Prototype Learning offers an interpretable and efficient classification framework by mapping data into an embedding space structured around class prototypes.Recent research has explored non-Euclidean geometries, such as hyperspherical and hyperbolic spaces, to more effectively model latent hierarchical structures and complex data relationships.While these geometries have shown potential, leveraging them within an image classification context is not trivial.To address this, we propose HypPNet, a hyperbolic prototypical model on the Poincaré ball that integrates Riemannian optimization and norm-based regularization to perform effectively without prior data knowledge.Experiments on three benchmark datasets and multiple embedding dimensions show that HypPNet outperforms its competitors across alternative geometries, improving classification performance over various metrics.

Non-Euclidean geometries have garnered significant research interest, particularly in their application to Deep Learning. Utilizing specific manifolds as embedding spaces has been shown to enhance neural network representational capabilities by aligning these spaces with the data’s latent structure. In this paper, we focus on hyperbolic manifolds and introduce a novel framework, Hyperbolic Prototypical Entailment Cones (HPEC). The core innovation of HPEC lies in utilizing angular relationships, rather than traditional distance metrics, to more effectively capture the similarity between data representations and their corresponding prototypes. This is achieved by leveraging hyperbolic entailment cones, a mathematical construct particularly suited for embedding hierarchical structures in the Poincare’ Ball, along with a novel Backclip mechanism. Our experimental results demonstrate that this approach significantly enhances performance in high-dimensional embedding spaces. To substantiate these findings, we evaluate HPEC on four diverse datasets across various embedding dimensions, consistently surpassing state-of-the-art methods in Prototype Learning.

Time series classification is a pivotal task in modern machine learning, with widespread applications in fields such as healthcare, finance, and cybersecurity. While deep learning methods dominate recent developments, their resource demands and privacy limitations hinder deployment on low-power and decentralized environments. To address these challenges, we introduce Fed2RC, a fully federated and gradient-free approach that integrates the efficiency of Rocket-based feature extraction with the robustness of ridge regression in a privacy-preserving setting. Fed2RC builds upon two key ideas: (i) federated selection and aggregation of high-performing random convolution kernels, and (ii) incremental and communication-efficient updates of ridge classifier parameters using closed-form solutions. Additionally, we propose a novel federated protocol for selecting the global ridge regularization parameter λ, and show how to improve the communication efficiency by matrix factorization techniques. Extensive experiments on the UCR benchmark demonstrate that Fed2RC achieves state-of-the-art results with a fraction of the computation and communication costs. Code to reproduce the experiments can be found at: https://github.com/CasellaJr/Fed2RC.

Hierarchical Text Classification poses the difficult challenge of classifying documents into multiple labels organized in a hierarchy.The vast majority of works aimed to address this problem relies on supervised methods which are difficult to implement due to the scarcity of labeled data in many real world applications.This paper focuses on strict Zero-Shot Classification, the setting in which the system lacks both labeled instances and training data.We propose a novel approach that uses a Large Language Model to augment the deepest layer of the labels hierarchy in order to enhance its specificity.We achieve this by generating semantically relevant labels as children connected to the existing branches, creating a deeper taxonomy that better overlaps with the input texts.We leverage the enriched hierarchy to perform Zero-Shot Hierarchical Classification by using the Upward score Propagation technique.We test our method on four public datasets, obtaining new state-of-the art results on three of them.We introduce two cosine similarity-based metrics to quantify the density and granularity of a label taxonomy and we show a strong correlation between the metric values and the classification performance of our method on the datasets.

This paper presents FedHP, an algorithm that amalgamates federated learning, hyperspherical geometries, and prototype learning.Federated Learning (FL) has garnered attention as a privacy-preserving method for constructing robust models across distributed datasets.Traditionally, FL involves exchanging model parameters to uphold data privacy; however, in scenarios with costly data communication, exchanging large neural network models becomes impractical.In such instances, prototype learning provides a feasible solution by necessitating the exchange of a few class prototypes instead of entire deep learning models.Motivated by these considerations, our approach leverages recent advancements in prototype learning, particularly the benefits offered by non-Euclidean geometries.Alongside introducing FedHP, we provide empirical evidence demonstrating its comparable performance to other state-of-the-art approaches while significantly reducing communication costs.

In this paper we investigate the relationships between a multipreferential semantics for defeasible reasoning in knowledge representation and a multilayer neural network model. Weighted knowledge bases for a simple description logic with typicality are considered under a (many-valued) “concept-wise” multipreference semantics. The semantics is used to provide a preferential interpretation of MultiLayer Perceptrons (MLPs). A model checking and an entailment based approach are exploited in the verification of conditional properties of MLPs.

Abstract 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.

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.

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.

In this paper, we explore the usage of hierarchical priors to improve learning in contexts where the number of available examples is extremely low.Specifically, we consider a Prototype Learning setting where deep neural networks are used to embed data in hyperspherical geometries.In this scenario, we propose an innovative way to learn the prototypes by combining class separation and hierarchical information.In addition, we introduce a contrastive loss function capable of balancing the exploitation of prototypes through a prototype pruning mechanism.We compare the proposed method with state-of-the-art approaches on two public datasets.This work has been partially supported by the Spoke 1 "FutureHPC & BigData" of ICSC -Centro Nazionale di Ricerca in High-Performance-Computing, Big Data and Quantum Computing, funded by European Union -NextGenerationEU.

Federated Learning (FL) is becoming popular in different industrial sectors where data access is critical for security, privacy and the economic value of data itself. Unlike traditional machine learning, where all the data must be globally gathered for analysis, FL makes it possible to extract knowledge from data distributed across different organizations that can be coupled with different Machine Learning paradigms. In this work, we replicate, using Federated Learning, the analysis of a pooled dataset (with AdaBoost) that has been used to define the PRAISE score, which is today among the most accurate scores to evaluate the risk of a second acute myocardial infarction. We show that thanks to the extended-OpenFL framework, which implements AdaBoost.F, we can train a federated PRAISE model that exhibits comparable accuracy and recall as the centralised model. We achieved F1 and F2 scores which are consistently comparable to the PRAISE score study of a 16-parties federation but within an order of magnitude less time.

Abstract 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.

Federated Learning has been proposed to develop better AI systems without compromising the privacy of final users and the legitimate interests of private companies. Initially deployed by Google to predict text input on mobile devices, FL has been deployed in many other industries. Since its introduction, Federated Learning mainly exploited the inner working of neural networks and other gradient descent-based algorithms by either exchanging the weights of the model or the gradients computed during learning. While this approach has been very successful, it rules out applying FL in contexts where other models are preferred, e.g., easier to interpret or known to work better. This paper proposes FL algorithms that build federated models without relying on gradient descent-based methods. Specifically, we leverage distributed versions of the AdaBoost algorithm to acquire strong federated models. In contrast with previous approaches, our proposal does not put any constraint on the client-side learning models. We perform a large set of experiments on ten UCI datasets, comparing the algorithms in six non-iidness settings.

High-Performance Computing (HPC) is one of the strategic priorities for research and innovation worldwide due to its relevance for industrial and scientific applications. We envision HPC as composed of three pillars: infrastructures, applications, and key technologies and tools. While infrastructures are by construction centralized in large-scale HPC centers, and applications are generally within the purview of domain-specific organizations, key technologies fall in an intermediate case where coordination is needed, but design and development are often decentralized. A large group of Italian researchers has started a dedicated laboratory within the National Interuniversity Consortium for Informatics (CINI) to address this challenge. The laboratory, albeit young, has managed to succeed in its first attempts to propose a coordinated approach to HPC research within the EuroHPC Joint Undertaking, participating in the calls 2019--20 to five successful proposals for an aggregate total cost of 95M€. In this paper, we outline the working group's scope and goals and provide an overview of the five funded projects, which become fully operational in March 2021, and cover a selection of key technologies provided by the working group partners, highlighting their usage development within the projects.

To achieve high performance and high energy efficiency on near-future exascale computing systems, three key technology gaps needs to be bridged. These gaps include: energy efficiency and thermal control; extreme computation efficiency via HW acceleration and new arithmetics; methods and tools for seamless integration of reconfigurable accelerators in heterogeneous HPC multi-node platforms. TEXTAROSSA aims at tackling this gap through a co-design approach to heterogeneous HPC solutions, supported by the integration and extension of HW and SW IPs, programming models and tools derived from European research.

The last decade has witnessed a massive deployment of Machine Learning tools in everyday life automated tasks. Neural Networks are nowadays in use in a growing number of application areas because of their excellent performances. Unfortunately, it has been shown by many researchers that they can be attacked and fooled in several different ways, and this can dangerously impair their ability to correctly perform their tasks. In this paper we describe a watermarking algorithm that can protect and verify the integrity of (Deep) Neural Networks when deployed in safety critical systems, such as autonomous driving systems or monitoring and surveillance systems.

Ranking algorithms based on Neural Networks have been a topic of recent research. Ranking is employed in everyday applications like product recommendations, search results, or even in finding good candidates for hiring. However, Neural Networks are mostly opaque tools, and it is hard to evaluate why a specific candidate, for instance, was not considered. Therefore, for neural-based ranking methods to be trustworthy, it is crucial to guarantee that the outcome is fair and that the decisions are not discriminating people according to sensitive attributes such as gender, sexual orientation, or ethnicity.In this work we present a family of fair pairwise learning to rank approaches based on Neural Networks, which are able to produce balanced outcomes for underprivileged groups and, at the same time, build fair representations of data, i.e. new vectors having no correlation with regard to a sensitive attribute. We compare our approaches to recent work dealing with fair ranking and evaluate them using both relevance and fairness metrics. Our results show that the introduced fair pairwise ranking methods compare favorably to other methods when considering the fairness/relevance trade-off.

In this paper we present a novel algorithm, CarpeDiem. It significantly improves on the time complexity of Viterbi algorithm, preserving the optimality of the result. This fact has consequences on Machine Learning systems that use Viterbi algorithm during learning or classification. We show how the algorithm applies to the Supervised Sequential Learning task and, in particular, to the HMPerceptron algorithm. We illustrate CarpeDiem in full details, and provide experimental results that support the proposed approach.

Properties of ensemble classification can be studied using the framework of Monte Carlo stochastic algorithms. Within this framework it is also possible to define a new ensemble classifier, whose accuracy probability distribution can be computed exactly. This paper has two goals: first, an experimental comparison between the theoretical predictions and experimental results; second, a systematic comparison between bagging and Monte Carlo ensemble classification.

In this paper we extend previous results providing a theoretical analysis of a new Monte Carlo ensemble classifier. The framework allows us to characterize the conditions under which the ensemble approach can be expected to outperform the single hypothesis classifier. Moreover, we provide a closed form expression for the distribution of the true ensemble accuracy, as well as of its mean and variance. We then exploit this result in order to analyze the expected error behavior in a particularly interesting case.