Mirko Marras

Università degli studi di Cagliari | UNICA · Department of Mathematics and Computer Science

Detecting 3D objects in images from urban monocular cameras is essential to enable intelligent monitoring applications for local municipalities decision-support systems. However, existing detection methods in this domain are mainly focused on autonomous driving and limited to frontal views from sensors mounted on the vehicle. In contrast, to monito...

In recommendation literature, explainability and fairness are becoming two prominent perspectives to consider. However, prior works have mostly addressed them separately, for instance by explaining to consumers why a certain item was recommended or mitigating disparate impacts in recommendation utility. None of them has leveraged explainability tec...

Law enforcement regularly faces the challenge of ranking suspects from their facial images. Deep face models aid this process but frequently introduce biases that disproportionately affect certain demographic segments. While bias investigation is common in domains like job candidate ranking, the field of forensic face rankings remains underexplored...

In information forensics, (police) agents are usually presented with a ranking of suspects similar to a certain face probe whose identity should be determined. Used for estimating the relevance score of possible suspects, deep face models have been proven to lead to undesirable discriminatory outcomes for certain demographic groups. Despite other n...

Time series is the most prevalent form of input data for educational prediction tasks. The vast majority of research using time series data focuses on hand-crafted features, designed by experts for predictive performance and interpretability. However, extracting these features is labor-intensive for humans and computers. In this paper, we propose a...

Face biometrics play a primary role in smart cities, from consumer- to organizational-level applications. This class of technologies has been recently shown to emphasize performance disparities across gender and ethnic groups. Prior work on demographic bias in deep face recognition has tended to focus exclusively on high-resolution images, leaving...

The massive adoption of artificial intelligence has opened up the opportunity for a range of intelligent technologies that can support education. Empowering instructors with tools able to early predict the attendance and quality of their courses and consequently make prompt adjustments is one of them. However, the potential of these tools has by no...

In recent years, personalization research has been delving into issues of explainability and fairness. While some techniques have emerged to provide post-hoc and self-explanatory individual recommendations, there is still a lack of methods aimed at uncovering unfairness in recommendation systems beyond identifying biased user and item features. Thi...

Creating search and recommendation models responsibly requires monitoring more than just effectiveness and efficiency. Before moving these models into production, it is imperative to audit training data and evaluate their predictions for bias. Prior work has uncovered and studied the effects of different types of bias that can manifest in search an...

Path reasoning is a notable recommendation approach that models high-order user-product relations, based on a Knowledge Graph (KG). This approach can extract reasoning paths between recommended products and already experienced products and, then, turn such paths into textual explanations for the user. Unfortunately, evaluation protocols in this fie...

In recent years, there has been an increasing number of mitigation procedures against consumer unfairness in personalized rankings. However, the experimental protocols adopted so far for evaluating a mitigation procedure were often fundamentally different (e.g., with respect to the fairness definitions, data sets, data splits, and evaluation metric...

Path reasoning is a notable recommendation approach that models high-order user-product relations, based on a Knowledge Graph (KG). This approach can extract reasoning paths between recommended products and already experienced products and, then, turn such paths into textual explanations for the user. Unfortunately, evaluation protocols in this fie...

Algorithms deployed in education can shape the learning experience and success of a student. It is therefore important to understand whether and how such algorithms might create inequalities or amplify existing biases. In this paper, we analyze the fairness of models which use behavioral data to identify at-risk students and suggest two novel pre-p...

Deep learning models for learning analytics have become increasingly popular over the last few years; however, these approaches are still not widely adopted in real-world settings, likely due to a lack of trust and transparency. In this paper, we tackle this issue by implementing explainable AI methods for black-box neural networks. This work focus...

Student success models might be prone to develop weak spots, i.e., examples hard to accurately classify due to insufficient representation during model creation. This weakness is one of the main factors undermining users' trust, since model predictions could for instance lead an instructor to not intervene on a student in need. In this paper, we un...

Time series is the most prevalent form of input data for educational prediction tasks. The vast majority of research using time series data focuses on hand-crafted features, designed by experts for predictive performance and interpretability. However, extracting these features is labor-intensive for humans and computers. In this paper, we propose a...

Face biometrics are playing a key role in making modern smart city applications more secure and usable. Commonly, the recognition threshold of a face recognition system is adjusted based on the degree of security for the considered use case. The likelihood of a match can be for instance decreased by setting a high threshold in case of a payment tra...

Numerous Knowledge Graphs (KGs) are being created to make Recommender Systems (RSs) not only intelligent but also knowledgeable. Integrating a KG in the recommendation process allows the underlying model to extract reasoning paths between recommended products and already experienced products from the KG. These paths can be leveraged to generate tex...

In this paper, we propose a novel explanatory framework aimed to provide a better understanding of how face recognition models perform as the underlying data characteristics (protected attributes: gender, ethnicity, age; nonprotected attributes: facial hair, makeup, accessories, face orientation and occlusion, image distortion, emotions) on which t...

Learning journals are increasingly used in vocational education to foster self-regulated learning and reflective learning practices. However, for many apprentices, documenting working experiences is a difficult task. In this article, we profile apprentices' learning behavior in an online learning journal. Based on a pedagogical framework, we propos...

Face biometrics are playing a key role in making modern smart city applications more secure and usable. Commonly, the recognition threshold of a face recognition system is adjusted based on the degree of security for the considered use case. The likelihood of a match can be for instance decreased by setting a high threshold in case of a payment tra...

Numerous Knowledge Graphs (KGs) are being created to make recommender systems not only intelligent but also knowledgeable. Reinforcement recommendation reasoning is a recent approach able to model high-order user-product relations, according to the KG. This type of approach makes it possible to extract reasoning paths between the recommended produc...

In this paper, we propose a novel explanatory framework aimed to provide a better understanding of how face recognition models perform as the underlying data characteristics (protected attributes: gender, ethnicity, age; non-protected attributes: facial hair, makeup, accessories, face orientation and occlusion, image distortion, emotions) on which...

There is increasing evidence that recommendations accompanied by explanations positively impact on businesses in terms of trust, guidance, and persuasion. This advance has been made possible by traditional models representing user-product interactions augmented with external knowledge modelled as knowledge graphs. However, these models produce text...

Existing explainable recommender systems have mainly modeled relationships between recommended and already experienced products, and shaped explanation types accordingly (e.g., movie "x'' starred by actress "y'' recommended to a user because that user watched other movies with "y'' as an actress). However, none of these systems has investigated th...

Interactive simulations allow students to discover the underlying principles of a scientific phenomenon through their own exploration. Unfortunately, students often struggle to learn effectively in these environments. Classifying students' interaction data in the simulations based on their expected performance has the potential to enable adaptive g...

Neural networks are ubiquitous in applied machine learning for education. Their pervasive success in predictive performance comes alongside a severe weakness, the lack of explainability of their decisions, especially relevant in human-centric fields. We implement five state-of-the-art methodologies for explaining black-box machine learning models (...

In recent years, there has been a stimulating discussion on how artificial intelligence (AI) can support the science and engineering of intelligent educational applications. Many studies in the field are proposing actionable data mining pipelines and machine-learning models driven by learning-related data. The potential of these pipelines and model...

Ranking systems have an unprecedented influence on how and what information people access, and their impact on our society is being analyzed from different perspectives, such as users’ discrimination. A notable example is represented by reputation-based ranking systems, a class of systems that rely on users’ reputation to generate a non-personalize...

Despite the increasing popularity of massive open online courses (MOOCs), many suffer from high dropout and low success rates. Early prediction of student success for targeted intervention is therefore essential to ensure no student is left behind in a course. There exists a large body of research in success prediction for MOOCs, focusing mainly on...

Engaging all content providers, including newcomers or minority demographic groups, is crucial for online platforms to keep growing and working. Hence, while building recommendation services, the interests of those providers should be valued. In this paper, we consider providers as grouped based on a common characteristic in settings in which certa...

Existing explainable recommender systems have mainly modeled relationships between recommended and already experienced products, and shaped explanation types accordingly (e.g., movie "x" starred by actress "y" recommended to a user because that user watched other movies with "y" as an actress). However, none of these systems has investigated the ex...

In this paper, we propose dictionary attacks against speaker verification - a novel attack vector that aims to match a large fraction of speaker population by chance. We introduce a generic formulation of the attack that can be used with various speech representations and threat models. The attacker uses adversarial optimization to maximize raw sim...

Creating search and recommendation algorithms that are efficient and effective has been the main goal for the industry and the academia for years. However, recent research has shown that these algorithms lead to models, trained on historical data, that might exacerbate existing biases and generate potentially negative outcomes. Defining, assessing...

Ranking systems have an unprecedented influence on how and what information people access, and their impact on our society is being analyzed from different perspectives, such as users' discrimination. A notable example is represented by reputation-based ranking systems, a class of systems that rely on users' reputation to generate a non-personalize...

In urban scenarios, biometric recognition technologies are being increasingly adopted to empower citizens with a secure and usable access to personalized services. Given the challenging environmental scenarios, combining evidence from multiple biometrics at a certain step of the recognition pipeline has been often proved to increase the performance...

Enabling non-discrimination for end-users of recommender systems by introducing consumer fairness is a key problem, widely studied in both academia and industry. Current research has led to a variety of notions, metrics, and unfairness mitigation procedures. The evaluation of each procedure has been heterogeneous and limited to a mere comparison wi...

Enabling non-discrimination for end-users of recommender systems by introducing consumer fairness is a key problem, widely studied in both academia and industry. Current research has led to a variety of notions, metrics, and unfairness mitigation procedures. The evaluation of each procedure has been heterogeneous and limited to a mere comparison wi...

In recent years, there has been a stimulating discussion on how artificial intelligence (AI) can support the science and engineering of intelligent educational applications. Many studies in the field are proposing actionable data mining pipelines and machine-learning models driven by learning-related data. The potential of these pipelines and model...

In this paper, we propose dictionary attacks against speaker verification - a novel attack vector that aims to match a large fraction of speaker population by chance. We introduce a generic formulation of the attack that can be used with various speech representations and threat models. The attacker uses adversarial optimization to maximize raw sim...

Online education platforms play an increasingly important role in mediating the success of individuals’ careers. Therefore, while building overlying content recommendation services, it becomes essential to guarantee that learners are provided with equal recommended learning opportunities, according to the platform principles, context, and pedagogy....

Considering the impact of recommendations on item providers is one of the duties of multi-sided recommender systems. Item providers are key stakeholders in online platforms, and their earnings and plans are influenced by the exposure their items receive in recommended lists. Prior work showed that certain minority groups of providers, characterized...

Interactive simulations allow students to independently explore scientific phenomena and ideally infer the underlying principles through their exploration. Effectively using such environments is challenging for many students and therefore , adaptive guidance has the potential to improve student learning. Providing effective support is, however, als...

The First International Workshop on Enabling Data-Driven Decisions from Learning on the Web (L2D 2021) was held as part of the 14th ACM International Conference on Web Search and Data Mining (WSDM 2021) on March 12, 2021. The workshop collected novel, original research on the state of the art of online education empowered with data mining and machi...

The design and delivering of platforms for online education is fostering increasingly intense research. Scaling up education online brings new emerging needs related with hardly manageable classes, overwhelming content alternatives, and academic dishonesty while interacting remotely, as examples. However , with the impressive progress of the data m...

The human voice conveys unique characteristics of an individual, making voice biometrics a key technology for verifying identities in various industries. Despite the impressive progress of speaker recognition systems in terms of accuracy, a number of ethical and legal concerns has been raised, specifically relating to the fairness of such systems....

Providing efficient and effective search and recommendation algorithms has been traditionally the main objective for the industrial and academic research communities. However, recent studies have shown that optimizing models through these algorithms may reinforce the existing societal biases, especially under certain circumstances (e.g., when histo...

Recommender systems learn from historical users’ feedback that is often non-uniformly distributed across items. As a consequence, these systems may end up suggesting popular items more than niche items progressively, even when the latter would be of interest for users. This can hamper several core qualities of the recommended lists (e.g., novelty,...

This book constitutes refereed proceedings of the Second International Workshop on Algorithmic Bias in Search and Recommendation, BIAS 2021, held in April, 2021. Due to the COVID-19 pandemic BIAS 2021 was held virtually. The 11 full papers and 3 short papers were carefully reviewed and selected from 37 submissions. The papers cover topics that go...

To allow individuals to complete voice-based tasks (e.g., send messages or make payments), modern automated systems are required to match the speaker’s voice to a unique digital identity representation for verification. Despite the increasing accuracy achieved so far, it still remains under-explored how the decisions made by such systems may be inf...

Considering the impact of recommendations on item providers is one of the duties of multi-sided recommender systems. Item providers are key stakeholders in online platforms, and their earnings and plans are influenced by the exposure their items receive in recommended lists. Prior work showed that certain minority groups of providers, characterized...

Recommender systems learn from historical data that is often non-uniformly distributed across items, so they may end up suggesting popular items more than niche items. This can hamper user interest and several qualities of the recommended lists (e.g., novelty, coverage, diversity), impacting on the future success of the platform. In this paper, we...

Online educational platforms are promising to play a primary role in mediating the success of individuals' careers. Hence, while building overlying content recommendation services, it becomes essential to ensure that learners are provided with equal learning opportunities, according to the platform values, context, and pedagogy. Even though the imp...

The International Workshop on Algorithmic Bias in Search and Recommendation was held on April 14, 2020 in conjuction with the 42nd European Conference on Information Retrieval (ECIR 2020). The scientific program included paper and demo presentations and a final discussion. The keynote was delivered by Prof Chirag Shah. This report presents an overv...

ECIR 2020 ¹ was one of the many conferences affected by the COVID-19 pandemic. The Conference Chairs decided to keep the initially planned dates (April 14-17, 2020) and move to a fully online event. In this report, we describe the experience of organising the ECIR 2020 Workshops in this scenario from two perspectives: the workshop organisers and th...

ECIR 2020 https://ecir2020.org/ was one of the many conferences affected by the COVID-19 pandemic. The Conference Chairs decided to keep the initially planned dates (April 14-17, 2020) and move to a fully online event. In this report, we describe the experience of organizing the ECIR 2020 Workshops in this scenario from two perspectives: the worksh...

Both search and recommendation algorithms provide results based on their relevance for the current user. In order to do so, such a relevance is usually computed by models trained on historical data, which is biased in most cases. Hence, the results produced by these algorithms naturally propagate, and frequently reinforce, biases hidden in the data...

With tons of healthcare reviews being collected online, finding helpful opinions among this collective intelligence is becoming harder. Existing literature in this domain usually tackled helpfulness prediction with machine-learning models optimized for binary classification. While they can filter out a subset of reviews, users might be still overwh...

From border controls to personal devices, from online exam proctoring to human-robot interaction, biometric technologies are empowering individuals and organizations with convenient and secure authentication and identification services. However, most biometric systems leverage only a single modality, and may face challenges related to acquisition d...

This book constitutes refereed proceedings of the First International Workshop on Algorithmic Bias in Search and Recommendation, BIAS 2020, held in April, 2020. Due to the COVID-19 pandemic BIAS 2020 was held virtually. The 10 full papers and 7 short papers were carefully reviewed and seleced from 44 submissions. The papers cover topics that go f...

In this paper, we assess vulnerability of speaker verification systems to dictionary attacks. We seek master voices, i.e., adversarial utterances optimized to match against a large number of users by pure chance. First, we perform menagerie analysis to identify utterances which intrinsically hold this property. Then, we propose an adversarial optim...

Social media are providing the humus for the sharing of knowledge and experiences and the growth of community activities (e.g., debating about different topics). The analysis of the user-generated content in this area usually relies on Sentiment Analysis. Word embeddings and Deep Learning have attracted extensive attention in various sentiment dete...

Most recommender systems are evaluated on how they accurately predict user ratings. However, individuals use them for more than an anticipation of their preferences. The literature demonstrated that some recommendation algorithms achieve good prediction accuracy, but suffer from popularity bias. Other algorithms generate an item category bias due t...

Nowadays, biometric recognition and verification methods are everywhere, trying to face the security issues that constantly affect our digital-every day life. In addition, many special-purpose applications, also need a constant (continuous) verification of the user in order to avoid that a sensitive operation is executed by an impostor; as an examp...