André Péninou
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
André Péninou has a total of 86 co-authors. Here are the top co-authors by number of shared publications:
Florence Sèdes
Toulouse Institute of Computer Science Research (IRIT), University of Toulouse, CNRS, INPT, UPS, UT1, UT2J
10 shared publications- Corinne Amel Zayani
Sfax University
8 shared publications - Olivier Teste
IRIT, UMR 5505 CNRS, Université de Toulouse, UT2J, Toulouse, France
8 shared publications Florence Sedes
Toulouse Institute of Computer Science Research, University of Toulouse, CNRS, INPT, UPS, UT1, UT2J, TOULOUSE, France
6 shared publicationsMarie-Françoise Canut
Toulouse Institute of Computer Science Research (IRIT), University of Toulouse, CNRS, INPT, UPS, UT1, UT2J
6 shared publications- Imen Megdiche
Toulouse University, INUC, IRIT,France
5 shared publications
Latest Publications
- Open Access
- 26 September 2026
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 58 (16) , 1-35
A Survey on Clustered Federated Learning: Taxonomy, Analysis and Applications
As Federated Learning (FL) expands, the challenge of non-independent and identically distributed (non-IID) data becomes critical. Clustered Federated Learning (CFL) addresses this by training multiple specialized models, each representing a group of clients with similar data distributions. However, the term “CFL” has increasingly been applied to operational strategies unrelated to data heterogeneity, creating significant ambiguity. This survey provides a systematic review of the CFL literature and introduces a principled taxonomy that classifies algorithms into Server-side, Client-side, and Metadata-based approaches. Our analysis reveals a distinct dichotomy: while theoretical research prioritizes privacy-preserving Server/Client-side methods, applied papers overwhelmingly favor Metadata-based approaches, prioritizing efficiency over privacy. Furthermore, we explicitly distinguish “Core CFL” (grouping clients for non-IID data) from “Clustered X FL” (operational variants for system heterogeneity). Finally, we outline lessons learned and future directions to bridge the gap between theoretical privacy and practical efficiency.
- 26 September 2026
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 58 (16) , 1-35
Open AccessA Survey on Clustered Federated Learning: Taxonomy, Analysis and Applications
As Federated Learning (FL) expands, the challenge of non-independent and identically distributed (non-IID) data becomes critical. Clustered Federated Learning (CFL) addresses this by training multiple specialized models, each representing a group of clients with similar data distributions. However, the term “CFL” has increasingly been applied to operational strategies unrelated to data heterogeneity, creating significant ambiguity. This survey provides a systematic review of the CFL literature and introduces a principled taxonomy that classifies algorithms into Server-side, Client-side, and Metadata-based approaches. Our analysis reveals a distinct dichotomy: while theoretical research prioritizes privacy-preserving Server/Client-side methods, applied papers overwhelmingly favor Metadata-based approaches, prioritizing efficiency over privacy. Furthermore, we explicitly distinguish “Core CFL” (grouping clients for non-IID data) from “Clustered X FL” (operational variants for system heterogeneity). Finally, we outline lessons learned and future directions to bridge the gap between theoretical privacy and practical efficiency.
- 12 August 2026
- Published by Springer Nature
- p. 174-188
CODA: A Coordinate-Driven Autoencoder for Robust Multivariate Time Series Anomaly Detection
- 12 August 2026
- Published by Springer Nature
- p. 174-188
CODA: A Coordinate-Driven Autoencoder for Robust Multivariate Time Series Anomaly Detection
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 149-158
A Robust Clustered Federated Learning Approach for Non-IID Data with Quantity Skew
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 149-158
Open AccessA Robust Clustered Federated Learning Approach for Non-IID Data with Quantity Skew
- Open Access
- 10 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-10
Similarity Measures Recommendation for Mixed Data Clustering
Clustering is an important data mining task which is widely spread in various domains such as biology, finance, marketing, healthcare, and social sciences. It allows the end user to discover, through built clusters, relationships within data. Many non-expert users perceive clustering as an "easy" task because it always produces a result. However, choosing a clustering algorithm at random, without proper parameter tuning, often leads to poor results. In particular, an important choice when applying a clustering algorithm to a specific dataset is the similarity measure. Since clustering algorithms rely on similarities between data points to build clusters, the chosen similarity measure should fit the data as accurately as possible in order to form the best clusters. Mixed Data are data that are characterized by numerical as well as categorical attributes. When clustering mixed data, the same similarity measure cannot be used for the two attribute types. Commonly a pair of similarity measures is used, one dedicated to numerical attributes and one dedicated to categorical attributes. The choice of these two most appropriate similarity measures is very important in mixed data, as it significantly affects the clustering performance. In this paper, we challenge to recommend the best pairs of similarity measures to end-users, regardless of their experience, when applying a specific clustering algorithm to a mixed dataset to maximize a specific performance measure. The proposed recommendation process relies on knowledge extracted from a meta-model built by an automated machine learning (AutoML) approach. To evaluate the relevance of the recommendation process, experiments are conducted with two well-known clustering algorithms: K-Prototypes and Hierarchical Clustering. Our results show that the recommendations can positively help users select the most appropriate pairs of similarity measures depending on their use cases (i.e. clustering algorithm, dataset, and performance measure). These recommendations outperform the traditionally used similarity measures in the literature, particularly for datasets where the choice of the similarity measures has a significant impact.
- 10 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-10
Open AccessSimilarity Measures Recommendation for Mixed Data Clustering
Clustering is an important data mining task which is widely spread in various domains such as biology, finance, marketing, healthcare, and social sciences. It allows the end user to discover, through built clusters, relationships within data. Many non-expert users perceive clustering as an "easy" task because it always produces a result. However, choosing a clustering algorithm at random, without proper parameter tuning, often leads to poor results. In particular, an important choice when applying a clustering algorithm to a specific dataset is the similarity measure. Since clustering algorithms rely on similarities between data points to build clusters, the chosen similarity measure should fit the data as accurately as possible in order to form the best clusters. Mixed Data are data that are characterized by numerical as well as categorical attributes. When clustering mixed data, the same similarity measure cannot be used for the two attribute types. Commonly a pair of similarity measures is used, one dedicated to numerical attributes and one dedicated to categorical attributes. The choice of these two most appropriate similarity measures is very important in mixed data, as it significantly affects the clustering performance. In this paper, we challenge to recommend the best pairs of similarity measures to end-users, regardless of their experience, when applying a specific clustering algorithm to a mixed dataset to maximize a specific performance measure. The proposed recommendation process relies on knowledge extracted from a meta-model built by an automated machine learning (AutoML) approach. To evaluate the relevance of the recommendation process, experiments are conducted with two well-known clustering algorithms: K-Prototypes and Hierarchical Clustering. Our results show that the recommendations can positively help users select the most appropriate pairs of similarity measures depending on their use cases (i.e. clustering algorithm, dataset, and performance measure). These recommendations outperform the traditionally used similarity measures in the literature, particularly for datasets where the choice of the similarity measures has a significant impact.
- 2 May 2024
- Published by Springer Nature
- p. 3-18
Unified Models and Framework for Querying Distributed Data Across Polystores
- 2 May 2024
- Published by Springer Nature
- p. 3-18
Unified Models and Framework for Querying Distributed Data Across Polystores
- 18 August 2023
- Published by Springer Nature
- p. 437-442
A Polystore Querying System Applied to Heterogeneous and Horizontally Distributed Data
- 18 August 2023
- Published by Springer Nature
- p. 437-442
A Polystore Querying System Applied to Heterogeneous and Horizontally Distributed Data
- 10 August 2023
- Published by Springer Nature
- p. 319-324
Unified Views for Querying Heterogeneous Multi-model Polystores
- 10 August 2023
- Published by Springer Nature
- p. 319-324
Unified Views for Querying Heterogeneous Multi-model Polystores
- Open Access
- 29 January 2021
- Published by Institution of Engineering and Technology (IET) in IET Computer Vision
- Vol. 15 (2) , 85-98
Improving vehicle re‐identification using CNN latent spaces: Metrics comparison and track‐to‐track extension
Herein, the problem of vehicle re‐identification using distance comparison of images in CNN latent spaces is addressed. First, the impact of the distance metrics, comparing performances obtained with different metrics is studied: the minimal Euclidean distance ( MED ), the minimal cosine distance ( MCD ) and the residue of the sparse coding reconstruction ( RSCR ). These metrics are applied using features extracted from five different CNN architectures, namely ResNet18, AlexNet, VGG16, InceptionV3 and DenseNet201. We use the specific vehicle re‐identification dataset VeRi to fine‐tune these CNNs and evaluate results. Overall, independently of the CNN used, MCD outperforms MED , commonly used in the literature. These results are confirmed on other vehicle retrieval datasets. Second, the state‐of‐the‐art image‐to‐track process (I2TP) is extended to a track‐to‐track process (T2TP). The three distance metrics are extended to measure distance between tracks, enabling T2TP. T2TP and I2TP are compared using the same CNN models. Results show that T2TP outperforms I2TP for MCD and RSCR. T2TP combining DenseNet201 and MCD ‐based metrics exhibits the best performances, outperforming the state‐of‐the‐art I2TP‐based models. Finally, experiments highlight two main results: i) the impact of metric choice in vehicle re‐identification, and ii) T2TP improves the performances compared with I2TP, especially when coupled with MCD ‐based metrics.
- 29 January 2021
- Published by Institution of Engineering and Technology (IET) in IET Computer Vision
- Vol. 15 (2) , 85-98
Open AccessImproving vehicle re‐identification using CNN latent spaces: Metrics comparison and track‐to‐track extension
Herein, the problem of vehicle re‐identification using distance comparison of images in CNN latent spaces is addressed. First, the impact of the distance metrics, comparing performances obtained with different metrics is studied: the minimal Euclidean distance ( MED ), the minimal cosine distance ( MCD ) and the residue of the sparse coding reconstruction ( RSCR ). These metrics are applied using features extracted from five different CNN architectures, namely ResNet18, AlexNet, VGG16, InceptionV3 and DenseNet201. We use the specific vehicle re‐identification dataset VeRi to fine‐tune these CNNs and evaluate results. Overall, independently of the CNN used, MCD outperforms MED , commonly used in the literature. These results are confirmed on other vehicle retrieval datasets. Second, the state‐of‐the‐art image‐to‐track process (I2TP) is extended to a track‐to‐track process (T2TP). The three distance metrics are extended to measure distance between tracks, enabling T2TP. T2TP and I2TP are compared using the same CNN models. Results show that T2TP outperforms I2TP for MCD and RSCR. T2TP combining DenseNet201 and MCD ‐based metrics exhibits the best performances, outperforming the state‐of‐the‐art I2TP‐based models. Finally, experiments highlight two main results: i) the impact of metric choice in vehicle re‐identification, and ii) T2TP improves the performances compared with I2TP, especially when coupled with MCD ‐based metrics.
- Open Access
- 25 August 2020
- Published by Association for Computing Machinery (ACM)
- p. 1-10
Negative filtering of CCTV Content - forensic video analysis framework
This paper presents our work on forensic video analysis that aimed to assist videosurveillance operators by reducing the volume of video to analyze during the search for post-evidence in videos. This work is conducted in collaboration with the French National Police and is based on requirements defined in a project related to videos analysis in the context of investigations. Due to the constant increasing volume of video generated by CCTV cameras, one of the investigators' goals is to reduce video analysis time. For this purpose, we propose a negative filtering approach based on quality and usability/utility metadata, enabling to eliminate video sequences that do not satisfy requirements for their analysis through automatic processing. Our approach involves a data model which is able to integrate different levels of video metadata, and an associated query mechanism. Experiments performed using the developed framework demonstrate the utility of our approach in a real-world case. Results show that our approach helps CCTV operators to significantly reduce video analysis times.
- 25 August 2020
- Published by Association for Computing Machinery (ACM)
- p. 1-10
Open AccessNegative filtering of CCTV Content - forensic video analysis framework
This paper presents our work on forensic video analysis that aimed to assist videosurveillance operators by reducing the volume of video to analyze during the search for post-evidence in videos. This work is conducted in collaboration with the French National Police and is based on requirements defined in a project related to videos analysis in the context of investigations. Due to the constant increasing volume of video generated by CCTV cameras, one of the investigators' goals is to reduce video analysis time. For this purpose, we propose a negative filtering approach based on quality and usability/utility metadata, enabling to eliminate video sequences that do not satisfy requirements for their analysis through automatic processing. Our approach involves a data model which is able to integrate different levels of video metadata, and an associated query mechanism. Experiments performed using the developed framework demonstrate the utility of our approach in a real-world case. Results show that our approach helps CCTV operators to significantly reduce video analysis times.
- 20 February 2020
- Published by Springer Nature
- p. 424-442
CoRP: A Pattern-Based Anomaly Detection in Time-Series
- 20 February 2020
- Published by Springer Nature
- p. 424-442
CoRP: A Pattern-Based Anomaly Detection in Time-Series