Publications
(You may also look at my Google Scholar and dblp profiles)
■ Book/Theses ■ Journal articles ■ Conference papers ■ Informal publications & preprints
2024
- A. Shahin Shamsabadi, G. Tan, T. I. Cebere, A. Bellet, H. Haddadi, N. Papernot, X. Wang and A. Weller. Confidential-DPproof: Confidential Proof of Differentially Private Training. International Conference on Learning Representations (ICLR), 2024. Selected for spotlight presentation (5% acceptance rate).
[OpenReview version] [bibtex] - L. Béthune, T. Massena, T. Boissin, A. Bellet, F. Mamalet, Y. Prudent, C. Friedrich, M. Serrurier and D. Vigouroux. DP-SGD Without Clipping: The Lipschitz Neural Network Way. International Conference on Learning Representations (ICLR), 2024.
[OpenReview version] [bibtex] - H. Hendrikx, P. Mangold and A. Bellet. The Relative Gaussian Mechanism and its Application to Private Gradient Descent. International Conference on Artificial Intelligence and Statistics (AISTATS) , 2024.
[arXiv version] [bibtex] - A. El Mrini, E. Cyffers and A. Bellet. Privacy Attacks in Decentralized Learning. arXiv:2402.10001, 2024.
[paper] [bibtex] - E. Cyffers, A. Bellet and J. Upadhyay. Differentially Private Decentralized Learning with Random Walks. arXiv:2402.07471, 2024.
[paper] [bibtex]
2023
- G. Maheshwari, A. Bellet, P. Denis and M. Keller. Fair Without Leveling Down: A New Intersectional Fairness Definition. Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023.
[arXiv version] [bibtex] - E. Cyffers, A. Bellet and D. Basu. From Noisy Fixed-Point Iterations to Private ADMM for Centralized and Federated Learning. International Conference on Machine Learning (ICML), 2023.
[arXiv version] [bibtex] - P. Humbert, B. Le Bars, A. Bellet and S. Arlot. One-Shot Federated Conformal Prediction. International Conference on Machine Learning (ICML), 2023.
[arXiv version] [bibtex] [code] - P. Mangold, M. Perrot, A. Bellet and M. Tommasi. Differential Privacy has Bounded Impact on Fairness in Classification. International Conference on Machine Learning (ICML), 2023.
[arXiv version] [bibtex] - B. Le Bars, A. Bellet, M. Tommasi, E. Lavoie and A.-M. Kermarrec. Refined Convergence and Topology Learning for Decentralized SGD with Heterogeneous Data. International Conference on Artificial Intelligence and Statistics (AISTATS), 2023.
[arXiv version] [bibtex] - P. Mangold, A. Bellet, J. Salmon and M. Tommasi. High-Dimensional Private Empirical Risk Minimization by Greedy Coordinate Descent. International Conference on Artificial Intelligence and Statistics (AISTATS), 2023.
[arXiv version] [bibtex] - S. Sajadmanesh, A. Shahin Shamsabadi, A. Bellet and D. Gatica-Perez. GAP: Differentially Private Graph Neural Networks with Aggregation Perturbation. USENIX Security Symposium, 2023.
[arXiv version] [bibtex] [code] - A. Shahin Shamsabadi, B. M. L. Srivastava, A. Bellet, N. Vauquier, E. Vincent, M. Maouche, M. Tommasi and N. Papernot. Differentially Private Speaker Anonymization. Privacy Enhancing Technologies Symposium (PETS), 2023.
[arXiv version] [bibtex] - C. Pierquin, A. Bellet, M. Tommasi and M. Boussard. Rényi Pufferfish Privacy: General Additive Noise Mechanisms and Privacy Amplification by Iteration. arXiv:2312.13985, 2023.
[paper] [bibtex] - B. Le Bars, A. Bellet, M. Tommasi, K. Scaman, G. Neglia. Improved Stability and Generalization Guarantees of the Decentralized SGD Algorithm. arXiv:2306.02939, 2023.
[paper] [bibtex]
2022
- M. Asadi, A. Bellet, O.-A. Maillard and M. Tommasi. Collaborative Algorithms for Online Personalized Mean Estimation. Transactions on Machine Learning Research, 2022.
[paper] [bibtex] [code] - C. Sabater, A. Bellet and J. Ramon. An Accurate, Scalable and Verifiable Protocol for Federated Differentially Private Averaging. Machine Learning, 111:4249-4293, 2022.
[paper] [arXiv version] [bibtex] [code] - Y. Belal, A. Bellet, S. Ben Mokhtar and V. Nitu. PEPPER: Empowering User-Centric Recommender Systems over Gossip Learning. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT/Ubicomp), 6(3), 2022.
[paper] [arXiv version] [bibtex] - B. M. L. Srivastava, M. Maouche, M. Sahidullah, E. Vincent, A. Bellet, M. Tommasi, N. Tomashenko, X. Wang and J. Yamagishi. Privacy and utility of x-vector based speaker anonymization. IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP), 30:2383-2395, 2022.
[HAL version] [bibtex] - E. Cyffers, M. Even, A. Bellet and L. Massoulié. Muffliato: Peer-to-Peer Privacy Amplification for Decentralized Optimization and Averaging. Annual Conference on Neural Information Processing Systems (NeurIPS), 2022.
[arXiv version] [bibtex] [code] - J. Ogier du Terrail, S.-S. Ayed, E. Cyffers, F. Grimberg, C. He, R. Loeb, P. Mangold, T. Marchand, O. Marfoq, E. Mushtaq, B. Muzellec, C. Philippenko, S. Silva, M. Teleńczuk, S. Albarqouni, S. Avestimehr, A. Bellet, A. Dieuleveut, M. Jaggi, S.P. Karimireddy, M. Lorenzi, G. Neglia, M. Tommasi and M. Andreux. FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settings. Annual Conference on Neural Information Processing Systems (NeurIPS), 2022.
[arXiv version] [bibtex] - P. Mangold, A. Bellet, J. Salmon and M. Tommasi. Differentially Private Coordinate Descent for Composite Empirical Risk Minimization. International Conference on Machine Learning (ICML), 2022.
[arXiv version] [bibtex] [code] - M. Noble, A. Bellet, and A. Dieuleveut. Differentially Private Federated Learning on Heterogeneous Data. International Conference on Artificial Intelligence and Statistics (AISTATS), 2022.
[arXiv version] [bibtex] [code] - E. Cyffers and A. Bellet. Privacy Amplification by Decentralization. International Conference on Artificial Intelligence and Statistics (AISTATS), 2022.
[arXiv version] [bibtex] [code] - G. Maheshwari, P. Denis, M. Keller and A. Bellet. Fair NLP Models with Differentially Private Text Encoders. Findings of the Association for Computational Linguistics: EMNLP 2022, 2022.
[arXiv version] [bibtex] [code] - M. Maouche, B. M. L. Srivastava, N. Vauquier, A. Bellet, M. Tommasi and E. Vincent. Enhancing Speech Privacy with Slicing. Annual Conference of the International Speech Communication Association (INTERSPEECH), 2022.
[HAL version] [bibtex] - A. Bellet, A.-M. Kermarrec and E. Lavoie. D-Cliques: Compensating for Data Heterogeneity with Topology in Decentralized Federated Learning. International Symposium on Reliable Distributed Systems (SRDS), 2022.
[arXiv version] [bibtex] [code] - P. Mangold, M. Perrot, A. Bellet and M. Tommasi. Fairness Certificates for Differentially Private Classification. NeurIPS Workshop on Algorithmic Fairness through the Lens of Causality and Privacy, 2022.
- B. Le Bars, A. Bellet, M. Tommasi, E. Lavoie and A.-M. Kermarrec. Refined Convergence and Topology Learning for Decentralized Optimization with Heterogeneous Data. International Workshop on Federated Learning: Recent Advances and New Challenges (FL-NeurIPS'22), 2022.
2021
- A. Bellet. Contributions to Decentralized and Privacy-Preserving Machine Learning. Habilitation thesis (HDR), Université de Lille, 2021.
[manuscript] [slides] - P. Kairouz, H. B. McMahan, B. Avent, A. Bellet, M. Bennis, A. Nitin Bhagoji, K. Bonawitz, Z. Charles, G. Cormode, R. Cummings, R. G. L. D'Oliveira, H. Eichner, S. El Rouayheb, D. Evans, J. Gardner, Z. Garrett, A. Gascón, B. Ghazi, P. B. Gibbons, M. Gruteser, Z. Harchaoui, C. He, L. He, Z. Huo, B. Hutchinson, J. Hsu, M. Jaggi, T. Javidi, G. Joshi, M. Khodak, J. Konečný, A. Korolova, F. Koushanfar, S. Koyejo, T. Lepoint, Y. Liu, P. Mittal, M. Mohri, R. Nock, A. Özgür, R. Pagh, M. Raykova, H. Qi, D. Ramage, R. Raskar, D. Song, W. Song, S. U. Stich, Z. Sun, A. Theertha Suresh, F. Tramèr, P. Vepakomma, J. Wang, L. Xiong, Z. Xu, Q. Yang, F. X. Yu, H. Yu and S. Zhao. Advances and Open Problems in Federated Learning. Foundations and Trends® in Machine Learning, 14(1-2):1-210, 2021.
[arXiv version] [bibtex] - B. Paige, J. Bell, A. Bellet, A. Gascón and D. Ezer. Reconstructing Genotypes in Private Genomic Databases from Genetic Risk Scores. Journal of Computational Biology, 28(5):435-451, 2021.
[paper] [bioRxiv version] [bibtex] - A. Bellet, P. Denis, R. Gilleron, M. Keller and N. Vauquier. Pour plus de transparence dans l'analyse automatique des consultations ouvertes : leçons de la synthèse du Grand Débat National. Statistique et Société, 9(1-2):147-168, 2021.
[paper] [bibtex] [code] - O. Marfoq, G. Neglia, A. Bellet, L. Kameni and R. Vidal. Federated Multi-Task Learning under a Mixture of Distributions. Annual Conference on Neural Information Processing Systems (NeurIPS), 2021.
[arXiv version] [bibtex] [code] - R. Vogel, A. Bellet and S. Clémençon. Learning Fair Scoring Functions: Bipartite Ranking under ROC-based Fairness Constraints. International Conference on Artificial Intelligence and Statistics (AISTATS), 2021.
[paper] [supplementary] [arXiv version] [bibtex] [code] - M. Noble, A. Bellet, and A. Dieuleveut. Differentially Private Federated Learning on Heterogeneous Data. CCS Workshop on Privacy Preserving Machine Learning, 2021.
- P. Mangold, A. Bellet, J. Salmon and M. Tommasi. Differentially Private Coordinate Descent for Composite Empirical Risk Minimization. CCS Workshop on Privacy Preserving Machine Learning, 2021.
- O. Marfoq, G. Neglia, A. Bellet, L. Kameni and R. Vidal. Federated Multi-Task Learning under a Mixture of Distributions. ICML Workshop on Federated Learning for User Privacy and Data Confidentiality, 2021.
- R. Ladjel, N. Anciaux, A. Bellet and G. Scerri. Mitigating Leakage from Data Dependent Communications in Decentralized Computing using Differential Privacy. arXiv:2112.12411, 2021.
[paper] [bibtex]
2020
- W. de Vazelhes, C. J. Carey, Y. Tang, N. Vauquier and A. Bellet. metric-learn: Metric Learning Algorithms in Python. Journal of Machine Learning Research, 21(138):1-6, 2020.
[paper] [arXiv version] [bibtex] [code] - M. Maouche, B. M. L. Srivastava, N. Vauquier, A. Bellet, M. Tommasi and E. Vincent. A Comparative Study of Speech Anonymization Metrics. Annual Conference of the International Speech Communication Association (INTERSPEECH), 2020.
[paper] [bibtex] - B. M. L. Srivastava, N. Tomashenko, X. Wang, E. Vincent, J. Yamagishi, M. Maouche, A. Bellet and M. Tommasi. Design Choices for X-vector Based Speaker Anonymization. Annual Conference of the International Speech Communication Association (INTERSPEECH), 2020.
[paper] [bibtex] - A. Bellet, R. Guerraoui and H. Hendrikx. Who started this rumor? Quantifying the natural differential privacy guarantees of gossip protocols. International Symposium on Distributed Computing (DISC), 2020.
[paper] [arXiv version] [bibtex] - B. M. L. Srivastava, N. Vauquier, M. Sahidullah, A. Bellet, M. Tommasi and E. Vincent. Evaluating Voice Conversion-based Privacy Protection against Informed Attackers. International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2020.
[paper] [arXiv version] [bibtex] - J. Bell, A. Bellet, A. Gascón and T. Kulkarni. Private Protocols for U-Statistics in the Local Model and Beyond. International Conference on Artificial Intelligence and Statistics (AISTATS), 2020.
[paper] [supplementary] [arXiv version] [bibtex] - V. Zantedeschi, A. Bellet and M. Tommasi. Fully Decentralized Joint Learning of Personalized Models and Collaboration Graphs. International Conference on Artificial Intelligence and Statistics (AISTATS), 2020.
[paper] [supplementary] [arXiv version] [bibtex] [code] - M. Vargas-Vieyra, A. Bellet and P. Denis. Joint Learning of the Graph and the Data Representation for Graph-Based Semi-Supervised Learning. Workshop on Graph-Based Natural Language Processing (TextGraphs), 2020.
[paper] [bibtex] - B. Paige, J. Bell, A. Bellet, A. Gascón and D. Ezer. Reconstructing Genotypes in Private Genomic Databases from Genetic Risk Scores. International Conference on Research in Computational Molecular Biology (RECOMB), 2020.
[longer bioRxiv version] [bibtex] - E. Cyffers and A. Bellet. Privacy Amplification by Decentralization. NeurIPS Workshop on Privacy Preserving Machine Learning and NeurIPS Workshop on Scalability, Privacy, and Security in Federated Learning, 2020.
- C. Sabater, A. Bellet and J. Ramon. Distributed Differentially Private Averaging with Improved Utility and Robustness to Malicious Parties. NeurIPS Workshop on Privacy Preserving Machine Learning, 2020.
2019
- A. May, A. Bagheri Garakani, Z. Lu, D. Guo, K. Liu, A. Bellet, L. Fan, M. Collins, D. Hsu, B. Kingsbury, M. Picheny and F. Sha. Kernel Approximation Methods for Speech Recognition. Journal of Machine Learning Research, 20(59):1-36, 2019.
[paper] [arXiv version] [bibtex] - K. Liu and A. Bellet. Escaping the Curse of Dimensionality in Similarity Learning: Efficient Frank-Wolfe Algorithm and Generalization Bounds. Neurocomputing 333:185-199, 2019.
[paper] [arXiv version] [bibtex] [code] - B. M. L. Srivastava, A. Bellet, M. Tommasi and E. Vincent. Privacy-Preserving Adversarial Representation Learning in ASR: Reality or Illusion? Annual Conference of the International Speech Communication Association (INTERSPEECH), 2019.
[paper] [arXiv version] [bibtex] - R. Vogel, A. Bellet, S. Clémençon, O. Jelassi and G. Papa. Trade-offs in Large-Scale Distributed Tuplewise Estimation and Learning. European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML/PKDD), 2019.
[paper] [arXiv version] [bibtex] [code] - J. Bell, A. Bellet, A. Gascón and T. Kulkarni. Private Protocols for U-Statistics in the Local Model and Beyond. CCS Workshop on Theory and Practice of Differential Privacy and CCS Workshop on Privacy Preserving Machine Learning, 2019.
- M. Vargas Vieyra, A. Bellet and P. Denis. Probabilistic End-to-End Graph-based Semi-Supervised Learning. NeurIPS Workshop on Graph Representation Learning and NeurIPS Workshop on Bayesian Deep Learning, 2019.
2018
- W. Zheng, A. Bellet and P. Gallinari. A Distributed Frank-Wolfe Framework for Learning Low-Rank Matrices with the Trace Norm. Machine Learning 107(8-10):1457-1475, 2018.
[paper] [arXiv version] [bibtex] [code] - M. Ailem, B. Zhang, A. Bellet, P. Denis and F. Sha. A Probabilistic Model for Joint Learning of Word Embeddings from Texts and Images. Conference on Empirical Methods in Natural Language Processing (EMNLP), 2018.
[paper] [bibtex] - R. Vogel, A. Bellet and S. Clémençon. A Probabilistic Theory of Supervised Similarity Learning for Pointwise ROC Curve Optimization. International Conference on Machine Learning (ICML), 2018.
[paper] [supplementary] [arXiv version] [bibtex] [code] - A. Bellet, R. Guerraoui, M. Taziki and M. Tommasi. Personalized and Private Peer-to-Peer Machine Learning. International Conference on Artificial Intelligence and Statistics (AISTATS), 2018.
[paper] [supplementary] [arXiv version] [bibtex] - V. Zantedeschi, A. Bellet and M. Tommasi. Communication-Efficient Decentralized Boosting while Discovering the Collaboration Graph. NeurIPS Workshop on Machine Learning on the Phone and other Consumer Devices, 2018.
- A. Bellet, R. Guerraoui and H. Hendrikx. Who started this gossip? Differentially private rumor spreading. NeurIPS Workshop on Privacy Preserving Machine Learning, 2018.
- P. Dellenbach, A. Bellet and J. Ramon. Hiding in the Crowd: A Massively Distributed Algorithm for Private Averaging with Malicious Adversaries. arXiv:1803.09984, 2018.
[paper] [bibtex]
2017
- P. Vanhaesebrouck, A. Bellet and M. Tommasi. Decentralized Collaborative Learning of Personalized Models over Networks. International Conference on Artificial Intelligence and Statistics (AISTATS), 2017.
[paper] [supplementary] [arXiv version] [bibtex] - A. Bellet, R. Guerraoui, M. Taziki and M. Tommasi. Personalized and Private Peer-to-Peer Machine Learning. NIPS Workshop on Machine Learning on the Phone and other Consumer Devices, 2017.
[slides] - T. Le Van, A. Bellet and J. Ramon. Decentralized and Privacy-Aware Learning of Traversal Time Models. ECML/PKDD workshop on Data Mining with Secure Computation, 2017.
2016
- S. Clémençon, I. Colin and A. Bellet. Scaling-up Empirical Risk Minimization: Optimization of Incomplete U-statistics. Journal of Machine Learning Research 17(76):1-36, 2016.
[paper] [arXiv version] [bibtex] - A. Bellet, J.F. Bernabeu, A. Habrard and M. Sebban. Learning Discriminative Tree Edit Similarities for Linear Classification — Application to Melody Recognition. Neurocomputing 214:155-161, 2016.
[paper] [bibtex] - G. Papa, A. Bellet and S. Clémençon. On Graph Reconstruction via Empirical Risk Minimization: Fast Learning Rates and Scalability. Annual Conference on Neural Information Processing Systems (NIPS), 2016.
[paper] [supplementary] [bibtex] - I. Colin, A. Bellet, J. Salmon and S. Clémençon. Gossip Dual Averaging for Decentralized Optimization of Pairwise Functions. International Conference on Machine Learning (ICML), 2016.
[paper] [supplementary] [arXiv version] [bibtex] - Z. Lu, D. Guo, A. Bagheri Garakani, K. Liu, A. May, A. Bellet, L. Fan, M. Collins, B. Kingsbury, M. Picheny and F. Sha. A Comparison Between Deep Neural Nets and Kernel Acoustic Models for Speech Recognition. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2016.
[paper] [arXiv version] [bibtex] - P. Dellenbach, J. Ramon and A. Bellet. A Decentralized and Robust Protocol for Private Averaging over Highly Distributed Data. NIPS workshop on Private Multi-Party Machine Learning, 2016.
2015
- A. Bellet, A. Habrard and M. Sebban. Metric Learning. Morgan & Claypool Publishers, 2015.
[publisher's website] [bibtex] - A. Bellet and A. Habrard. Robustness and Generalization for Metric Learning. Neurocomputing 151(1):259–267, 2015.
[paper] [arXiv version] [bibtex] - I. Colin, A. Bellet, J. Salmon and S. Clémençon. Extending Gossip Algorithms to Distributed Estimation of U-statistics. Annual Conference on Neural Information Processing Systems (NIPS), 2015. Selected for spotlight presentation (4% acceptance rate).
[paper] [supplementary] [arXiv version] [bibtex] [code] - G. Papa, S. Clémençon and A. Bellet. SGD Algorithms based on Incomplete U-statistics: Large-Scale Minimization of Empirical Risk. Annual Conference on Neural Information Processing Systems (NIPS), 2015.
[paper] [supplementary] [bibtex] - S. Clémençon, A. Bellet, O. Jelassi and G. Papa. Scalability of Stochastic Gradient Descent based on "Smart" Sampling Techniques. INNS Conference on Big Data (INNS-BigData), 2015.
[bibtex] - K. Liu, A. Bellet and F. Sha. Similarity Learning for High-Dimensional Sparse Data. International Conference on Artificial Intelligence and Statistics (AISTATS), 2015.
[paper] [arXiv version] [bibtex] [code] - A. Bellet, Y. Liang, A. Bagheri Garakani, M.-F. Balcan and F. Sha. A Distributed Frank-Wolfe Algorithm for Communication-Efficient Sparse Learning. SIAM International Conference on Data Mining (SDM), 2015.
[paper] [extended version] [bibtex] [code]
2014
- A. Bellet, A. Habrard, E. Morvant and M. Sebban. Learning A Priori Constrained Weighted Majority Votes. Machine Learning 97(1-2):129-154, 2014.
[paper] [bibtex] - Y. Shi, A. Bellet and F. Sha. Sparse Compositional Metric Learning. AAAI Conference on Artificial Intelligence (AAAI), 2014.
[paper] [extended version] [bibtex] [code] - A. Bellet, Y. Liang, A. Bagheri Garakani, M.-F. Balcan and F. Sha. Distributed Frank-Wolfe Algorithm: A Unified Framework for Communication-Efficient Sparse Learning. ICML workshop on New Learning Frameworks and Models for Big Data, 2014.
[slides] - Z. Lu, A. May, K. Liu, A. Bagheri Garakani, D. Guo, A. Bellet, L. Fan, M. Collins, B. Kingsbury, M. Picheny and F. Sha. How to Scale Up Kernel Methods to Be As Good As Deep Neural Nets. arXiv:1411.4000, 2014.
[paper] [bibtex]
2013
- A. Bellet, A. Habrard and M. Sebban. A Survey on Metric Learning for Feature Vectors and Structured Data. arXiv:1306.6709, 2013.
[paper] [bibtex]
2012
- A. Bellet. Supervised Metric Learning with Generalization Guarantees. Ph.D. thesis, Université Jean Monnet de Saint-Étienne, 2012.
[manuscript] [slides] - A. Bellet, A. Habrard and M. Sebban. Good edit similarity learning by loss minimization. Machine Learning 89(1):5-35, 2012.
[paper] [bibtex] [code] - A. Bellet, A. Habrard and M. Sebban. Similarity Learning for Provably Accurate Sparse Linear Classification. International Conference on Machine Learning (ICML), 2012.
[paper] [slides] [video] [bibtex]
2011
- A. Bellet, A. Habrard and M. Sebban. Learning Good Edit Similarities with Generalization Guarantees. European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML/PKDD), 2011. Among the 10 papers selected for an extended version in Machine Learning Journal.
[paper] [slides] [video] [bibtex] [code] - A. Bellet, A. Habrard and M. Sebban. An Experimental Study on Learning with Good Edit Similarity Functions. International Conference on Tools with Artificial Intelligence (ICTAI), 2011.
[paper] [bibtex] - A. Bellet, A. Habrard and M. Sebban. Good Similarity Learning for Structured Data. NIPS workshop "Beyond Mahalanobis: Supervised Large-Scale Learning of Similarity", 2011.
2010
- A. Bellet, M. Bernard, T. Murgue and M. Sebban. Learning State Machine-based String Edit Kernels. Pattern Recognition 43(6):2330-2339, 2010.
[paper] [bibtex]