91 citations · 354 across the 18 of their papers we have counts for
19 papers
Improved Stability and Generalization Guarantees of the Decentralized SGD Algorithm
Batiste Le Bars, Aurélien Bellet, Marc Tommasi +2
This paper presents a new generalization error analysis for Decentralized Stochastic Gradient Descent (D-SGD) based on algorithmic stability. The obtained results overhaul a series…
Differential Privacy has Bounded Impact on Fairness in Classification
Paul Mangold, Michaël Perrot, Aurélien Bellet +1
We theoretically study the impact of differential privacy on fairness in classification. We prove that, given a class of models, popular group fairness measures are pointwise Lipsc…
FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settings
Jean Ogier du Terrail, Samy-Safwan Ayed, Edwige Cyffers +21
Federated Learning (FL) is a novel approach enabling several clients holding sensitive data to collaboratively train machine learning models, without centralizing data. The cross-s…
Collaborative Algorithms for Online Personalized Mean Estimation
Mahsa Asadi, Aurélien Bellet, Odalric-Ambrym Maillard +1
We consider an online estimation problem involving a set of agents. Each agent has access to a (personal) process that generates samples from a real-valued distribution and seeks t…
High-Dimensional Private Empirical Risk Minimization by Greedy Coordinate Descent
Paul Mangold, Aurélien Bellet, Joseph Salmon +1
In this paper, we study differentially private empirical risk minimization (DP-ERM). It has been shown that the worst-case utility of DP-ERM reduces polynomially as the dimension i…
Refined Convergence and Topology Learning for Decentralized SGD with Heterogeneous Data
Batiste Le Bars, Aurélien Bellet, Marc Tommasi +2
One of the key challenges in decentralized and federated learning is to design algorithms that efficiently deal with highly heterogeneous data distributions across agents. In this…
Differentially Private Speaker Anonymization
Ali Shahin Shamsabadi, Brij Mohan Lal Srivastava, Aurélien Bellet +5
Sharing real-world speech utterances is key to the training and deployment of voice-based services. However, it also raises privacy risks as speech contains a wealth of personal da…
Retrieving Speaker Information from Personalized Acoustic Models for Speech Recognition
Salima Mdhaffar, Jean-François Bonastre, Marc Tommasi +2
The widespread of powerful personal devices capable of collecting voice of their users has opened the opportunity to build speaker adapted speech recognition system (ASR) or to par…
Privacy attacks for automatic speech recognition acoustic models in a federated learning framework
Natalia Tomashenko, Salima Mdhaffar, Marc Tommasi +2
This paper investigates methods to effectively retrieve speaker information from the personalized speaker adapted neural network acoustic models (AMs) in automatic speech recogniti…
Differentially Private Coordinate Descent for Composite Empirical Risk Minimization
Paul Mangold, Aurélien Bellet, Joseph Salmon +1
Machine learning models can leak information about the data used to train them. To mitigate this issue, Differentially Private (DP) variants of optimization algorithms like Stochas…
Design Choices for X-vector Based Speaker Anonymization
Brij Mohan Lal Srivastava, Natalia Tomashenko, Xin Wang +5
The recently proposed x-vector based anonymization scheme converts any input voice into that of a random pseudo-speaker. In this paper, we present a flexible pseudo-speaker selecti…
Privacy-Preserving Adversarial Representation Learning in ASR: Reality or Illusion?
Brij Mohan Lal Srivastava, Aurélien Bellet, Marc Tommasi +1
Automatic speech recognition (ASR) is a key technology in many services and applications. This typically requires user devices to send their speech data to the cloud for ASR decodi…
Evaluating Voice Conversion-based Privacy Protection against Informed Attackers
Brij Mohan Lal Srivastava, Nathalie Vauquier, Md Sahidullah +3
Speech data conveys sensitive speaker attributes like identity or accent. With a small amount of found data, such attributes can be inferred and exploited for malicious purposes: v…
Fully Decentralized Joint Learning of Personalized Models and Collaboration Graphs
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 ce…
Personalized and Private Peer-to-Peer Machine Learning
Aurélien Bellet, Rachid Guerraoui, Mahsa Taziki +1
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 perso…
Decentralized Collaborative Learning of Personalized Models over Networks
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. The question add…
Spectral Estimation of Conditional Random Graph Models for Large-Scale Network Data
Antonino Freno, Mikaela Keller, Gemma C. Garriga +1
Generative models for graphs have been typically committed to strong prior assumptions concerning the form of the modeled distributions. Moreover, the vast majority of currently av…
On Probability Distributions for Trees: Representations, Inference and Learning
François Denis, Amaury Habrard, Rémi Gilleron +2
We study probability distributions over free algebras of trees. Probability distributions can be seen as particular (formal power) tree series [Berstel et al 82, Esik et al 03], i.…
Residual Finite Tree Automata
J. Carme, R. Gilleron, A. Lemay +2
Tree automata based algorithms are essential in many fields in computer science such as verification, specification, program analysis. They become also essential for databases with…