Vito Walter Anelli

Vito Walter Anelli, Daniele Malitesta, Claudio Pomo et al.

The success of graph neural network-based models (GNNs) has significantly advanced recommender systems by effectively modeling users and items as a bipartite, undirected graph. However, many original graph-based works often adopt results from baseline papers without verifying their validity for the specific configuration under analysis. Our work addresses this issue by focusing on the replicability of results. We present a code that successfully replicates results from six popular and recent graph recommendation models (NGCF, DGCF, LightGCN, SGL, UltraGCN, and GFCF) on three common benchmark datasets (Gowalla, Yelp 2018, and Amazon Book). Additionally, we compare these graph models with traditional collaborative filtering models that historically performed well in offline evaluations. Furthermore, we extend our study to two new datasets (Allrecipes and BookCrossing) that lack established setups in existing literature. As the performance on these datasets differs from the previous benchmarks, we analyze the impact of specific dataset characteristics on recommendation accuracy. By investigating the information flow from users' neighborhoods, we aim to identify which models are influenced by intrinsic features in the dataset structure. The code to reproduce our experiments is available at: https://github.com/sisinflab/Graph-RSs-Reproducibility.

Marco Avolio, Potito Aghilar, Sabino Roccotelli et al.

Innovation in Recommender Systems is currently impeded by a fractured ecosystem, where researchers must choose between the ease of in-memory experimentation and the costly, complex rewriting required for distributed industrial engines. To bridge this gap, we present WarpRec, a high-performance framework that eliminates this trade-off through a novel, backend-agnostic architecture. It includes 50+ state-of-the-art algorithms, 40 metrics, and 19 filtering and splitting strategies that seamlessly transition from local execution to distributed training and optimization. The framework enforces ecological responsibility by integrating CodeCarbon for real-time energy tracking, showing that scalability need not come at the cost of scientific integrity or sustainability. Furthermore, WarpRec anticipates the shift toward Agentic AI, leading Recommender Systems to evolve from static ranking engines into interactive tools within the Generative AI ecosystem. In summary, WarpRec not only bridges the gap between academia and industry but also can serve as the architectural backbone for the next generation of sustainable, agent-ready Recommender Systems. Code is available at https://github.com/sisinflab/warprec/

Dario Di Palma, Giovanni Maria Biancofiore, Vito Walter Anelli et al.

Large Language Models (LLMs) have recently shown impressive abilities in handling various natural language-related tasks. Among different LLMs, current studies have assessed ChatGPT's superior performance across manifold tasks, especially under the zero/few-shot prompting conditions. Given such successes, the Recommender Systems (RSs) research community have started investigating its potential applications within the recommendation scenario. However, although various methods have been proposed to integrate ChatGPT's capabilities into RSs, current research struggles to comprehensively evaluate such models while considering the peculiarities of generative models. Often, evaluations do not consider hallucinations, duplications, and out-of-the-closed domain recommendations and solely focus on accuracy metrics, neglecting the impact on beyond-accuracy facets. To bridge this gap, we propose a robust evaluation pipeline to assess ChatGPT's ability as an RS and post-process ChatGPT recommendations to account for these aspects. Through this pipeline, we investigate ChatGPT-3.5 and ChatGPT-4 performance in the recommendation task under the zero-shot condition employing the role-playing prompt. We analyze the model's functionality in three settings: the Top-N Recommendation, the cold-start recommendation, and the re-ranking of a list of recommendations, and in three domains: movies, music, and books. The experiments reveal that ChatGPT exhibits higher accuracy than the baselines on books domain. It also excels in re-ranking and cold-start scenarios while maintaining reasonable beyond-accuracy metrics. Furthermore, we measure the similarity between the ChatGPT recommendations and the other recommenders, providing insights about how ChatGPT could be categorized in the realm of recommender systems. The evaluation pipeline is publicly released for future research.

Vincenzo Paparella, Vito Walter Anelli, Franco Maria Nardini et al.

Information Retrieval (IR) and Recommender Systems (RS) tasks are moving from computing a ranking of final results based on a single metric to multi-objective problems. Solving these problems leads to a set of Pareto-optimal solutions, known as Pareto frontier, in which no objective can be further improved without hurting the others. In principle, all the points on the Pareto frontier are potential candidates to represent the best model selected with respect to the combination of two, or more, metrics. To our knowledge, there are no well-recognized strategies to decide which point should be selected on the frontier. In this paper, we propose a novel, post-hoc, theoretically-justified technique, named "Population Distance from Utopia" (PDU), to identify and select the one-best Pareto-optimal solution from the frontier. In detail, PDU analyzes the distribution of the points by investigating how far each point is from its utopia point (the ideal performance for the objectives). The possibility of considering fine-grained utopia points allows PDU to select solutions tailored to individual user preferences, a novel feature we call "calibration". We compare PDU against existing state-of-the-art strategies through extensive experiments on tasks from both IR and RS. Experimental results show that PDU and combined with calibration notably impact the solution selection. Furthermore, the results show that the proposed framework selects a solution in a principled way, irrespective of its position on the frontier, thus overcoming the limits of other strategies.

Giandomenico Cornacchia, Vito Walter Anelli, Fedelucio Narducci et al.

Current AI regulations require discarding sensitive features (e.g., gender, race, religion) in the algorithm's decision-making process to prevent unfair outcomes. However, even without sensitive features in the training set, algorithms can persist in discrimination. Indeed, when sensitive features are omitted (fairness under unawareness), they could be inferred through non-linear relations with the so called proxy features. In this work, we propose a way to reveal the potential hidden bias of a machine learning model that can persist even when sensitive features are discarded. This study shows that it is possible to unveil whether the black-box predictor is still biased by exploiting counterfactual reasoning. In detail, when the predictor provides a negative classification outcome, our approach first builds counterfactual examples for a discriminated user category to obtain a positive outcome. Then, the same counterfactual samples feed an external classifier (that targets a sensitive feature) that reveals whether the modifications to the user characteristics needed for a positive outcome moved the individual to the non-discriminated group. When this occurs, it could be a warning sign for discriminatory behavior in the decision process. Furthermore, we leverage the deviation of counterfactuals from the original sample to determine which features are proxies of specific sensitive information. Our experiments show that, even if the model is trained without sensitive features, it often suffers discriminatory biases.

Potito Aghilar, Vito Walter Anelli, Michelantonio Trizio et al.

In recent years, 3D models have gained popularity in various fields, including entertainment, manufacturing, and simulation. However, manually creating these models can be a time-consuming and resource-intensive process, making it impractical for large-scale industrial applications. To address this issue, researchers are exploiting Artificial Intelligence and Machine Learning algorithms to automatically generate 3D models effortlessly. In this paper, we present a novel cloud-native pipeline that can automatically reconstruct 3D models from monocular 2D images captured using a smartphone camera. Our goal is to provide an efficient and easily-adoptable solution that meets the Industry 4.0 standards for creating a Digital Twin model, which could enhance personnel expertise through accelerated training. We leverage machine learning models developed by NVIDIA Research Labs alongside a custom-designed pose recorder with a unique pose compensation component based on the ARCore framework by Google. Our solution produces a reusable 3D model, with embedded materials and textures, exportable and customizable in any external 3D modelling software or 3D engine. Furthermore, the whole workflow is implemented by adopting the microservices architecture standard, enabling each component of the pipeline to operate as a standalone replaceable module.

Gabriele Conte, Alessio Mattiace, Gianni Carmosino et al.

The Personal AI landscape is currently dominated by "Black Box" Retrieval-Augmented Generation. While standard vector databases offer statistical matching, they suffer from a fundamental lack of accountability: when an AI hallucinates or retrieves sensitive data, the user cannot inspect the cause nor correct the error. Worse, "deleting" a concept from a vector space is mathematically imprecise, leaving behind probabilistic "ghosts" that violate true privacy. We propose Ruva, the first "Glass Box" architecture designed for Human-in-the-Loop Memory Curation. Ruva grounds Personal AI in a Personal Knowledge Graph, enabling users to inspect what the AI knows and to perform precise redaction of specific facts. By shifting the paradigm from Vector Matching to Graph Reasoning, Ruva ensures the "Right to be Forgotten." Users are the editors of their own lives; Ruva hands them the pen. The project and the demo video are available at http://sisinf00.poliba.it/ruva/.

Dario Di Palma, Giovanni Maria Biancofiore, Vito Walter Anelli et al.

ChatGPT has emerged as a versatile tool, demonstrating capabilities across diverse domains. Given these successes, the Recommender Systems (RSs) community has begun investigating its applications within recommendation scenarios primarily focusing on accuracy. While the integration of ChatGPT into RSs has garnered significant attention, a comprehensive analysis of its performance across various dimensions remains largely unexplored. Specifically, the capabilities of providing diverse and novel recommendations or exploring potential biases such as popularity bias have not been thoroughly examined. As the use of these models continues to expand, understanding these aspects is crucial for enhancing user satisfaction and achieving long-term personalization. This study investigates the recommendations provided by ChatGPT-3.5 and ChatGPT-4 by assessing ChatGPT's capabilities in terms of diversity, novelty, and popularity bias. We evaluate these models on three distinct datasets and assess their performance in Top-N recommendation and cold-start scenarios. The findings reveal that ChatGPT-4 matches or surpasses traditional recommenders, demonstrating the ability to balance novelty and diversity in recommendations. Furthermore, in the cold-start scenario, ChatGPT models exhibit superior performance in both accuracy and novelty, suggesting they can be particularly beneficial for new users. This research highlights the strengths and limitations of ChatGPT's recommendations, offering new perspectives on the capacity of these models to provide recommendations beyond accuracy-focused metrics.

Giandomenico Cornacchia, Vito Walter Anelli, Fedelucio Narducci et al.

The increasing application of Artificial Intelligence and Machine Learning models poses potential risks of unfair behavior and, in light of recent regulations, has attracted the attention of the research community. Several researchers focused on seeking new fairness definitions or developing approaches to identify biased predictions. However, none try to exploit the counterfactual space to this aim. In that direction, the methodology proposed in this work aims to unveil unfair model behaviors using counterfactual reasoning in the case of fairness under unawareness setting. A counterfactual version of equal opportunity named counterfactual fair opportunity is defined and two novel metrics that analyze the sensitive information of counterfactual samples are introduced. Experimental results on three different datasets show the efficacy of our methodologies and our metrics, disclosing the unfair behavior of classic machine learning and debiasing models.

Dario Di Palma, Felice Antonio Merra, Maurizio Sfilio et al.

Large Language Models (LLMs) have become increasingly central to recommendation scenarios due to their remarkable natural language understanding and generation capabilities. Although significant research has explored the use of LLMs for various recommendation tasks, little effort has been dedicated to verifying whether they have memorized public recommendation dataset as part of their training data. This is undesirable because memorization reduces the generalizability of research findings, as benchmarking on memorized datasets does not guarantee generalization to unseen datasets. Furthermore, memorization can amplify biases, for example, some popular items may be recommended more frequently than others. In this work, we investigate whether LLMs have memorized public recommendation datasets. Specifically, we examine two model families (GPT and Llama) across multiple sizes, focusing on one of the most widely used dataset in recommender systems: MovieLens-1M. First, we define dataset memorization as the extent to which item attributes, user profiles, and user-item interactions can be retrieved by prompting the LLMs. Second, we analyze the impact of memorization on recommendation performance. Lastly, we examine whether memorization varies across model families and model sizes. Our results reveal that all models exhibit some degree of memorization of MovieLens-1M, and that recommendation performance is related to the extent of memorization. We have made all the code publicly available at: https://github.com/sisinflab/LLM-MemoryInspector

Giovanni Servedio, Alessandro De Bellis, Dario Di Palma et al.

Factual hallucinations are a major challenge for Large Language Models (LLMs). They undermine reliability and user trust by generating inaccurate or fabricated content. Recent studies suggest that when generating false statements, the internal states of LLMs encode information about truthfulness. However, these studies often rely on synthetic datasets that lack realism, which limits generalization when evaluating the factual accuracy of text generated by the model itself. In this paper, we challenge the findings of previous work by investigating truthfulness encoding capabilities, leading to the generation of a more realistic and challenging dataset. Specifically, we extend previous work by introducing: (1) a strategy for sampling plausible true-false factoid sentences from tabular data and (2) a procedure for generating realistic, LLM-dependent true-false datasets from Question Answering collections. Our analysis of two open-source LLMs reveals that while the findings from previous studies are partially validated, generalization to LLM-generated datasets remains challenging. This study lays the groundwork for future research on factuality in LLMs and offers practical guidelines for more effective evaluation.

Alessandro De Bellis, Salvatore Bufi, Giovanni Servedio et al.

Inductive link prediction is emerging as a key paradigm for real-world knowledge graphs (KGs), where new entities frequently appear and models must generalize to them without retraining. Predicting links in a KG faces the challenge of guessing previously unseen entities by leveraging generalizable node features such as subgraph structure, type annotations, and ontological constraints. However, explicit type information is often lacking or incomplete. Even when available, type information in most KGs is often coarse-grained, sparse, and prone to errors due to human annotation. In this work, we explore the potential of pre-trained language models (PLMs) to enrich node representations with implicit type signals. We introduce TyleR, a Type-less yet type-awaRe approach for subgraph-based inductive link prediction that leverages PLMs for semantic enrichment. Experiments on standard benchmarks demonstrate that TyleR outperforms state-of-the-art baselines in scenarios with scarce type annotations and sparse graph connectivity. To ensure reproducibility, we share our code at https://github.com/sisinflab/tyler .

Chiara Mallamaci, Aleksandr Vladimirovich Petrov, Alberto Carlo Maria Mancino et al.

In the realm of music recommendation, sequential recommenders have shown promise in capturing the dynamic nature of music consumption. A key characteristic of this domain is repetitive listening, where users frequently replay familiar tracks. To capture these repetition patterns, recent research has introduced Personalised Popularity Scores (PPS), which quantify user-specific preferences based on historical frequency. While PPS enhances relevance in recommendation, it often reinforces already-known content, limiting the system's ability to surface novel or serendipitous items - key elements for fostering long-term user engagement and satisfaction. To address this limitation, we build upon RecJPQ, a Transformer-based framework initially developed to improve scalability in large-item catalogues through sub-item decomposition. We repurpose RecJPQ's sub-item architecture to model personalised popularity at a finer granularity. This allows us to capture shared repetition patterns across sub-embeddings - latent structures not accessible through item-level popularity alone. We propose a novel integration of sub-ID-level personalised popularity within the RecJPQ framework, enabling explicit control over the trade-off between accuracy and personalised novelty. Our sub-ID-level PPS method (sPPS) consistently outperforms item-level PPS by achieving significantly higher personalised novelty without compromising recommendation accuracy. Code and experiments are publicly available at https://github.com/sisinflab/Sub-id-Popularity.

Vito Walter Anelli, Alejandro Bellogín, Tommaso Di Noia et al.

Collaborative filtering models based on matrix factorization and learned similarities using Artificial Neural Networks (ANNs) have gained significant attention in recent years. This is, in part, because ANNs have demonstrated good results in a wide variety of recommendation tasks. The introduction of ANNs within the recommendation ecosystem has been recently questioned, raising several comparisons in terms of efficiency and effectiveness. One aspect most of these comparisons have in common is their focus on accuracy, neglecting other evaluation dimensions important for the recommendation, such as novelty, diversity, or accounting for biases. We replicate experiments from three papers that compare Neural Collaborative Filtering (NCF) and Matrix Factorization (MF), to extend the analysis to other evaluation dimensions. Our contribution shows that the experiments are entirely reproducible, and we extend the study including other accuracy metrics and two statistical hypothesis tests. We investigated the Diversity and Novelty of the recommendations, showing that MF provides a better accuracy also on the long tail, although NCF provides a better item coverage and more diversified recommendations. We discuss the bias effect generated by the tested methods. They show a relatively small bias, but other recommendation baselines, with competitive accuracy performance, consistently show to be less affected by this issue. This is the first work, to the best of our knowledge, where several evaluation dimensions have been explored for an array of SOTA algorithms covering recent adaptations of ANNs and MF. Hence, we show the potential these techniques may have on beyond-accuracy evaluation while analyzing the effect on reproducibility these complementary dimensions may spark. Available at github.com/sisinflab/Reenvisioning-the-comparison-between-Neural-Collaborative-Filtering-and-Matrix-Factorization

Vito Walter Anelli, Alejandro Bellogín, Antonio Ferrara et al.

Recommender Systems have shown to be an effective way to alleviate the over-choice problem and provide accurate and tailored recommendations. However, the impressive number of proposed recommendation algorithms, splitting strategies, evaluation protocols, metrics, and tasks, has made rigorous experimental evaluation particularly challenging. Puzzled and frustrated by the continuous recreation of appropriate evaluation benchmarks, experimental pipelines, hyperparameter optimization, and evaluation procedures, we have developed an exhaustive framework to address such needs. Elliot is a comprehensive recommendation framework that aims to run and reproduce an entire experimental pipeline by processing a simple configuration file. The framework loads, filters, and splits the data considering a vast set of strategies (13 splitting methods and 8 filtering approaches, from temporal training-test splitting to nested K-folds Cross-Validation). Elliot optimizes hyperparameters (51 strategies) for several recommendation algorithms (50), selects the best models, compares them with the baselines providing intra-model statistics, computes metrics (36) spanning from accuracy to beyond-accuracy, bias, and fairness, and conducts statistical analysis (Wilcoxon and Paired t-test). The aim is to provide the researchers with a tool to ease (and make them reproducible) all the experimental evaluation phases, from data reading to results collection. Elliot is available on GitHub (https://github.com/sisinflab/elliot).

Vito Walter Anelli, Yashar Deldjoo, Tommaso Di Noia et al.

Recommendation services are extensively adopted in several user-centered applications as a tool to alleviate the information overload problem and help users in orienteering in a vast space of possible choices. In such scenarios, data ownership is a crucial concern since users may not be willing to share their sensitive preferences (e.g., visited locations) with a central server. Unfortunately, data harvesting and collection is at the basis of modern, state-of-the-art approaches to recommendation. To address this issue, we present FPL, an architecture in which users collaborate in training a central factorization model while controlling the amount of sensitive data leaving their devices. The proposed approach implements pair-wise learning-to-rank optimization by following the Federated Learning principles, originally conceived to mitigate the privacy risks of traditional machine learning. The public implementation is available at https://split.to/sisinflab-fpl.

Giovanni Servedio, Potito Aghilar, Alessio Mattiace et al.

Personal Artificial Intelligence is currently hindered by the fragmentation of user data across isolated silos. While Retrieval-Augmented Generation offers a partial remedy, its reliance on unstructured vector similarity fails to capture the latent semantic topology and temporal dependencies essential for holistic sensemaking. We introduce EpisTwin, a neuro-symbolic framework that grounds generative reasoning in a verifiable, user-centric Personal Knowledge Graph. EpisTwin leverages Multimodal Language Models to lift heterogeneous, cross-application data into semantic triples. At inference, EpisTwin enables complex reasoning over the personal semantic graph via an agentic coordinator that combines Graph Retrieval-Augmented Generation with Online Deep Visual Refinement, dynamically re-grounding symbolic entities in their raw visual context. We also introduce PersonalQA-71-100, a synthetic benchmark designed to simulate a realistic user's digital footprint and evaluate EpisTwin performance. Our framework demonstrates robust results across a suite of state-of-the-art judge models, offering a promising direction for trustworthy Personal AI.

Dario Di Palma, Alessandro De Bellis, Giovanni Servedio et al.

Large Language Models (LLMs) have rapidly become central to NLP, demonstrating their ability to adapt to various tasks through prompting techniques, including sentiment analysis. However, we still have a limited understanding of how these models capture sentiment-related information. This study probes the hidden layers of Llama models to pinpoint where sentiment features are most represented and to assess how this affects sentiment analysis. Using probe classifiers, we analyze sentiment encoding across layers and scales, identifying the layers and pooling methods that best capture sentiment signals. Our results show that sentiment information is most concentrated in mid-layers for binary polarity tasks, with detection accuracy increasing up to 14% over prompting techniques. Additionally, we find that in decoder-only models, the last token is not consistently the most informative for sentiment encoding. Finally, this approach enables sentiment tasks to be performed with memory requirements reduced by an average of 57%. These insights contribute to a broader understanding of sentiment in LLMs, suggesting layer-specific probing as an effective approach for sentiment tasks beyond prompting, with potential to enhance model utility and reduce memory requirements.

Potito Aghilar, Vito Walter Anelli, Michelantonio Trizio et al.

Recent advancements in diffusion models have significantly broadened the possibilities for editing images of real-world objects. However, performing non-rigid transformations, such as changing the pose of objects or image-based conditioning, remains challenging. Maintaining object identity during these edits is difficult, and current methods often fall short of the precision needed for industrial applications, where consistency is critical. Additionally, fine-tuning diffusion models requires custom training data, which is not always accessible in real-world scenarios. This work introduces FashionRepose, a training-free pipeline for non-rigid pose editing specifically designed for the fashion industry. The approach integrates off-the-shelf models to adjust poses of long-sleeve garments, maintaining identity and branding attributes. FashionRepose uses a zero-shot approach to perform these edits in near real-time, eliminating the need for specialized training. consistent image editing. The solution holds potential for applications in the fashion industry and other fields demanding identity preservation in image editing.

Vito Walter Anelli, Alejandro Bellogín, Tommaso Di Noia et al.

Explainable Recommendation has attracted a lot of attention due to a renewed interest in explainable artificial intelligence. In particular, post-hoc approaches have proved to be the most easily applicable ones to increasingly complex recommendation models, which are then treated as black-boxes. The most recent literature has shown that for post-hoc explanations based on local surrogate models, there are problems related to the robustness of the approach itself. This consideration becomes even more relevant in human-related tasks like recommendation. The explanation also has the arduous task of enhancing increasingly relevant aspects of user experience such as transparency or trustworthiness. This paper aims to show how the characteristics of a classical post-hoc model based on surrogates is strongly model-dependent and does not prove to be accountable for the explanations generated.

Vito Walter Anelli, Tommaso Di Noia, Eugenio Di Sciascio et al.

Deep Learning and factorization-based collaborative filtering recommendation models have undoubtedly dominated the scene of recommender systems in recent years. However, despite their outstanding performance, these methods require a training time proportional to the size of the embeddings and it further increases when also side information is considered for the computation of the recommendation list. In fact, in these cases we have that with a large number of high-quality features, the resulting models are more complex and difficult to train. This paper addresses this problem by presenting KGFlex: a sparse factorization approach that grants an even greater degree of expressiveness. To achieve this result, KGFlex analyzes the historical data to understand the dimensions the user decisions depend on (e.g., movie direction, musical genre, nationality of book writer). KGFlex represents each item feature as an embedding and it models user-item interactions as a factorized entropy-driven combination of the item attributes relevant to the user. KGFlex facilitates the training process by letting users update only those relevant features on which they base their decisions. In other words, the user-item prediction is mediated by the user's personal view that considers only relevant features. An extensive experimental evaluation shows the approach's effectiveness, considering the recommendation results' accuracy, diversity, and induced bias. The public implementation of KGFlex is available at https://split.to/kgflex.

Vito Walter Anelli, Yashar Deldjoo, Tommaso Di Noia et al.

Recommender systems (RSs) employ user-item feedback, e.g., ratings, to match customers to personalized lists of products. Approaches to top-k recommendation mainly rely on Learning-To-Rank algorithms and, among them, the most widely adopted is Bayesian Personalized Ranking (BPR), which bases on a pair-wise optimization approach. Recently, BPR has been found vulnerable against adversarial perturbations of its model parameters. Adversarial Personalized Ranking (APR) mitigates this issue by robustifying BPR via an adversarial training procedure. The empirical improvements of APR's accuracy performance on BPR have led to its wide use in several recommender models. However, a key overlooked aspect has been the beyond-accuracy performance of APR, i.e., novelty, coverage, and amplification of popularity bias, considering that recent results suggest that BPR, the building block of APR, is sensitive to the intensification of biases and reduction of recommendation novelty. In this work, we model the learning characteristics of the BPR and APR optimization frameworks to give mathematical evidence that, when the feedback data have a tailed distribution, APR amplifies the popularity bias more than BPR due to an unbalanced number of received positive updates from short-head items. Using matrix factorization (MF), we empirically validate the theoretical results by performing preliminary experiments on two public datasets to compare BPR-MF and APR-MF performance on accuracy and beyond-accuracy metrics. The experimental results consistently show the degradation of novelty and coverage measures and a worrying amplification of bias.

Vito Walter Anelli, Yashar Deldjoo, Tommaso Di Noia et al.

Recommender systems have shown to be a successful representative of how data availability can ease our everyday digital life. However, data privacy is one of the most prominent concerns in the digital era. After several data breaches and privacy scandals, the users are now worried about sharing their data. In the last decade, Federated Learning has emerged as a new privacy-preserving distributed machine learning paradigm. It works by processing data on the user device without collecting data in a central repository. We present FedeRank (https://split.to/federank), a federated recommendation algorithm. The system learns a personal factorization model onto every device. The training of the model is a synchronous process between the central server and the federated clients. FedeRank takes care of computing recommendations in a distributed fashion and allows users to control the portion of data they want to share. By comparing with state-of-the-art algorithms, extensive experiments show the effectiveness of FedeRank in terms of recommendation accuracy, even with a small portion of shared user data. Further analysis of the recommendation lists' diversity and novelty guarantees the suitability of the algorithm in real production environments.

Vito Walter Anelli, Alejandro Bellogín, Yashar Deldjoo et al.

Recommender systems (RSs) have attained exceptional performance in learning users' preferences and helping them in finding the most suitable products. Recent advances in adversarial machine learning (AML) in the computer vision domain have raised interests in the security of state-of-the-art model-based recommenders. Recently, worrying deterioration of recommendation accuracy has been acknowledged on several state-of-the-art model-based recommenders (e.g., BPR-MF) when machine-learned adversarial perturbations contaminate model parameters. However, while the single-step fast gradient sign method (FGSM) is the most explored perturbation strategy, multi-step (iterative) perturbation strategies, that demonstrated higher efficacy in the computer vision domain, have been highly under-researched in recommendation tasks. In this work, inspired by the basic iterative method (BIM) and the projected gradient descent (PGD) strategies proposed in the CV domain, we adapt the multi-step strategies for the item recommendation task to study the possible weaknesses of embedding-based recommender models under minimal adversarial perturbations. Letting the magnitude of the perturbation be fixed, we illustrate the highest efficacy of the multi-step perturbation compared to the single-step one with extensive empirical evaluation on two widely adopted recommender datasets. Furthermore, we study the impact of structural dataset characteristics, i.e., sparsity, density, and size, on the performance degradation issued by presented perturbations to support RS designer in interpreting recommendation performance variation due to minimal variations of model parameters. Our implementation and datasets are available at https://anonymous.4open.science/r/9f27f909-93d5-4016-b01c-8976b8c14bc5/.

Vito Walter Anelli, Tommaso Di Noia, Daniele Malitesta et al.

Visual-based recommender systems (VRSs) enhance recommendation performance by integrating users' feedback with the visual features of product images extracted from a deep neural network (DNN). Recently, human-imperceptible images perturbations, defined \textit{adversarial attacks}, have been demonstrated to alter the VRSs recommendation performance, e.g., pushing/nuking category of products. However, since adversarial training techniques have proven to successfully robustify DNNs in preserving classification accuracy, to the best of our knowledge, two important questions have not been investigated yet: 1) How well can these defensive mechanisms protect the VRSs performance? 2) What are the reasons behind ineffective/effective defenses? To answer these questions, we define a set of defense and attack settings, as well as recommender models, to empirically investigate the efficacy of defensive mechanisms. The results indicate alarming risks in protecting a VRS through the DNN robustification. Our experiments shed light on the importance of visual features in very effective attack scenarios. Given the financial impact of VRSs on many companies, we believe this work might rise the need to investigate how to successfully protect visual-based recommenders. Source code and data are available at https://anonymous.4open.science/r/868f87ca-c8a4-41ba-9af9-20c41de33029/.

Vito Walter Anelli, Yashar Deldjoo, Tommaso Di Noia et al.

In Machine Learning scenarios, privacy is a crucial concern when models have to be trained with private data coming from users of a service, such as a recommender system, a location-based mobile service, a mobile phone text messaging service providing next word prediction, or a face image classification system. The main issue is that, often, data are collected, transferred, and processed by third parties. These transactions violate new regulations, such as GDPR. Furthermore, users usually are not willing to share private data such as their visited locations, the text messages they wrote, or the photo they took with a third party. On the other hand, users appreciate services that work based on their behaviors and preferences. In order to address these issues, Federated Learning (FL) has been recently proposed as a means to build ML models based on private datasets distributed over a large number of clients, while preventing data leakage. A federation of users is asked to train a same global model on their private data, while a central coordinating server receives locally computed updates by clients and aggregate them to obtain a better global model, without the need to use clients' actual data. In this work, we extend the FL approach by pushing forward the state-of-the-art approaches in the aggregation step of FL, which we deem crucial for building a high-quality global model. Specifically, we propose an approach that takes into account a suite of client-specific criteria that constitute the basis for assigning a score to each client based on a priority of criteria defined by the service provider. Extensive experiments on two publicly available datasets indicate the merits of the proposed approach compared to standard FL baseline.

Vito Walter Anelli, Tommaso Di Noia, Eugenio Di Sciascio et al.

Model-based approaches to recommendation can recommend items with a very high level of accuracy. Unfortunately, even when the model embeds content-based information, if we move to a latent space we miss references to the actual semantics of recommended items. Consequently, this makes non-trivial the interpretation of a recommendation process. In this paper, we show how to initialize latent factors in Factorization Machines by using semantic features coming from a knowledge graph in order to train an interpretable model. With our model, semantic features are injected into the learning process to retain the original informativeness of the items available in the dataset. The accuracy and effectiveness of the trained model have been tested using two well-known recommender systems datasets. By relying on the information encoded in the original knowledge graph, we have also evaluated the semantic accuracy and robustness for the knowledge-aware interpretability of the final model.

Vito Walter Anelli, Tommaso Di Noia, Eugenio Di Sciascio et al.

Hyper-parameters tuning is a crucial task to make a model perform at its best. However, despite the well-established methodologies, some aspects of the tuning remain unexplored. As an example, it may affect not just accuracy but also novelty as well as it may depend on the adopted dataset. Moreover, sometimes it could be sufficient to concentrate on a single parameter only (or a few of them) instead of their overall set. In this paper we report on our investigation on hyper-parameters tuning by performing an extensive 10-Folds Cross-Validation on MovieLens and Amazon Movies for three well-known baselines: User-kNN, Item-kNN, BPR-MF. We adopted a grid search strategy considering approximately 15 values for each parameter, and we then evaluated each combination of parameters in terms of accuracy and novelty. We investigated the discriminative power of nDCG, Precision, Recall, MRR, EFD, EPC, and, finally, we analyzed the role of parameters on model evaluation for Cross-Validation.

Vito Walter Anelli, Yashar Deldjoo, Tommaso Di Noia et al.

With the wealth of information produced by social networks, smartphones, medical or financial applications, speculations have been raised about the sensitivity of such data in terms of users' personal privacy and data security. To address the above issues, Federated Learning (FL) has been recently proposed as a means to leave data and computational resources distributed over a large number of nodes (clients) where a central coordinating server aggregates only locally computed updates without knowing the original data. In this work, we extend the FL framework by pushing forward the state the art in the field on several dimensions: (i) unlike the original FedAvg approach relying solely on single criteria (i.e., local dataset size), a suite of domain- and client-specific criteria constitute the basis to compute each local client's contribution, (ii) the multi-criteria contribution of each device is computed in a prioritized fashion by leveraging a priority-aware aggregation operator used in the field of information retrieval, and (iii) a mechanism is proposed for online-adjustment of the aggregation operator parameters via a local search strategy with backtracking. Extensive experiments on a publicly available dataset indicate the merits of the proposed approach compared to standard FedAvg baseline.

Yashar Deldjoo, Vito Walter Anelli, Hamed Zamani et al.

Fairness in recommender systems has been considered with respect to sensitive attributes of users (e.g., gender, race) or items (e.g., revenue in a multistakeholder setting). Regardless, the concept has been commonly interpreted as some form of equality -- i.e., the degree to which the system is meeting the information needs of all its users in an equal sense. In this paper, we argue that fairness in recommender systems does not necessarily imply equality, but instead it should consider a distribution of resources based on merits and needs. We present a probabilistic framework based on generalized cross entropy to evaluate fairness of recommender systems under this perspective, where we show that the proposed framework is flexible and explanatory by allowing to incorporate domain knowledge (through an ideal fair distribution) that can help to understand which item or user aspects a recommendation algorithm is over- or under-representing. Results on two real-world datasets show the merits of the proposed evaluation framework both in terms of user and item fairness.

Vito Walter Anelli, Joseph Trotta, Tommaso Di Noia et al.

Similarity measures play a fundamental role in memory-based nearest neighbors approaches. They recommend items to a user based on the similarity of either items or users in a neighborhood. In this paper we argue that, although it keeps a leading importance in computing recommendations, similarity between users or items should be paired with a value of dissimilarity (computed not just as the complement of the similarity one). We formally modeled and injected this notion in some of the most used similarity measures and evaluated our approach showing its effectiveness in terms of accuracy results.

Vito Walter Anelli, Tommaso Di Noia, Eugenio Di Sciascio et al.

Items popularity is a strong signal in recommendation algorithms. It strongly affects collaborative filtering approaches and it has been proven to be a very good baseline in terms of results accuracy. Even though we miss an actual personalization, global popularity can be effectively used to recommend items to users. In this paper we introduce the idea of a time-aware personalized popularity in recommender systems by considering both items popularity among neighbors and how it changes over time. An experimental evaluation shows a highly competitive behavior of the proposed approach, compared to state of the art model-based collaborative approaches, in terms of results accuracy.

Vito Bellini, Vito Walter Anelli, Tommaso Di Noia et al.

In the last decade, driven also by the availability of an unprecedented computational power and storage capabilities in cloud environments we assisted to the proliferation of new algorithms, methods, and approaches in two areas of artificial intelligence: knowledge representation and machine learning. On the one side, the generation of a high rate of structured data on the Web led to the creation and publication of the so-called knowledge graphs. On the other side, deep learning emerged as one of the most promising approaches in the generation and training of models that can be applied to a wide variety of application fields. More recently, autoencoders have proven their strength in various scenarios, playing a fundamental role in unsupervised learning. In this paper, we instigate how to exploit the semantic information encoded in a knowledge graph to build connections between units in a Neural Network, thus leading to a new method, SEM-AUTO, to extract and weigh semantic features that can eventually be used to build a recommender system. As adding content-based side information may mitigate the cold user problems, we tested how our approach behave in the presence of a few rating from a user on the Movielens 1M dataset and compare results with BPRSLIM.