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.

Since its inception in 2016, Federated Learning (FL) has gained significant traction in the machine learning community. Several frameworks have been developed to facilitate FL algorithm design, yet researchers often resort to implementing their own solutions from scratch, including simulated environments and baselines. This is likely due to the complexity and inflexibility of existing frameworks, as well as the steep learning curve needed to extend them. In this paper, we introduce fluke , a Python package designed to streamline the development and evaluation of FL algorithms. fluke is specifically tailored for prototyping, making it ideal for researchers and practitioners focused on the learning components of federated systems. fluke is open source and can be used off-the-shelf via its command-line interface or extended with new algorithms with minimal effort. It is designed to be user-friendly, emphasizing ease of use and extensibility. The package includes a wide array of state-of-the-art FL algorithms and datasets, and it is regularly updated to include the latest advancements in the field.

Federated learning enables privacy-preserving machine learning across distributed data sources, but real-world deployments face challenges that extend beyond standard protocols. This tutorial provides a structured overview of the field, addressing issues such as non-stationary data, client heterogeneity, resource constraints, and security threats. Beyond existing surveys, it incorporates hands-on insights and deployment experiences, including concrete war stories illustrating how federated learning methods perform under real-world conditions. The tutorial also outlines emerging directions, including federated graph learning, game-theoretic approaches, and sustainable AI concepts. It aims to provide both a conceptual framework and practical guidance for researchers and practitioners advancing federated learning in dynamic and evolving environments.

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.

The widespread adoption of artificial intelligence systems with continuously higher capabilities is causing ethical concerns. The lack of transparency, particularly for state-of-the-art models such as deep neural networks, hinders the applicability of such black-box methods in many domains, like the medical or the financial ones, where model transparency is a mandatory requirement, and hence white-box models are largely preferred over potentially more accurate but opaque techniques. For this reason, in this paper, we focus on ruleset learning, arguably the most interpretable class of learning techniques. Specifically, we propose Bayes Point Rule Classifier, an ensemble methodology inspired by the Bayes Point Machine, to improve the performance and robustness of rule-based classifiers. In addition, to improve interpretability, we propose a technique to retain the most relevant rules based on their importance, thus increasing the transparency of the ensemble, making it easier to understand its decision-making process. We also propose FIND-RS, a greedy ruleset learning algorithm that, under mild conditions, guarantees to learn hypothesis with perfect accuracy on the training set while preserving a good generalization capability to unseen data points. We performed extensive experimentation showing that FIND-RS achieves state-of-the-art classification performance at the cost of a slight increase in the ruleset complexity w.r.t. the competitors. However, when paired with the Bayes Point Rule Classifier, FIND-RS outperforms all the considered baselines. • A committee of rule sets is proposed to improve the performance of rule-based classifiers. • The methodology is inspired by the Bayes Point classifier. • The interpretability of rule sets is improved by identifying the most important rules. • Find-RS, a novel rule learning algorithm, is proposed, to take advantage of the aggregation. • The methodology can be easily applied to existing rule-based classifiers.

Federated learning provides a collaborative way to build machine learning models without sharing private data. However, attackers might infer private information from model updates submitted by participants, and the aggregator might maliciously forge the final aggregation results. Federated learning still faces data privacy and aggregation integrity challenges. In this paper, we combine inference attacks and information theory to analyze the sensitivity of different bits of model parameters. We conclude that not all bits of model parameters will leak privacy. This realization inspires us to propose a novel low-expansion homomorphic aggregation scheme based on Paillier homomorphic encryption (PHE) for safeguarding participants’ data privacy. Building upon this, we develop PriVeriFL-A, a privacy-preserving and aggregation-verifiable federated learning scheme that combines homomorphic hash function and signature. To prevent collusion attacks between the aggregator and malicious participants, we further improve our PHE-based scheme into a threshold PHE-based one, named PriVeriFL-B. Compared with the privacy-preserving federated learning scheme based on classic PHE, PriVeriFL-A reduces the communication overhead to 1.65%, and the encryption/decryption computation overhead to 0.88%. Both PriVeriFL-A and PriVeriFL-B can effectively verify the integrity of the global model, while maintaining an almost negligible communication overhead for integrity verification and protecting the privacy of participants’ data.

In various domains requiring general knowledge and agent reasoning, traditional reinforcement learning (RL) algorithms often start from scratch, lacking prior knowledge of the environment.This approach can lead to significant inefficiencies as agents sometimes undergo extensive exploration before optimizing their actions.Conversely, in this paper we assume that recent Vision Language Models (VLMs), integrating both visual and textual information, possess inherent knowledge and basic reasoning capabilities, offering potential solutions to the sample inefficiency problem in RL.The paper explores the integration of VLMs into RL by employing a robust VLM model, Idefics-9B, as a policy updated via Proximal Policy Optimization (PPO).Experimental results on simulated environments demonstrate that utilizing VLMs in RL significantly accelerates PPO convergence and improves rewards compared to traditional solutions.Additionally, we propose a streamlined modification to the model architecture for memory efficiency and lighter training, and we release a number of upgraded environments featuring both visual observations and textual descriptions, which, we hope, will facilitate research in VLM and RL applications.Code is available at: https://github.com/giobin/VlmPolicyEsann24

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.

This tutorial provides an overview of machine learning methodologies applied in distributed, federated, and non-stationary environments.We focus on recent advancements and novel research contributions of the field.Key topics include data analysis and pattern recognition for non-stationary environments, model compression, federated learning algorithms, and privacy preservation.This tutorial aims to equip researchers and practitioners with insights into current challenges and innovative solutions in this dynamic field. 47

Higher-order interactions (HOIs) are ubiquitous in real-world complex systems and applications. Investigation of deep learning for HOIs, thus, has become a valuable agenda for the data mining and machine learning communities. As networks of HOIs are expressed mathematically as hypergraphs, hypergraph neural networks (HNNs) have emerged as a powerful tool for representation learning on hypergraphs. Given the emerging trend, we present the first survey dedicated to HNNs, with an in-depth and step-by-step guide. Broadly, the present survey overviews HNN architectures, training strategies, and applications. First, we break existing HNNs down into four design components: (i) input features, (ii) input structures, (iii) message-passing schemes, and (iv) training strategies. Second, we examine how HNNs address and learn HOIs with each of their components. Third, we overview the recent applications of HNNs in recommendation, bioinformatics and medical science, time series analysis, and computer vision. Lastly, we conclude with a discussion on limitations and future directions.

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.

This paper proposes an effective bottom-up extension of the popular FIND-S algorithm to learn (monotone) DNF-type rulesets.The algorithm greedily finds a partition of the positive examples.The produced monotone DNF is a set of conjunctive rules, each corresponding to the most specific rule consistent with a part of positive and all negative examples.We also propose two principled extensions of this method, approximating the Bayes Optimal Classifier by aggregating monotone DNF decision rules.Finally, we provide a methodology to improve the explainability of the learned rules while retaining their generalization capabilities.An extensive comparison with state-of-the-art symbolic and statistical methods on several benchmark data sets shows that our proposal provides an excellent balance between explainability and accuracy.

Deep generative modeling (DGM) is an increasingly popular approach that can create novel and unseen data, starting from a given data set. As the technology shows promising applications, many ethical issues also arise. For example, their misuse can enable disinformation campaigns and powerful phishing attempts. Research also shows different biases affect deep learning models, leading to social issues such as misrepresentation. In this work, we formulate a novel setting to deal with similar problems, showing that a repurposed anomaly detection system effectively generates novel data, avoiding generating specified unwanted data. We propose Variational Auto-encoding Binary Classifiers (V-ABC): a novel model that repurposes and extends the Auto-encoding Binary Classifier (ABC) anomaly detector using the Variational Auto-encoder (VAE). We survey the limitations of existing approaches and explore many tools to show the model's inner workings in an interpretable way. This proposal has excellent potential for generative applications: models that rely on user-generated data could automatically filter out unwanted content, such as offensive language, obscene images, and misleading information.

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.

Nowadays, online services, like e-commerce or streaming services, provide a personalized user experience through recommender systems. Recommender systems are built upon a vast amount of data about users/items acquired by the services. Such knowledge represents an invaluable resource. However, commonly, part of this knowledge is public and can be easily accessed via the Internet. Unfortunately, that same knowledge can be leveraged by competitors or malicious users. The literature offers a large number of works concerning attacks on recommender systems, but most of them assume that the attacker can easily access the full rating matrix. In practice, this is never the case. The only way to access the rating matrix is by gathering the ratings (e.g., reviews) by crawling the service’s website. Crawling a website has a cost in terms of time and resources. What is more, the targeted website can employ defensive measures to detect automatic scraping. In this paper, we assess the impact of a series of attacks on recommender systems. Our analysis aims to set up the most realistic scenarios considering both the possibilities and the potential attacker’s limitations. In particular, we assess the impact of different crawling approaches when attacking a recommendation service. From the collected information, we mount various profile injection attacks. We measure the value of the collected knowledge through the identification of the most similar user/item. Our empirical results show that while crawling can indeed bring knowledge to the attacker (up to 65% of neighborhood reconstruction on a mid-size dataset and up to 90% on a small-size dataset), this will not be enough to mount a successful shilling attack in practice.

The latest developments in the field of artificial intelligence (AI) have given rise to many ethical and socio-economic concerns. Nonetheless, the impact of AI technologies is evident and tangible in our everyday life. This dichotomy leads to mixed feelings toward AI: people recognize the positive impact of AI, but they also show concerns, especially about their privacy and security. In this article, we try to understand whether the implicit and explicit attitudes toward AI are coherent. We investigated explicit and implicit attitudes toward AI by combining a self-report measure and an implicit measure, i.e., the implicit association test. We analyzed the explicit and implicit responses of 829 participants. Results revealed that while most of the participants explicitly express a positive attitude toward AI, their implicit responses seem to point in the opposite direction. Results also show that, in both the explicit and implicit measures, females show a more negative attitude than males, and people who work in the field of AI are inclined to be positive toward AI.

In this paper, we propose a secure and privacy-preserving technique for computing dot-product kernels on vertically distributed data.Our proposal is based on secure multi-party computation which provides theoretical guarantees on both security and privacy.We also provide a practical application of the method by adapting a kernel-based collaborative filtering technique to the federated setting.An extensive experimental evaluation shows the effectiveness of the proposed approach.11

Recommender Systems (RSs) are valuable technologies that help users in their decision-making process. Generally, RSs are designed with the assumption that a central server stores and manages historical users' behaviors. However, users are nowadays more aware of privacy issues leading to a higher demand for privacy-preserving technologies. To cope with this issue, the Federated Learning (FL) paradigm can provide good performance without harming the users' privacy. Some efforts have been devoted to adapt standard collaborative filtering methods (e.g., matrix factorization) into the FL framework in recent years. In this paper, we present a Federated Variational Autoencoder for Collaborative Filtering (FedVAE), which extends the state-of-the-art MultVAE model. Additionally, we propose an adaptive learning rate schedule to accelerate learning. We also discuss the potential privacy-preserving capabilities of FedVAE. An extensive experimental evaluation on five benchmark data sets shows that our proposal can achieve performance close to MultVAE in a reasonable number of iterations. We also empirically demonstrate that the adaptive learning rate guarantees both accelerated learning and good stability.

E-commerce and online services are getting more and more ubiquitous day by day. Like many other e-commerce paradigms, online grocery services can highly benefit from recommender systems, especially when it comes to predicting users' shopping behavior. This specific scenario owns peculiar characteristics, such as repetitiveness and loyalty, which makes the task very different from the standard recommendations. In this work, we present an efficient solution to compute the next basket recommendation, under a more general top-n recommendation framework. We propose a set of collaborative filtering based techniques able to capture users' shopping patterns. Furthermore, we analyzed how recency plays a key role in this particular task. We finally compare our method with state-of-the-art algorithms on two online grocery service datasets.

A large body of research is currently investigating on the connection between machine learning and game theory. In this work, game theory notions are injected into a preference learning framework. Specifically, a preference learning problem is seen as a two-players zero-sum game. An algorithm is proposed to incrementally include new useful features into the hypothesis. This can be particularly important when dealing with a very large number of potential features like, for instance, in relational learning and rule extraction. A game theoretical analysis is used to demonstrate the convergence of the algorithm. Furthermore, leveraging on the natural analogy between features and rules, the resulting models can be easily interpreted by humans. An extensive set of experiments on classification tasks shows the effectiveness of the proposed method in terms of interpretability and feature selection quality, with accuracy at the state-of-the-art.

Accurate prediction of the completion time of a business process instance would constitute a valuable tool when managing processes under service level agreement constraints. Such prediction, however, is a very challenging task. A wide variety of factors could influence the trend of a process instance, and hence just using time statistics of historical cases cannot be sufficient to get accurate predictions. Here we propose a new approach where, in order to improve the prediction quality, both the control and the data flow perspectives are jointly used. To achieve this goal, our approach builds a process model which is augmented by time and data information in order to enable remaining time prediction. The remaining time prediction of a running case is calculated combining two factors: (a) the likelihood of all the following activities, given the data collected so far; and (b) the remaining time estimation given by a regression model built upon the data.