Aris Anagnostopoulos

Marianna Maranghi, Aris Anagnostopoulos, Irene Cannistraci et al. · eth-zurich

The Associazione Medici Diabetologi (AMD) collects and manages one of the largest worldwide-available collections of diabetic patient records, also known as the AMD database. This paper presents the initial results of an ongoing project whose focus is the application of Artificial Intelligence and Machine Learning techniques for conceptualizing, cleaning, and analyzing such an important and valuable dataset, with the goal of providing predictive insights to better support diabetologists in their diagnostic and therapeutic choices.

Irene Amerini, Aris Anagnostopoulos, Luca Maiano et al.

Social media and messaging apps have become major communication platforms. Multimedia contents promote improved user engagement and have thus become a very important communication tool. However, fake news and manipulated content can easily go viral, so, being able to verify the source of videos and images as well as to distinguish between native and downloaded content becomes essential. Most of the work performed so far on social media provenance has concentrated on images; in this paper, we propose a CNN architecture that analyzes video content to trace videos back to their social network of origin. The experiments demonstrate that stating platform provenance is possible for videos as well as images with very good accuracy.

Daniel M. Jimenez-Gutierrez, Mehrdad Hassanzadeh, Aris Anagnostopoulos et al.

Federated learning (FL) supports privacy-preserving, decentralized machine learning (ML) model training by keeping data on client devices. However, non-independent and identically distributed (non-IID) data across clients biases updates and degrades performance. To alleviate these issues, we propose Clust-PSI-PFL, a clustering-based personalized FL framework that uses the Population Stability Index (PSI) to quantify the level of non-IID data. We compute a weighted PSI metric, $WPSI^L$, which we show to be more informative than common non-IID metrics (Hellinger, Jensen-Shannon, and Earth Mover's distance). Using PSI features, we form distributionally homogeneous groups of clients via K-means++; the number of optimal clusters is chosen by a systematic silhouette-based procedure, typically yielding few clusters with modest overhead. Across six datasets (tabular, image, and text modalities), two partition protocols (Dirichlet with parameter $α$ and Similarity with parameter S), and multiple client sizes, Clust-PSI-PFL delivers up to 18% higher global accuracy than state-of-the-art baselines and markedly improves client fairness by a relative improvement of 37% under severe non-IID data. These results establish PSI-guided clustering as a principled, lightweight mechanism for robust PFL under label skew.

Daniel M. Jimenez G., David Solans, Mikko Heikkila et al.

Recent advances in machine learning have highlighted Federated Learning (FL) as a promising approach that enables multiple distributed users (so-called clients) to collectively train ML models without sharing their private data. While this privacy-preserving method shows potential, it struggles when data across clients is not independent and identically distributed (non-IID) data. The latter remains an unsolved challenge that can result in poorer model performance and slower training times. Despite the significance of non-IID data in FL, there is a lack of consensus among researchers about its classification and quantification. This technical survey aims to fill that gap by providing a detailed taxonomy for non-IID data, partition protocols, and metrics to quantify data heterogeneity. Additionally, we describe popular solutions to address non-IID data and standardized frameworks employed in FL with heterogeneous data. Based on our state-of-the-art survey, we present key lessons learned and suggest promising future research directions.

Daniel M. Jimenez-Gutierrez, Yelizaveta Falkouskaya, Jose L. Hernandez-Ramos et al.

Federated Learning (FL) is an emerging distributed machine learning paradigm enabling multiple clients to train a global model collaboratively without sharing their raw data. While FL enhances data privacy by design, it remains vulnerable to various security and privacy threats. This survey provides a comprehensive overview of more than 200 papers regarding the state-of-the-art attacks and defense mechanisms developed to address these challenges, categorizing them into security-enhancing and privacy-preserving techniques. Security-enhancing methods aim to improve FL robustness against malicious behaviors such as byzantine attacks, poisoning, and Sybil attacks. At the same time, privacy-preserving techniques focus on protecting sensitive data through cryptographic approaches, differential privacy, and secure aggregation. We critically analyze the strengths and limitations of existing methods, highlight the trade-offs between privacy, security, and model performance, and discuss the implications of non-IID data distributions on the effectiveness of these defenses. Furthermore, we identify open research challenges and future directions, including the need for scalable, adaptive, and energy-efficient solutions operating in dynamic and heterogeneous FL environments. Our survey aims to guide researchers and practitioners in developing robust and privacy-preserving FL systems, fostering advancements safeguarding collaborative learning frameworks' integrity and confidentiality.

Daniel M. Jimenez-Gutierrez, Mehrdad Hassanzadeh, Aris Anagnostopoulos et al.

Federated learning (FL) allows collaborative machine learning (ML) model training among decentralized clients' information, ensuring data privacy. The decentralized nature of FL deals with non-independent and identically distributed (non-IID) data. This open problem has notable consequences, such as decreased model performance and more significant convergence times. Despite its importance, experimental studies systematically addressing all types of data heterogeneity (a.k.a. non-IIDness) remain scarce. We aim to fill this gap by assessing and quantifying the non-IID effect through a thorough empirical analysis. We use the Hellinger Distance (HD) to measure differences in distribution among clients. Our study benchmarks four state-of-the-art strategies for handling non-IID data, including label, feature, quantity, and spatiotemporal skewness, under realistic and controlled conditions. This is the first comprehensive analysis of the spatiotemporal skew effect in FL. Our findings highlight the significant impact of label and spatiotemporal skew non-IID types on FL model performance, with notable performance drops occurring at specific HD thresholds. Additionally, the FL performance is heavily affected mainly when the non-IIDness is extreme. Thus, we provide recommendations for FL research to tackle data heterogeneity effectively. Our work represents the most extensive examination of non-IIDness in FL, offering a robust foundation for future research.

Gianluca De Carlo, Andrea Mastropietro, Aris Anagnostopoulos

Graph neural networks (GNNs) excel in learning from network-like data but often lack interpretability, making their application challenging in domains requiring transparent decision-making. We propose the Graph Kolmogorov-Arnold Network (GKAN), a novel GNN model leveraging spline-based activation functions on edges to enhance both accuracy and interpretability. Our experiments on five benchmark datasets demonstrate that GKAN outperforms state-of-the-art GNN models in node classification, link prediction, and graph classification tasks. In addition to the improved accuracy, GKAN's design inherently provides clear insights into the model's decision-making process, eliminating the need for post-hoc explainability techniques. This paper discusses the methodology, performance, and interpretability of GKAN, highlighting its potential for applications in domains where interpretability is crucial.

Luca Maiano, Irene Amerini, Lorenzo Ricciardi Celsi et al.

Videos have become a powerful tool for spreading illegal content such as military propaganda, revenge porn, or bullying through social networks. To counter these illegal activities, it has become essential to try new methods to verify the origin of videos from these platforms. However, collecting datasets large enough to train neural networks for this task has become difficult because of the privacy regulations that have been enacted in recent years. To mitigate this limitation, in this work we propose two different solutions based on transfer learning and multitask learning to determine whether a video has been uploaded from or downloaded to a specific social platform through the use of shared features with images trained on the same task. By transferring features from the shallowest to the deepest levels of the network from the image task to videos, we measure the amount of information shared between these two tasks. Then, we introduce a model based on multitask learning, which learns from both tasks simultaneously. The promising experimental results show, in particular, the effectiveness of the multitask approach. According to our knowledge, this is the first work that addresses the problem of social media platform identification of videos through the use of shared features.

Tesi Aliaj, Aris Anagnostopoulos, Stefano Piersanti

Academics and practitioners have studied over the years models for predicting firms bankruptcy, using statistical and machine-learning approaches. An earlier sign that a company has financial difficulties and may eventually bankrupt is going in \emph{default}, which, loosely speaking means that the company has been having difficulties in repaying its loans towards the banking system. Firms default status is not technically a failure but is very relevant for bank lending policies and often anticipates the failure of the company. Our study uses, for the first time according to our knowledge, a very large database of granular credit data from the Italian Central Credit Register of Bank of Italy that contain information on all Italian companies' past behavior towards the entire Italian banking system to predict their default using machine-learning techniques. Furthermore, we combine these data with other information regarding companies' public balance sheet data. We find that ensemble techniques and random forest provide the best results, corroborating the findings of Barboza et al. (Expert Syst. Appl., 2017).

Aris Anagnostopoulos, Carlos Castillo, Adriano Fazzone et al.

Although freelancing work has grown substantially in recent years, in part facilitated by a number of online labor marketplaces, (e.g., Guru, Freelancer, Amazon Mechanical Turk), traditional forms of "in-sourcing" work continue being the dominant form of employment. This means that, at least for the time being, freelancing and salaried employment will continue to co-exist. In this paper, we provide algorithms for outsourcing and hiring workers in a general setting, where workers form a team and contribute different skills to perform a task. We call this model team formation with outsourcing. In our model, tasks arrive in an online fashion: neither the number nor the composition of the tasks is known a-priori. At any point in time, there is a team of hired workers who receive a fixed salary independently of the work they perform. This team is dynamic: new members can be hired and existing members can be fired, at some cost. Additionally, some parts of the arriving tasks can be outsourced and thus completed by non-team members, at a premium. Our contribution is an efficient online cost-minimizing algorithm for hiring and firing team members and outsourcing tasks. We present theoretical bounds obtained using a primal-dual scheme proving that our algorithms have a logarithmic competitive approximation ratio. We complement these results with experiments using semi-synthetic datasets based on actual task requirements and worker skills from three large online labor marketplaces.

Na Zhu, Aris Anagnostopoulos, Ioannis Chatzigiannakis

Public educational systems operate thousands of buildings with vastly different characteristics in terms of size, age, location, construction, thermal behavior and user communities. Their strategic planning and sustainable operation is an extremely complex and requires quantitative evidence on the performance of buildings such as the interaction of indoor-outdoor environment. Internet of Things (IoT) deployments can provide the necessary data to evaluate, redesign and eventually improve the organizational and managerial measures. In this work a data mining approach is presented to analyze the sensor data collected over a period of 2 years from an IoT infrastructure deployed over 18 school buildings spread in Greece, Italy and Sweden. The real-world evaluation indicates that data mining on sensor data can provide critical insights to building managers and custodial staff about ways to lower a building's energy footprint through effectively managing building operations.

Aris Anagnostopoulos, Luca Becchetti, Adriano Fazzone et al.

Reducing hidden bias in the data and ensuring fairness in algorithmic data analysis has recently received significant attention. We complement several recent papers in this line of research by introducing a general method to reduce bias in the data through random projections in a "fair" subspace. We apply this method to densest subgraph problem. For densest subgraph, our approach based on fair projections allows to recover both theoretically and empirically an almost optimal, fair, dense subgraph hidden in the input data. We also show that, under the small set expansion hypothesis, approximating this problem beyond a factor of 2 is NP-hard and we show a polynomial time algorithm with a matching approximation bound.