Frederic Precioso
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
Frederic Precioso has a total of 47 co-authors. Here are the top co-authors by number of shared publications:
- Elisa Ancarani
Université Côte d'Azur, CNRS, I3S, Sophia Antipolis, France
2 shared publications - Hui-Yin Wu
Université Côte d'Azur, INRIA, Sophia-Antipolis, France
2 shared publications - Julie Tores
Université Côte d'Azur, CNRS, Inria, I3S, Sophia Antipolis, France
2 shared publications - Lucile Sassatelli
Université Côte d'Azur, CNRS, I3S, Sophia Antipolis, France
2 shared publications - Mireille Blay-Fornarino
I3S Lab (UMR CNRS 7271), Université Côte d'Azur, Sophia Antipolis, France
2 shared publications - Rémy Sun
Université Côte d'Azur, Inria, CNRS, I3S, Sophia Antipolis, France
2 shared publications
Latest Publications
- Open Access
Using Small Language Models to Reverse-Engineer Machine Learning Pipelines Structures
Background: Extracting the stages that structure Machine Learning (ML) pipelines from source code is key for gaining a deeper understanding of data science practices. However, the diversity caused by the constant evolution of the ML ecosystem (e.g., algorithms, libraries, datasets) makes this task challenging. Existing approaches either depend on non-scalable, manual labeling, or on ML classifiers that do not properly support the diversity of the domain. These limitations highlight the need for more flexible and reliable solutions. Objective: We evaluate whether Small Language Models (SLMs) can leverage their code understanding and classification abilities to address these limitations, and subsequently how they can advance our understanding of data science practices. Method: We conduct a confirmatory study based on two reference works selected for their relevance regarding current state-of-the-art's limitations. First, we compare several SLMs using Cochran's Q test. The best-performing model is then evaluated against the reference studies using two distinct McNemar's tests. We further analyze how variations in taxonomy definitions affect performance through an additional Cochran's Q test. Finally, a goodness-of-fit analysis is conducted using Pearson's chi-squared tests to compare our insights on data science practices with those from prior studies.
Open AccessUsing Small Language Models to Reverse-Engineer Machine Learning Pipelines Structures
Background: Extracting the stages that structure Machine Learning (ML) pipelines from source code is key for gaining a deeper understanding of data science practices. However, the diversity caused by the constant evolution of the ML ecosystem (e.g., algorithms, libraries, datasets) makes this task challenging. Existing approaches either depend on non-scalable, manual labeling, or on ML classifiers that do not properly support the diversity of the domain. These limitations highlight the need for more flexible and reliable solutions. Objective: We evaluate whether Small Language Models (SLMs) can leverage their code understanding and classification abilities to address these limitations, and subsequently how they can advance our understanding of data science practices. Method: We conduct a confirmatory study based on two reference works selected for their relevance regarding current state-of-the-art's limitations. First, we compare several SLMs using Cochran's Q test. The best-performing model is then evaluated against the reference studies using two distinct McNemar's tests. We further analyze how variations in taxonomy definitions affect performance through an additional Cochran's Q test. Finally, a goodness-of-fit analysis is conducted using Pearson's chi-squared tests to compare our insights on data science practices with those from prior studies.
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 12437-12445
Re-examining Concept-based Explainable Models for Multimodal Interpretative Tasks
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 12437-12445
Open AccessRe-examining Concept-based Explainable Models for Multimodal Interpretative Tasks
- Open Access
- 26 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 11-19
Leveraging Concept Annotations for Trustworthy Multimodal Video Interpretation through Modality Specialization
- 26 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 11-19
Open AccessLeveraging Concept Annotations for Trustworthy Multimodal Video Interpretation through Modality Specialization
- Open Access
- 7 October 2025
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 58 (4) , 1-36
A Tutorial on Discriminative Clustering and Mutual Information
To cluster data is to separate samples into distinctive groups that should ideally have some cohesive properties. Today, numerous clustering algorithms exist, and their differences lie essentially in what can be perceived as “cohesive properties”. Therefore, hypotheses on the nature of clusters must be set: they can be either generative or discriminative. As the last decade witnessed the impressive growth of deep clustering methods that involve neural networks to handle high-dimensional data often in a discriminative manner; we concentrate mainly on the discriminative hypotheses. In this article, our aim is to provide an accessible historical perspective on the evolution of discriminative clustering methods and notably how the nature of assumptions of the discriminative models changed over time: from decision boundaries to invariance critics. We notably highlight how mutual information has been a historical cornerstone of the progress of (deep) discriminative clustering methods. We also show some known limitations of mutual information and how discriminative clustering methods tried to circumvent those. We then discuss the challenges that discriminative clustering faces with respect to the selection of the number of clusters. Finally, we showcase these techniques using the dedicated Python package, GemClus , that we have developed for discriminative clustering.
- 7 October 2025
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 58 (4) , 1-36
Open AccessA Tutorial on Discriminative Clustering and Mutual Information
To cluster data is to separate samples into distinctive groups that should ideally have some cohesive properties. Today, numerous clustering algorithms exist, and their differences lie essentially in what can be perceived as “cohesive properties”. Therefore, hypotheses on the nature of clusters must be set: they can be either generative or discriminative. As the last decade witnessed the impressive growth of deep clustering methods that involve neural networks to handle high-dimensional data often in a discriminative manner; we concentrate mainly on the discriminative hypotheses. In this article, our aim is to provide an accessible historical perspective on the evolution of discriminative clustering methods and notably how the nature of assumptions of the discriminative models changed over time: from decision boundaries to invariance critics. We notably highlight how mutual information has been a historical cornerstone of the progress of (deep) discriminative clustering methods. We also show some known limitations of mutual information and how discriminative clustering methods tried to circumvent those. We then discuss the challenges that discriminative clustering faces with respect to the selection of the number of clusters. Finally, we showcase these techniques using the dedicated Python package, GemClus , that we have developed for discriminative clustering.
- Open Access
scMusketeers: Addressing imbalanced cell type annotation and batch effect reduction with a modular autoencoder
The growing number of single-cell gene expression atlases available offers a conceptual framework for improving our understanding of physio-pathological processes. To take full advantage of this revolution, data integration and cell annotation strategies need to be improved, in particular to better detect rare cell types and by better controlling batch effects in experiments. scMusketeers is a deep learning model that optimises the representation of latent data and solves both challenges. scMusketeers features three modules: (1) an autoencoder for noise and dimensionality reductions; (2) a focal loss classifier to enhance rare cell type predictions; and (3) an adversarial domain adaptation (DANN) module for batch effect correction. Benchmarking against state-of-the-art tools, including the UCE foundation model, showed that scMusketeers performs on par or better, particularly in identifying rare cell types. It also allows to transfer cell labels from single-cell RNA sequencing to spatial transcriptomics. With its modular and adaptable design, scMusketeers offers a versatile framework that can be generalized to other large-scale biological projects requiring deep learning approaches, establishing itself as a valuable tool for single-cell data integration and analysis.
Open AccessscMusketeers: Addressing imbalanced cell type annotation and batch effect reduction with a modular autoencoder
The growing number of single-cell gene expression atlases available offers a conceptual framework for improving our understanding of physio-pathological processes. To take full advantage of this revolution, data integration and cell annotation strategies need to be improved, in particular to better detect rare cell types and by better controlling batch effects in experiments. scMusketeers is a deep learning model that optimises the representation of latent data and solves both challenges. scMusketeers features three modules: (1) an autoencoder for noise and dimensionality reductions; (2) a focal loss classifier to enhance rare cell type predictions; and (3) an adversarial domain adaptation (DANN) module for batch effect correction. Benchmarking against state-of-the-art tools, including the UCE foundation model, showed that scMusketeers performs on par or better, particularly in identifying rare cell types. It also allows to transfer cell labels from single-cell RNA sequencing to spatial transcriptomics. With its modular and adaptable design, scMusketeers offers a versatile framework that can be generalized to other large-scale biological projects requiring deep learning approaches, establishing itself as a valuable tool for single-cell data integration and analysis.
- Open Access
- 28 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 27-33
Taming the Diversity of Computational Notebooks
- 28 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 27-33
Open AccessTaming the Diversity of Computational Notebooks
- 1 January 2023
- Published by OpenEdition in Corpus
- Vol. 24
From text saliency to linguistic objects: learning linguistic interpretable markers with a multi-channels convolutional architecture
A lot of effort is currently made to provide methods to analyze and understand deep neural network impressive performances for tasks such as image or text classification. These methods are mainly based on visualizing the important input features taken into account by the network to build a decision. However these techniques, let us cite LIME, SHAP, Grad-CAM, or TDS, require extra effort to interpret the visualization with respect to expert knowledge. In this paper, we propose a novel approach to inspect the hidden layers of a fitted CNN in order to extract interpretable linguistic objects from texts exploiting classification process. In particular, we detail a weighted extension of the Text Deconvolution Saliency (wTDS) measure which can be used to highlight the relevant features used by the CNN to perform the classification task. We empirically demonstrate the efficiency of our approach on corpora from two different languages: English and French. On all datasets, wTDS automatically encodes complex linguistic objects based on co-occurrences and possibly on grammatical and syntax analysis.
- 1 January 2023
- Published by OpenEdition in Corpus
- Vol. 24
From text saliency to linguistic objects: learning linguistic interpretable markers with a multi-channels convolutional architecture
A lot of effort is currently made to provide methods to analyze and understand deep neural network impressive performances for tasks such as image or text classification. These methods are mainly based on visualizing the important input features taken into account by the network to build a decision. However these techniques, let us cite LIME, SHAP, Grad-CAM, or TDS, require extra effort to interpret the visualization with respect to expert knowledge. In this paper, we propose a novel approach to inspect the hidden layers of a fitted CNN in order to extract interpretable linguistic objects from texts exploiting classification process. In particular, we detail a weighted extension of the Text Deconvolution Saliency (wTDS) measure which can be used to highlight the relevant features used by the CNN to perform the classification task. We empirically demonstrate the efficiency of our approach on corpora from two different languages: English and French. On all datasets, wTDS automatically encodes complex linguistic objects based on co-occurrences and possibly on grammatical and syntax analysis.
- Top Cited PapersOpen Access
- 16 September 2022
- Published by Association for Computing Machinery (ACM) in Journal on Computing and Cultural Heritage
- Vol. 15 (3) , 1-23
Learning and Reasoning for Cultural Metadata Quality: Coupling Symbolic AI and Machine Learning over a Semantic Web Knowledge Graph to Support Museum Curators in Improving the Quality of Cultural Metadata and Information Retrieval
This work combines semantic reasoning and machine learning to create tools that allow curators of the visual art collections to identify and correct the annotations of the artwork as well as to improve the relevance of the content-based search results in these collections. The research is based on the Joconde database maintained by the French Ministry of Culture that contains illustrated artwork records from main French public and private museums representing archeological objects, decorative arts, fine arts, historical and scientific documents, etc. The Joconde database includes semantic metadata that describes properties of the artworks and their content. The developed methods create a data pipeline that processes metadata, trains a Convolutional Neural Network image classification model, makes prediction for the entire collection and expands the metadata to be the base for the SPARQL search queries. We developed a set of such queries to identify noise and silence in the human annotations and to search image content with results ranked according to the relevance of the objects quantified by the prediction score provided by the deep learning model. We also developed methods to discover new contextual relationships between the concepts in the metadata by analyzing the contrast between the concepts’ similarities in the Joconde's semantic model and other vocabularies and we tried to improve the model prediction scores based on the semantic relations. Our results show that cross-fertilization between symbolic AI and machine learning can indeed provide the tools to address the challenges of the museum curators work describing the artwork pieces and searching for the relevant images.
- 16 September 2022
- Published by Association for Computing Machinery (ACM) in Journal on Computing and Cultural Heritage
- Vol. 15 (3) , 1-23
Top Cited PapersOpen AccessLearning and Reasoning for Cultural Metadata Quality: Coupling Symbolic AI and Machine Learning over a Semantic Web Knowledge Graph to Support Museum Curators in Improving the Quality of Cultural Metadata and Information Retrieval
This work combines semantic reasoning and machine learning to create tools that allow curators of the visual art collections to identify and correct the annotations of the artwork as well as to improve the relevance of the content-based search results in these collections. The research is based on the Joconde database maintained by the French Ministry of Culture that contains illustrated artwork records from main French public and private museums representing archeological objects, decorative arts, fine arts, historical and scientific documents, etc. The Joconde database includes semantic metadata that describes properties of the artworks and their content. The developed methods create a data pipeline that processes metadata, trains a Convolutional Neural Network image classification model, makes prediction for the entire collection and expands the metadata to be the base for the SPARQL search queries. We developed a set of such queries to identify noise and silence in the human annotations and to search image content with results ranked according to the relevance of the objects quantified by the prediction score provided by the deep learning model. We also developed methods to discover new contextual relationships between the concepts in the metadata by analyzing the contrast between the concepts’ similarities in the Joconde's semantic model and other vocabularies and we tried to improve the model prediction scores based on the semantic relations. Our results show that cross-fertilization between symbolic AI and machine learning can indeed provide the tools to address the challenges of the museum curators work describing the artwork pieces and searching for the relevant images.
- 1 January 2022
- Published by Elsevier in Knowledge-Based Systems
- Vol. 235
Semi-supervised consensus clustering based on closed patterns
- 1 January 2022
- Published by Elsevier in Knowledge-Based Systems
- Vol. 235
Semi-supervised consensus clustering based on closed patterns