RERoberto Esposito

Roberto Esposito

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Roberto Esposito has a total of 61 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • A Lightweight Random Feature Framework for Efficient Image Classification

    by Luca Grandi, Loris Signoretti, Lorenzo Sciandra, Bruno Casella, Marco Aldinucci, Roberto Esposito

  • A survey on multimodal federated learning

    by Silvia Grosso, Nawel Benarba, Sara Bouchenak, Roberto Esposito, Mirko Polato


  • Open Access

    SVF: Support Vector Federation

    by Mirko Polato, Roberto Esposito, Lorenzo Sciandra

    In recent years, Federated Learning applied to neural networks has garnered significant attention, yet applying this approach to other machine learning algorithms remains underexplored. Support Vector Machines (SVMs), in particular, have seen limited exploration within the federated context, with existing techniques often constrained by the necessity to share the weight vector of the linear classifier. Unfortunately, this constraint severely limits the method’s utility, restricting its application to linear feature spaces. This study addresses and overcomes this limitation by proposing an innovative approach: instead of sharing weight vectors, we advocate sharing support vectors while safeguarding client data privacy through vector perturbation. Simple random perturbation works remarkably well in practice, and indeed we provide a bound on the approximation error of the learnt model which goes to zero as the number of input features grows. We also introduce a refined technique that involves strategically moving the support vectors along the margin of the decision function, which we empirically show to slightly improve the performances. Through extensive experimentation, we demonstrate that our proposed approach achieves state-of-the-art performance and consistently enables the federated classifier to match the performance of classifiers trained on the entire dataset.


  • Open Access

    Partitioned least squares

    by Roberto Esposito, Mattia Cerrato, Marco Locatelli

    Linear least squares is one of the most widely used regression methods in many fields. The simplicity of the model allows this method to be used when data is scarce and allows practitioners to gather some insight into the problem by inspecting the values of the learnt parameters. In this paper we propose a variant of the linear least squares model allowing practitioners to partition the input features into groups of variables that they require to contribute similarly to the final result. We show that the new formulation is not convex and provide two alternative methods to deal with the problem: one non-exact method based on an alternating least squares approach; and one exact method based on a reformulation of the problem. We show the correctness of the exact method and compare the two solutions showing that the exact solution provides better results in a fraction of the time required by the alternating least squares solution (when the number of partitions is small). We also provide a branch and bound algorithm that can be used in place of the exact method when the number of partitions is too large as well as a proof of NP-completeness of the optimization problem.


  • Open Access

    Experimenting With Normalization Layers in Federated Learning on Non-IID Scenarios

    by Bruno Casella, Roberto Esposito, Antonio Sciarappa, Carlo Cavazzoni, Marco Aldinucci

    Training Deep Learning (DL) models require large, high-quality datasets, often assembled with data from different institutions. Federated Learning (FL) has been emerging as a method for privacy-preserving pooling of datasets employing collaborative training from different institutions by iteratively globally aggregating locally trained models. One critical performance challenge of FL is operating on datasets not independently and identically distributed (non-IID) among the federation participants. Even though this fragility cannot be eliminated, it can be debunked by a suitable optimization of two hyper-parameters: layer normalization methods and collaboration frequency selection. In this work, we benchmark five different normalization layers for training Neural Networks (NNs), two families of non-IID data skew, and two datasets. Results show that Batch Normalization, widely employed for centralized DL, is not the best choice for FL, whereas Group and Layer Normalization consistently outperform Batch Normalization, with a performance gain of up to about 15 % in the most challenging non-IID scenario. Similarly, frequent model aggregation decreases convergence speed and mode quality.


  • Open Access

    Label Augmentation for Zero-Shot Hierarchical Text Classification

    by Lorenzo Paletto, Valerio Basile, Roberto Esposito

    Lorenzo Paletto, Valerio Basile, Roberto Esposito. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.


  • Open Access

    FairSwiRL: fair semi-supervised classification with representation learning

    by Shuyi Yang, Mattia Cerrato, Dino Ienco, Ruggero G. Pensa, Roberto Esposito

    Semi-supervised learning has shown its potential in many real-world applications where only few labeled examples are available. However, when some fairness constraints need to be satisfied, semi-supervised classification models often struggle as they are required to cope with the lack of sufficient information for predicting the target variable while forgetting its relationships with any sensitive and potentially discriminatory attribute. To address this issue, we propose a fair semi-supervised representation learning architecture that leads to fair and accurate classification results even in very challenging scenarios with few labeled (but biased) instances. We show experimentally that our model can be easily adopted in very general settings, as the learned representations may be employed to train any supervised classifier. Moreover, when applied to several synthetic and real-world datasets, our method is competitive with state-of-the-art fair semi-supervised approaches.


  • Open Access

    Invariant Representations with Stochastically Quantized Neural Networks

    by Mattia Cerrato, Marius Köppel, Roberto Esposito, Stefan Kramer

    Representation learning algorithms offer the opportunity to learn invariant representations of the input data with regard to nuisance factors. Many authors have leveraged such strategies to learn fair representations, i.e., vectors where information about sensitive attributes is removed. These methods are attractive as they may be interpreted as minimizing the mutual information between a neural layer's activations and a sensitive attribute. However, the theoretical grounding of such methods relies either on the computation of infinitely accurate adversaries or on minimizing a variational upper bound of a mutual information estimate. In this paper, we propose a methodology for direct computation of the mutual information between neurons in a layer and a sensitive attribute. We employ stochastically-activated binary neural networks, which lets us treat neurons as random variables. Our method is therefore able to minimize an upper bound on the mutual information between the neural representations and a sensitive attribute. We show that this method compares favorably with the state of the art in fair representation learning and that the learned representations display a higher level of invariance compared to full-precision neural networks.


  • Open Access

    Experimenting with Emerging RISC-V Systems for Decentralised Machine Learning

    by Gianluca Mittone, Nicoló Tonci, Robert Birke, Iacopo Colonnelli, Doriana Medić, Andrea Bartolini, Roberto Esposito, Emanuele Parisi, Francesco Beneventi, Mirko Polato, et al.

    Decentralised Machine Learning (DML) enables collaborative machine learning without centralised input data. Federated Learning (FL) and Edge Inference are examples of DML. While tools for DML (especially FL) are starting to flourish, many are not flexible and portable enough to experiment with novel processors (e.g., RISC-V), non-fully connected network topologies, and asynchronous collaboration schemes. We overcome these limitations via a domain-specific language allowing us to map DML schemes to an underlying middleware, i.e. the FastFlow parallel programming library. We experiment with it by generating different working DML schemes on x86-64 and ARM platforms and an emerging RISC-V one. We characterise the performance and energy efficiency of the presented schemes and systems. As a byproduct, we introduce a RISC-V porting of the PyTorch framework, the first publicly available to our knowledge.


  • Open Access

    1st Workshop on Federated Learning Technologies

    by Mirko Polato, Roberto Esposito, Walter Riviera, Zenglin Xu, Irwin King

    AI-based systems, especially those based on machine learning technologies, have become central in modern societies. In the meanwhile, users and legislators are becoming aware of privacy issues. Users are increasingly reluctant in sharing their sensitive information, and new laws have been enacted to regulate how private data is handled (e.g., the GDPR). Federated Learning (FL) has been proposed to develop better AI systems without compromising users’ privacy and the legitimate interests of private companies. Although still in its infancy, FL has already shown significant theoretical and practical results making FL one of the hottest topics in the machine learning community. Given the considerable potential in overcoming the challenges of protecting users’ privacy while making the most of available data, we propose a workshop on Federated Learning Technologies (FLT) at TheWebConf 2023. The goal of this workshop is to focus the attention of the TheWebConf research community on addressing the open questions and challenges in this thriving research area. Given the broad range of competencies in the TheWebConf community, the workshop will welcome foundational contributions as well as contributions expanding the scope of these techniques, such as improvements in the interpretability and fairness of the learned models.