay
The popularity of federated learning comes from the possibility of better scalability and the ability for participants to keep control of their data, improving data security and sovereignty.
no code implementations • 21 Dec 2023 • Clément Pierquin, Aurélien Bellet, Marc Tommasi, Matthieu Boussard
Pufferfish privacy is a flexible generalization of differential privacy that allows to model arbitrary secrets and adversary's prior knowledge about the data.
no code implementations • 29 Aug 2023 • Hadrien Hendrikx, Paul Mangold, Aurélien Bellet
Leveraging this assumption, we introduce the Relative Gaussian Mechanism (RGM), in which the variance of the noise depends on the norm of the output.
no code implementations • 5 Jun 2023 • Batiste Le Bars, Aurélien Bellet, Marc Tommasi, Kevin Scaman, Giovanni Neglia
On the contrary, we show, for convex, strongly convex and non-convex functions, that D-SGD can always recover generalization bounds analogous to those of classical SGD, suggesting that the choice of graph does not matter.
no code implementations • 21 May 2023 • Gaurav Maheshwari, Aurélien Bellet, Pascal Denis, Mikaela Keller
In this work, we consider the problem of intersectional group fairness in the classification setting, where the objective is to learn discrimination-free models in the presence of several intersecting sensitive groups.
1 code implementation • 24 Feb 2023 • Edwige Cyffers, Aurélien Bellet, Debabrota Basu
We study differentially private (DP) machine learning algorithms as instances of noisy fixed-point iterations, in order to derive privacy and utility results from this well-studied framework.
1 code implementation • 13 Feb 2023 • Pierre Humbert, Batiste Le Bars, Aurélien Bellet, Sylvain Arlot
In this paper, we introduce a conformal prediction method to construct prediction sets in a oneshot federated learning setting.
1 code implementation • 28 Oct 2022 • Paul Mangold, Michaël Perrot, Aurélien Bellet, Marc Tommasi
We theoretically study the impact of differential privacy on fairness in classification.
1 code implementation • 10 Oct 2022 • Jean Ogier du Terrail, Samy-Safwan Ayed, Edwige Cyffers, Felix Grimberg, Chaoyang He, Regis Loeb, Paul Mangold, Tanguy Marchand, Othmane Marfoq, Erum Mushtaq, Boris Muzellec, Constantin Philippenko, Santiago Silva, Maria Teleńczuk, Shadi Albarqouni, Salman Avestimehr, Aurélien Bellet, Aymeric Dieuleveut, Martin Jaggi, Sai Praneeth Karimireddy, Marco Lorenzi, Giovanni Neglia, Marc Tommasi, Mathieu Andreux
In this work, we propose a novel cross-silo dataset suite focused on healthcare, FLamby (Federated Learning AMple Benchmark of Your cross-silo strategies), to bridge the gap between theory and practice of cross-silo FL.
1 code implementation • 24 Aug 2022 • Mahsa Asadi, Aurélien Bellet, Odalric-Ambrym Maillard, Marc Tommasi
We study the case where some of the distributions have the same mean, and the agents are allowed to actively query information from other agents.
no code implementations • 9 Aug 2022 • Yacine Belal, Aurélien Bellet, Sonia Ben Mokhtar, Vlad Nitu
To remedy this, we propose PEPPER, a decentralized recommender system based on gossip learning principles.
no code implementations • 4 Jul 2022 • Paul Mangold, Aurélien Bellet, Joseph Salmon, Marc Tommasi
In this paper, we study differentially private empirical risk minimization (DP-ERM).
1 code implementation • 10 Jun 2022 • Edwige Cyffers, Mathieu Even, Aurélien Bellet, Laurent Massoulié
In this work, we introduce pairwise network differential privacy, a relaxation of LDP that captures the fact that the privacy leakage from a node $u$ to a node $v$ may depend on their relative position in the graph.
1 code implementation • 12 May 2022 • Gaurav Maheshwari, Pascal Denis, Mikaela Keller, Aurélien Bellet
Encoded text representations often capture sensitive attributes about individuals (e. g., race or gender), which raise privacy concerns and can make downstream models unfair to certain groups.
no code implementations • 9 Apr 2022 • Batiste Le Bars, Aurélien Bellet, Marc Tommasi, Erick Lavoie, Anne-Marie Kermarrec
One of the key challenges in decentralized and federated learning is to design algorithms that efficiently deal with highly heterogeneous data distributions across agents.
1 code implementation • 2 Mar 2022 • Sina Sajadmanesh, Ali Shahin Shamsabadi, Aurélien Bellet, Daniel Gatica-Perez
In this paper, we study the problem of learning Graph Neural Networks (GNNs) with Differential Privacy (DP).
no code implementations • 23 Feb 2022 • Ali Shahin Shamsabadi, Brij Mohan Lal Srivastava, Aurélien Bellet, Nathalie Vauquier, Emmanuel Vincent, Mohamed Maouche, Marc Tommasi, Nicolas Papernot
We remove speaker information from these attributes by introducing differentially private feature extractors based on an autoencoder and an automatic speech recognizer, respectively, trained using noise layers.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
no code implementations • 23 Dec 2021 • Riad Ladjel, Nicolas Anciaux, Aurélien Bellet, Guillaume Scerri
In this paper, we define a general execution model to control the data-dependence of communications in user-side decentralized computations, in which differential privacy guarantees for communication patterns in global execution plans can be analyzed by combining guarantees obtained on local clusters of nodes.
1 code implementation • 17 Nov 2021 • Maxence Noble, Aurélien Bellet, Aymeric Dieuleveut
Federated Learning (FL) is a paradigm for large-scale distributed learning which faces two key challenges: (i) efficient training from highly heterogeneous user data, and (ii) protecting the privacy of participating users.
no code implementations • 22 Oct 2021 • Paul Mangold, Aurélien Bellet, Joseph Salmon, Marc Tommasi
In this paper, we propose Differentially Private proximal Coordinate Descent (DP-CD), a new method to solve composite DP-ERM problems.
5 code implementations • NeurIPS 2021 • Othmane Marfoq, Giovanni Neglia, Aurélien Bellet, Laetitia Kameni, Richard Vidal
The increasing size of data generated by smartphones and IoT devices motivated the development of Federated Learning (FL), a framework for on-device collaborative training of machine learning models.
no code implementations • 15 Apr 2021 • Aurélien Bellet, Anne-Marie Kermarrec, Erick Lavoie
The convergence speed of machine learning models trained with Federated Learning is significantly affected by heterogeneous data partitions, even more so in a fully decentralized setting without a central server.
1 code implementation • 9 Dec 2020 • Edwige Cyffers, Aurélien Bellet
In this work, we introduce a novel relaxation of local differential privacy (LDP) that naturally arises in fully decentralized algorithms, i. e., when participants exchange information by communicating along the edges of a network graph without central coordinator.
no code implementations • 12 Jun 2020 • César Sabater, Aurélien Bellet, Jan Ramon
Learning from data owned by several parties, as in federated learning, raises challenges regarding the privacy guarantees provided to participants and the correctness of the computation in the presence of malicious parties.
no code implementations • 18 May 2020 • Brij Mohan Lal Srivastava, Natalia Tomashenko, Xin Wang, Emmanuel Vincent, Junichi Yamagishi, Mohamed Maouche, Aurélien Bellet, Marc Tommasi
The recently proposed x-vector based anonymization scheme converts any input voice into that of a random pseudo-speaker.
no code implementations • 19 Feb 2020 • Robin Vogel, Aurélien Bellet, Stephan Clémençon
We establish generalization bounds for scoring functions learned under such constraints, design practical learning algorithms and show the relevance our approach with numerical experiments on real and synthetic data.
9 code implementations • 10 Dec 2019 • Peter Kairouz, H. Brendan McMahan, Brendan Avent, Aurélien Bellet, Mehdi Bennis, Arjun Nitin Bhagoji, Kallista Bonawitz, Zachary Charles, Graham Cormode, Rachel Cummings, Rafael G. L. D'Oliveira, Hubert Eichner, Salim El Rouayheb, David Evans, Josh Gardner, Zachary Garrett, Adrià Gascón, Badih Ghazi, Phillip B. Gibbons, Marco Gruteser, Zaid Harchaoui, Chaoyang He, Lie He, Zhouyuan Huo, Ben Hutchinson, Justin Hsu, Martin Jaggi, Tara Javidi, Gauri Joshi, Mikhail Khodak, Jakub Konečný, Aleksandra Korolova, Farinaz Koushanfar, Sanmi Koyejo, Tancrède Lepoint, Yang Liu, Prateek Mittal, Mehryar Mohri, Richard Nock, Ayfer Özgür, Rasmus Pagh, Mariana Raykova, Hang Qi, Daniel Ramage, Ramesh Raskar, Dawn Song, Weikang Song, Sebastian U. Stich, Ziteng Sun, Ananda Theertha Suresh, Florian Tramèr, Praneeth Vepakomma, Jianyu Wang, Li Xiong, Zheng Xu, Qiang Yang, Felix X. Yu, Han Yu, Sen Zhao
FL embodies the principles of focused data collection and minimization, and can mitigate many of the systemic privacy risks and costs resulting from traditional, centralized machine learning and data science approaches.
no code implementations • 12 Nov 2019 • Brij Mohan Lal Srivastava, Aurélien Bellet, Marc Tommasi, Emmanuel Vincent
In this paper, we focus on the protection of speaker identity and study the extent to which users can be recognized based on the encoded representation of their speech as obtained by a deep encoder-decoder architecture trained for ASR.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
no code implementations • 10 Nov 2019 • Brij Mohan Lal Srivastava, Nathalie Vauquier, Md Sahidullah, Aurélien Bellet, Marc Tommasi, Emmanuel Vincent
In this paper, we investigate anonymization methods based on voice conversion.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
no code implementations • 9 Oct 2019 • James Bell, Aurélien Bellet, Adrià Gascón, tejas kulkarni
In this paper, we study the problem of computing $U$-statistics of degree $2$, i. e., quantities that come in the form of averages over pairs of data points, in the local model of differential privacy (LDP).
6 code implementations • 13 Aug 2019 • William de Vazelhes, CJ Carey, Yuan Tang, Nathalie Vauquier, Aurélien Bellet
metric-learn is an open source Python package implementing supervised and weakly-supervised distance metric learning algorithms.
1 code implementation • 21 Jun 2019 • Robin Vogel, Aurélien Bellet, Stephan Clémençon, Ons Jelassi, Guillaume Papa
The development of cluster computing frameworks has allowed practitioners to scale out various statistical estimation and machine learning algorithms with minimal programming effort.
1 code implementation • 24 Jan 2019 • Valentina Zantedeschi, Aurélien Bellet, Marc Tommasi
We consider the fully decentralized machine learning scenario where many users with personal datasets collaborate to learn models through local peer-to-peer exchanges, without a central coordinator.
1 code implementation • 20 Jul 2018 • Kuan Liu, Aurélien Bellet
Our experiments on datasets with up to one million features demonstrate the ability of our approach to generalize well despite the high dimensionality as well as its superiority compared to several competing methods.
no code implementations • ICML 2018 • Robin Vogel, Aurélien Bellet, Stéphan Clémençon
In this paper, similarity learning is investigated from the perspective of pairwise bipartite ranking, where the goal is to rank the elements of a database by decreasing order of the probability that they share the same label with some query data point, based on the similarity scores.
no code implementations • 27 Mar 2018 • Pierre Dellenbach, Aurélien Bellet, Jan Ramon
The amount of personal data collected in our everyday interactions with connected devices offers great opportunities for innovative services fueled by machine learning, as well as raises serious concerns for the privacy of individuals.
1 code implementation • 20 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.
no code implementations • 23 May 2017 • Aurélien Bellet, Rachid Guerraoui, Mahsa Taziki, Marc Tommasi
The rise of connected personal devices together with privacy concerns call for machine learning algorithms capable of leveraging the data of a large number of agents to learn personalized models under strong privacy requirements.
no code implementations • 13 Jan 2017 • Avner May, Alireza Bagheri Garakani, Zhiyun Lu, Dong Guo, Kuan Liu, Aurélien Bellet, Linxi Fan, Michael Collins, Daniel Hsu, Brian Kingsbury, Michael Picheny, Fei Sha
First, in order to reduce the number of random features required by kernel models, we propose a simple but effective method for feature selection.
no code implementations • NeurIPS 2016 • Guillaume Papa, Aurélien Bellet, Stephan Clémençon
The problem of predicting connections between a set of data points finds many applications, in systems biology and social network analysis among others.
no code implementations • 17 Oct 2016 • Paul Vanhaesebrouck, Aurélien Bellet, Marc Tommasi
We consider a set of learning agents in a collaborative peer-to-peer network, where each agent learns a personalized model according to its own learning objective.
no code implementations • 8 Jun 2016 • Igor Colin, Aurélien Bellet, Joseph Salmon, Stéphan Clémençon
In decentralized networks (of sensors, connected objects, etc.
no code implementations • NeurIPS 2015 • Guillaume Papa, Stéphan Clémençon, Aurélien Bellet
In many learning problems, ranging from clustering to ranking through metric learning, empirical estimates of the risk functional consist of an average over tuples (e. g., pairs or triplets) of observations, rather than over individual observations.
no code implementations • NeurIPS 2015 • Igor Colin, Aurélien Bellet, Joseph Salmon, Stéphan Clémençon
Efficient and robust algorithms for decentralized estimation in networks are essential to many distributed systems.
no code implementations • 12 Jan 2015 • Stéphan Clémençon, Aurélien Bellet, Igor Colin
In a wide range of statistical learning problems such as ranking, clustering or metric learning among others, the risk is accurately estimated by $U$-statistics of degree $d\geq 1$, i. e. functionals of the training data with low variance that take the form of averages over $k$-tuples.
no code implementations • 14 Nov 2014 • Zhiyun Lu, Avner May, Kuan Liu, Alireza Bagheri Garakani, Dong Guo, Aurélien Bellet, Linxi Fan, Michael Collins, Brian Kingsbury, Michael Picheny, Fei Sha
The computational complexity of kernel methods has often been a major barrier for applying them to large-scale learning problems.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
1 code implementation • 10 Nov 2014 • Kuan Liu, Aurélien Bellet, Fei Sha
A good measure of similarity between data points is crucial to many tasks in machine learning.
no code implementations • 15 Apr 2014 • Yuan Shi, Aurélien Bellet, Fei Sha
We propose a new approach for metric learning by framing it as learning a sparse combination of locally discriminative metrics that are inexpensive to generate from the training data.
no code implementations • 9 Apr 2014 • Aurélien Bellet, YIngyu Liang, Alireza Bagheri Garakani, Maria-Florina Balcan, Fei Sha
We further show that the communication cost of dFW is optimal by deriving a lower-bound on the communication cost required to construct an $\epsilon$-approximate solution.
no code implementations • 17 Jul 2013 • Aurélien Bellet
In our third contribution, we extend these ideas to metric learning from feature vectors by proposing a bilinear similarity learning method that efficiently optimizes the (e, g, t)-goodness.
no code implementations • 28 Jun 2013 • Aurélien Bellet, Amaury Habrard, Marc Sebban
The need for appropriate ways to measure the distance or similarity between data is ubiquitous in machine learning, pattern recognition and data mining, but handcrafting such good metrics for specific problems is generally difficult.
no code implementations • 5 Sep 2012 • Aurélien Bellet, Amaury Habrard
Metric learning has attracted a lot of interest over the last decade, but the generalization ability of such methods has not been thoroughly studied.