Paolo Cremonesi

Maurizio Ferrari Dacrema, Fabio Moroni, Riccardo Nembrini et al.

Feature selection is a common step in many ranking, classification, or prediction tasks and serves many purposes. By removing redundant or noisy features, the accuracy of ranking or classification can be improved and the computational cost of the subsequent learning steps can be reduced. However, feature selection can be itself a computationally expensive process. While for decades confined to theoretical algorithmic papers, quantum computing is now becoming a viable tool to tackle realistic problems, in particular special-purpose solvers based on the Quantum Annealing paradigm. This paper aims to explore the feasibility of using currently available quantum computing architectures to solve some quadratic feature selection algorithms for both ranking and classification. The experimental analysis includes 15 state-of-the-art datasets. The effectiveness obtained with quantum computing hardware is comparable to that of classical solvers, indicating that quantum computers are now reliable enough to tackle interesting problems. In terms of scalability, current generation quantum computers are able to provide a limited speedup over certain classical algorithms and hybrid quantum-classical strategies show lower computational cost for problems of more than a thousand features.

Gloria Turati, Maurizio Ferrari Dacrema, Paolo Cremonesi

Feature selection is of great importance in Machine Learning, where it can be used to reduce the dimensionality of classification, ranking and prediction problems. The removal of redundant and noisy features can improve both the accuracy and scalability of the trained models. However, feature selection is a computationally expensive task with a solution space that grows combinatorically. In this work, we consider in particular a quadratic feature selection problem that can be tackled with the Quantum Approximate Optimization Algorithm (QAOA), already employed in combinatorial optimization. First we represent the feature selection problem with the QUBO formulation, which is then mapped to an Ising spin Hamiltonian. Then we apply QAOA with the goal of finding the ground state of this Hamiltonian, which corresponds to the optimal selection of features. In our experiments, we consider seven different real-world datasets with dimensionality up to 21 and run QAOA on both a quantum simulator and, for small datasets, the 7-qubit IBM (ibm-perth) quantum computer. We use the set of selected features to train a classification model and evaluate its accuracy. Our analysis shows that it is possible to tackle the feature selection problem with QAOA and that currently available quantum devices can be used effectively. Future studies could test a wider range of classification models as well as improve the effectiveness of QAOA by exploring better performing optimizers for its classical step.

Fernando B. Pérez Maurera, Maurizio Ferrari Dacrema, Pablo Castells et al.

Novel data sources bring new opportunities to improve the quality of recommender systems and serve as a catalyst for the creation of new paradigms on personalized recommendations. Impressions are a novel data source containing the items shown to users on their screens. Past research focused on providing personalized recommendations using interactions, and occasionally using impressions when such a data source was available. Interest in impressions has increased due to their potential to provide more accurate recommendations. Despite this increased interest, research in recommender systems using impressions is still dispersed. Many works have distinct interpretations of impressions and use impressions in recommender systems in numerous different manners. To unify those interpretations into a single framework, we present a systematic literature review on recommender systems using impressions, focusing on three fundamental perspectives: recommendation models, datasets, and evaluation methodologies. We define a theoretical framework to delimit recommender systems using impressions and a novel paradigm for personalized recommendations, called impression-aware recommender systems. We propose a classification system for recommenders in this paradigm, which we use to categorize the recommendation models, datasets, and evaluation methodologies used in past research. Lastly, we identify open questions and future directions, highlighting missing aspects in the reviewed literature.

Gloria Turati, Maurizio Ferrari Dacrema, Paolo Cremonesi

In recent years, Variational Quantum Algorithms (VQAs) have emerged as a promising approach for solving optimization problems on quantum computers in the NISQ era. However, one limitation of VQAs is their reliance on fixed-structure circuits, which may not be taylored for specific problems or hardware configurations. A leading strategy to address this issue are Adaptative VQAs, which dynamically modify the circuit structure by adding and removing gates, and optimize their parameters during the training. Several Adaptative VQAs, based on heuristics such as circuit shallowness, entanglement capability and hardware compatibility, have already been proposed in the literature, but there is still lack of a systematic comparison between the different methods. In this paper, we aim to fill this gap by analyzing three Adaptative VQAs: Evolutionary Variational Quantum Eigensolver (EVQE), Variable Ansatz (VAns), already proposed in the literature, and Random Adapt-VQE (RA-VQE), a random approach we introduce as a baseline. In order to compare these algorithms to traditional VQAs, we also include the Quantum Approximate Optimization Algorithm (QAOA) in our analysis. We apply these algorithms to QUBO problems and study their performance by examining the quality of the solutions found and the computational times required. Additionally, we investigate how the choice of the hyperparameters can impact the overall performance of the algorithms, highlighting the importance of selecting an appropriate methodology for hyperparameter tuning. Our analysis sets benchmarks for Adaptative VQAs designed for near-term quantum devices and provides valuable insights to guide future research in this area.

Simone Foderà, Gloria Turati, Riccardo Nembrini et al.

Variational Quantum Algorithms have emerged as promising tools for solving optimization problems on quantum computers. These algorithms leverage a parametric quantum circuit called ansatz, where its parameters are adjusted by a classical optimizer with the goal of optimizing a certain cost function. However, a significant challenge lies in designing effective circuits for addressing specific problems. In this study, we leverage the powerful and flexible Reinforcement Learning paradigm to train an agent capable of autonomously generating quantum circuits that can be used as ansatzes in variational algorithms to solve optimization problems. The agent is trained on diverse problem instances, including Maximum Cut, Maximum Clique and Minimum Vertex Cover, built from different graph topologies and sizes. Our analysis of the circuits generated by the agent and the corresponding solutions shows that the proposed method is able to generate effective ansatzes. While our goal is not to propose any new specific ansatz, we observe how the agent has discovered a novel family of ansatzes effective for Maximum Cut problems, which we call $R_{yz}$-connected. We study the characteristics of one of these ansatzes by comparing it against state-of-the-art quantum algorithms across instances of varying graph topologies, sizes, and problem types. Our results indicate that the $R_{yz}$-connected circuit achieves high approximation ratios for Maximum Cut problems, further validating our proposed agent. In conclusion, our study highlights the potential of Reinforcement Learning techniques in assisting researchers to design effective quantum circuits which could have applications in a wide number of tasks.

Costantino Carugno, Maurizio Ferrari Dacrema, Paolo Cremonesi

The recent availability of quantum annealers as cloud-based services has enabled new ways to handle machine learning problems, and several relevant algorithms have been adapted to run on these devices. In a recent work, linear regression was formulated as a quadratic binary optimization problem that can be solved via quantum annealing. Although this approach promises a computational time advantage for large datasets, the quality of the solution is limited by the necessary use of a precision vector, used to approximate the real-numbered regression coefficients in the quantum formulation. In this work, we focus on the practical challenge of improving the precision vector encoding: instead of setting an array of generic values equal for all coefficients, we allow each one to be expressed by its specific precision, which is tuned with a simple adaptive algorithm. This approach is evaluated on synthetic datasets of increasing size, and linear regression is solved using the D-Wave Advantage quantum annealer, as well as classical solvers. To the best of our knowledge, this is the largest dataset ever evaluated for linear regression on a quantum annealer. The results show that our formulation is able to deliver improved solution quality in all instances, and could better exploit the potential of current quantum devices.

Fernando Benjamín Pérez Maurera, Maurizio Ferrari Dacrema, Lorenzo Saule et al.

In this article, we introduce the ContentWise Impressions dataset, a collection of implicit interactions and impressions of movies and TV series from an Over-The-Top media service, which delivers its media contents over the Internet. The dataset is distinguished from other already available multimedia recommendation datasets by the availability of impressions, i.e., the recommendations shown to the user, its size, and by being open-source. We describe the data collection process, the preprocessing applied, its characteristics, and statistics when compared to other commonly used datasets. We also highlight several possible use cases and research questions that can benefit from the availability of user impressions in an open-source dataset. Furthermore, we release software tools to load and split the data, as well as examples of how to use both user interactions and impressions in several common recommendation algorithms.

Maurizio Ferrari Dacrema, Paolo Cremonesi, Dietmar Jannach

Deep learning techniques have become the method of choice for researchers working on algorithmic aspects of recommender systems. With the strongly increased interest in machine learning in general, it has, as a result, become difficult to keep track of what represents the state-of-the-art at the moment, e.g., for top-n recommendation tasks. At the same time, several recent publications point out problems in today's research practice in applied machine learning, e.g., in terms of the reproducibility of the results or the choice of the baselines when proposing new models. In this work, we report the results of a systematic analysis of algorithmic proposals for top-n recommendation tasks. Specifically, we considered 18 algorithms that were presented at top-level research conferences in the last years. Only 7 of them could be reproduced with reasonable effort. For these methods, it however turned out that 6 of them can often be outperformed with comparably simple heuristic methods, e.g., based on nearest-neighbor or graph-based techniques. The remaining one clearly outperformed the baselines but did not consistently outperform a well-tuned non-neural linear ranking method. Overall, our work sheds light on a number of potential problems in today's machine learning scholarship and calls for improved scientific practices in this area. Source code of our experiments and full results are available at: https://github.com/MaurizioFD/RecSys2019_DeepLearning_Evaluation.

Riccardo Nembrini, Maurizio Ferrari Dacrema, Paolo Cremonesi

Quantum Annealing (QA) is a quantum computing paradigm for solving combinatorial optimization problems formulated as Quadratic Unconstrained Binary Optimization (QUBO) problems. An essential step in QA is minor embedding, which maps the problem graph onto the sparse topology of the quantum processor. This process is computationally expensive and scales poorly with increasing problem size and hardware complexity. Existing heuristics are often developed for specific problem graphs or hardware topologies and are difficult to generalize. Reinforcement Learning (RL) offers a promising alternative by treating minor embedding as a sequential decision-making problem, where an agent learns to construct minor embeddings by iteratively mapping the problem variables to the hardware qubits. We propose a RL-based approach to minor embedding using a Proximal Policy Optimization agent, testing its ability to embed both fully connected and randomly generated problem graphs on two hardware topologies, Chimera and Zephyr. The results show that our agent consistently produces valid minor embeddings, with reasonably efficient number of qubits, in particular on the more modern Zephyr topology. Our proposed approach is also able to scale to moderate problem sizes and adapts well to different graph structures, highlighting RL's potential as a flexible and general-purpose framework for minor embedding in QA.

Gloria Turati, Simone Foderà, Riccardo Nembrini et al.

Variational Quantum Algorithms (VQAs) are among the most promising approaches for leveraging near-term quantum hardware, yet their effectiveness strongly depends on the design of the underlying circuit ansatz, which is typically constructed with heuristic methods. In this work, we represent the synthesis of variational quantum circuits as a sequential decision-making problem, where gates are added iteratively in order to optimize an objective function, and we introduce two reinforcement learning-based methods, RLVQC Global and RLVQC Block, tailored to combinatorial optimization problems. RLVQC Block creates ansatzes that generalize the Quantum Approximate Optimization Algorithm (QAOA), by discovering a two-qubits block that is applied to all the interacting qubit pairs. While RLVQC Global further generalizes the ansatz and adds gates unconstrained by the structure of the interacting qubits. Both methods adopt the Proximal Policy Optimization (PPO) algorithm and use empirical measurement outcomes as state observations to guide the agent. We evaluate the proposed methods on a broad set of QUBO instances derived from classical graph-based optimization problems. Our results show that both RLVQC methods exhibit strong results with RLVQC Block consistently outperforming QAOA and generally surpassing RLVQC Global. While RLVQC Block produces circuits with depth comparable to QAOA, the Global variant is instead able to find significantly shorter ones. These findings suggest that reinforcement learning methods can be an effective tool to discover new ansatz structures tailored for specific problems and that the most effective circuit design strategy lies between rigid predefined architectures and completely unconstrained ones, offering a favourable trade-off between structure and adaptability.

Ervin Dervishaj, Paolo Cremonesi

Proposed in 2014, Generative Adversarial Networks (GAN) initiated a fresh interest in generative modelling. They immediately achieved state-of-the-art in image synthesis, image-to-image translation, text-to-image generation, image inpainting and have been used in sciences ranging from medicine to high-energy particle physics. Despite their popularity and ability to learn arbitrary distributions, GAN have not been widely applied in recommender systems (RS). Moreover, only few of the techniques that have introduced GAN in RS have employed them directly as a collaborative filtering (CF) model. In this work we propose a new GAN-based approach that learns user and item latent factors in a matrix factorization setting for the generic top-N recommendation problem. Following the vector-wise GAN training approach for RS introduced by CFGAN, we identify 2 unique issues when utilizing GAN for CF. We propose solutions for both of them by using an autoencoder as discriminator and incorporating an additional loss function for the generator. We evaluate our model, GANMF, through well-known datasets in the RS community and show improvements over traditional CF approaches and GAN-based models. Through an ablation study on the components of GANMF we aim to understand the effects of our architectural choices. Finally, we provide a qualitative evaluation of the matrix factorization performance of GANMF.

Fernando Benjamín Pérez Maurera, Maurizio Ferrari Dacrema, Paolo Cremonesi

This work explores the reproducibility of CFGAN. CFGAN and its family of models (TagRec, MTPR, and CRGAN) learn to generate personalized and fake-but-realistic rankings of preferences for top-N recommendations by using previous interactions. This work successfully replicates the results published in the original paper and discusses the impact of certain differences between the CFGAN framework and the model used in the original evaluation. The absence of random noise and the use of real user profiles as condition vectors leaves the generator prone to learn a degenerate solution in which the output vector is identical to the input vector, therefore, behaving essentially as a simple autoencoder. The work further expands the experimental analysis comparing CFGAN against a selection of simple and well-known properly optimized baselines, observing that CFGAN is not consistently competitive against them despite its high computational cost. To ensure the reproducibility of these analyses, this work describes the experimental methodology and publishes all datasets and source code.

Riccardo Nembrini, Maurizio Ferrari Dacrema, Paolo Cremonesi

The promise of quantum computing to open new unexplored possibilities in several scientific fields has been long discussed, but until recently the lack of a functional quantum computer has confined this discussion mostly to theoretical algorithmic papers. It was only in the last few years that small but functional quantum computers have become available to the broader research community. One paradigm in particular, quantum annealing, can be used to sample optimal solutions for a number of NP-hard optimization problems represented with classical operations research tools, providing an easy access to the potential of this emerging technology. One of the tasks that most naturally fits in this mathematical formulation is feature selection. In this paper, we investigate how to design a hybrid feature selection algorithm for recommender systems that leverages the domain knowledge and behavior hidden in the user interactions data. We represent the feature selection as an optimization problem and solve it on a real quantum computer, provided by D-Wave. The results indicate that the proposed approach is effective in selecting a limited set of important features and that quantum computers are becoming powerful enough to enter the wider realm of applied science.

Nicolò Felicioni, Maurizio Ferrari Dacrema, Paolo Cremonesi

It is common for video-on-demand and music streaming services to adopt a user interface composed of several recommendation lists, i.e. widgets or swipeable carousels, each generated according to a specific criterion or algorithm (e.g. most recent, top popular, recommended for you, editors' choice, etc.). Selecting the appropriate combination of carousel has significant impact on user satisfaction. A crucial aspect of this user interface is that to measure the relevance a new carousel for the user it is not sufficient to account solely for its individual quality. Instead, it should be considered that other carousels will already be present in the interface. This is not considered by traditional evaluation protocols for recommenders systems, in which each carousel is evaluated in isolation, regardless of (i) which other carousels are displayed to the user and (ii) the relative position of the carousel with respect to other carousels. Hence, we propose a two-dimensional evaluation protocol for a carousel setting that will measure the quality of a recommendation carousel based on how much it improves upon the quality of an already available set of carousels. Our evaluation protocol takes into account also the position bias, i.e. users do not explore the carousels sequentially, but rather concentrate on the top-left corner of the screen. We report experiments on the movie domain and notice that under a carousel setting the definition of which criteria has to be preferred to generate a list of recommended items changes with respect to what is commonly understood.

Nicolò Felicioni, Maurizio Ferrari Dacrema, Paolo Cremonesi

Many video-on-demand and music streaming services provide the user with a page consisting of several recommendation lists, i.e. widgets or swipeable carousels, each built with a specific criterion (e.g. most recent, TV series, etc.). Finding efficient strategies to select which carousels to display is an active research topic of great industrial interest. In this setting, the overall quality of the recommendations of a new algorithm cannot be assessed by measuring solely its individual recommendation quality. Rather, it should be evaluated in a context where other recommendation lists are already available, to account for how they complement each other. This is not considered by traditional offline evaluation protocols. Hence, we propose an offline evaluation protocol for a carousel setting in which the recommendation quality of a model is measured by how much it improves upon that of an already available set of carousels. We report experiments on publicly available datasets on the movie domain and notice that under a carousel setting the ranking of the algorithms change. In particular, when a SLIM carousel is available, matrix factorization models tend to be preferred, while item-based models are penalized. We also propose to extend ranking metrics to the two-dimensional carousel layout in order to account for a known position bias, i.e. users will not explore the lists sequentially, but rather concentrate on the top-left corner of the screen.

Giovanni Gabbolini, Edoardo D'Amico, Cesare Bernardis et al.

Most state-of-the-art top-N collaborative recommender systems work by learning embeddings to jointly represent users and items. Learned embeddings are considered to be effective to solve a variety of tasks. Among others, providing and explaining recommendations. In this paper we question the reliability of the embeddings learned by Matrix Factorization (MF). We empirically demonstrate that, by simply changing the initial values assigned to the latent factors, the same MF method generates very different embeddings of items and users, and we highlight that this effect is stronger for less popular items. To overcome these drawbacks, we present a generalization of MF, called Nearest Neighbors Matrix Factorization (NNMF). The new method propagates the information about items and users to their neighbors, speeding up the training procedure and extending the amount of information that supports recommendations and representations. We describe the NNMF variants of three common MF approaches, and with extensive experiments on five different datasets we show that they strongly mitigate the instability issues of the original MF versions and they improve the accuracy of recommendations on the long-tail.

Maurizio Ferrari Dacrema, Federico Parroni, Paolo Cremonesi et al.

In recent years, algorithm research in the area of recommender systems has shifted from matrix factorization techniques and their latent factor models to neural approaches. However, given the proven power of latent factor models, some newer neural approaches incorporate them within more complex network architectures. One specific idea, recently put forward by several researchers, is to consider potential correlations between the latent factors, i.e., embeddings, by applying convolutions over the user-item interaction map. However, contrary to what is claimed in these articles, such interaction maps do not share the properties of images where Convolutional Neural Networks (CNNs) are particularly useful. In this work, we show through analytical considerations and empirical evaluations that the claimed gains reported in the literature cannot be attributed to the ability of CNNs to model embedding correlations, as argued in the original papers. Moreover, additional performance evaluations show that all of the examined recent CNN-based models are outperformed by existing non-neural machine learning techniques or traditional nearest-neighbor approaches. On a more general level, our work points to major methodological issues in recommender systems research.

Luca Benedetto, Andrea Cappelli, Roberto Turrin et al.

Statistical models such as those derived from Item Response Theory (IRT) enable the assessment of students on a specific subject, which can be useful for several purposes (e.g., learning path customization, drop-out prediction). However, the questions have to be assessed as well and, although it is possible to estimate with IRT the characteristics of questions that have already been answered by several students, this technique cannot be used on newly generated questions. In this paper, we propose a framework to train and evaluate models for estimating the difficulty and discrimination of newly created Multiple Choice Questions by extracting meaningful features from the text of the question and of the possible choices. We implement one model using this framework and test it on a real-world dataset provided by CloudAcademy, showing that it outperforms previously proposed models, reducing by 6.7% the RMSE for difficulty estimation and by 10.8% the RMSE for discrimination estimation. We also present the results of an ablation study performed to support our features choice and to show the effects of different characteristics of the questions' text on difficulty and discrimination.

Luca Benedetto, Andrea Cappelli, Roberto Turrin et al.

The main objective of exams consists in performing an assessment of students' expertise on a specific subject. Such expertise, also referred to as skill or knowledge level, can then be leveraged in different ways (e.g., to assign a grade to the students, to understand whether a student might need some support, etc.). Similarly, the questions appearing in the exams have to be assessed in some way before being used to evaluate students. Standard approaches to questions' assessment are either subjective (e.g., assessment by human experts) or introduce a long delay in the process of question generation (e.g., pretesting with real students). In this work we introduce R2DE (which is a Regressor for Difficulty and Discrimination Estimation), a model capable of assessing newly generated multiple-choice questions by looking at the text of the question and the text of the possible choices. In particular, it can estimate the difficulty and the discrimination of each question, as they are defined in Item Response Theory. We also present the results of extensive experiments we carried out on a real world large scale dataset coming from an e-learning platform, showing that our model can be used to perform an initial assessment of newly created questions and ease some of the problems that arise in question generation.

Maurizio Ferrari Dacrema, Simone Boglio, Paolo Cremonesi et al.

The design of algorithms that generate personalized ranked item lists is a central topic of research in the field of recommender systems. In the past few years, in particular, approaches based on deep learning (neural) techniques have become dominant in the literature. For all of them, substantial progress over the state-of-the-art is claimed. However, indications exist of certain problems in today's research practice, e.g., with respect to the choice and optimization of the baselines used for comparison, raising questions about the published claims. In order to obtain a better understanding of the actual progress, we have tried to reproduce recent results in the area of neural recommendation approaches based on collaborative filtering. The worrying outcome of the analysis of these recent works-all were published at prestigious scientific conferences between 2015 and 2018-is that 11 out of the 12 reproducible neural approaches can be outperformed by conceptually simple methods, e.g., based on the nearest-neighbor heuristics. None of the computationally complex neural methods was actually consistently better than already existing learning-based techniques, e.g., using matrix factorization or linear models. In our analysis, we discuss common issues in today's research practice, which, despite the many papers that are published on the topic, have apparently led the field to a certain level of stagnation.

Luca Luciano Costanzo, Yashar Deldjoo, Maurizio Ferrari Dacrema et al.

In order to improve the accuracy of recommendations, many recommender systems nowadays use side information beyond the user rating matrix, such as item content. These systems build user profiles as estimates of users' interest on content (e.g., movie genre, director or cast) and then evaluate the performance of the recommender system as a whole e.g., by their ability to recommend relevant and novel items to the target user. The user profile modelling stage, which is a key stage in content-driven RS is barely properly evaluated due to the lack of publicly available datasets that contain user preferences on content features of items. To raise awareness of this fact, we investigate differences between explicit user preferences and implicit user profiles. We create a dataset of explicit preferences towards content features of movies, which we release publicly. We then compare the collected explicit user feature preferences and implicit user profiles built via state-of-the-art user profiling models. Our results show a maximum average pairwise cosine similarity of 58.07\% between the explicit feature preferences and the implicit user profiles modelled by the best investigated profiling method and considering movies' genres only. For actors and directors, this maximum similarity is only 9.13\% and 17.24\%, respectively. This low similarity between explicit and implicit preference models encourages a more in-depth study to investigate and improve this important user profile modelling step, which will eventually translate into better recommendations.

Luca Benedetto, Paolo Cremonesi, Manuel Parenti

In this extended abstract, we propose an intelligent system that can be used as a Personalized Virtual Teaching Assistant (PVTA) to improve the students learning experience both for online and on-site courses. We show the architecture of such system, which is composed of an instance of IBM Watson Assistant and a server, and present an initial implementation, consisting in a chatbot that can be questioned about the content and the organization of the RecSys course, an introductory course on recommender systems.

Maurizio Ferrari Dacrema, Alberto Gasparin, Paolo Cremonesi

An Item based recommender system works by computing a similarity between items, which can exploit past user interactions (collaborative filtering) or item features (content based filtering). Collaborative algorithms have been proven to achieve better recommendation quality then content based algorithms in a variety of scenarios, being more effective in modeling user behaviour. However, they can not be applied when items have no interactions at all, i.e. cold start items. Content based algorithms, which are applicable to cold start items, often require a lot of feature engineering in order to generate useful recommendations. This issue is specifically relevant as the content descriptors become large and heterogeneous. The focus of this paper is on how to use a collaborative models domain-specific knowledge to build a wrapper feature weighting method which embeds collaborative knowledge in a content based algorithm. We present a comparative study for different state of the art algorithms and present a more general model. This machine learning approach to feature weighting shows promising results and high flexibility.

Cesare Bernardis, Maurizio Ferrari Dacrema, Paolo Cremonesi

Cold-start is a very common and still open problem in the Recommender Systems literature. Since cold start items do not have any interaction, collaborative algorithms are not applicable. One of the main strategies is to use pure or hybrid content-based approaches, which usually yield to lower recommendation quality than collaborative ones. Some techniques to optimize performance of this type of approaches have been studied in recent past. One of them is called feature weighting, which assigns to every feature a real value, called weight, that estimates its importance. Statistical techniques for feature weighting commonly used in Information Retrieval, like TF-IDF, have been adapted for Recommender Systems, but they often do not provide sufficient quality improvements. More recent approaches, FBSM and LFW, estimate weights by leveraging collaborative information via machine learning, in order to learn the importance of a feature based on other users opinions. This type of models have shown promising results compared to classic statistical analyzes cited previously. We propose a novel graph, feature-based machine learning model to face the cold-start item scenario, learning the relevance of features from probabilities of item-based collaborative filtering algorithms.

Maurizio Ferrari Dacrema, Paolo Cremonesi

Item-item collaborative filtering (CF) models are a well known and studied family of recommender systems, however current literature does not provide any theoretical explanation of the conditions under which item-based recommendations will succeed or fail. We investigate the existence of an ideal item-based CF method able to make perfect recommendations. This CF model is formalized as an eigenvalue problem, where estimated ratings are equivalent to the true (unknown) ratings multiplied by a user-specific eigenvalue of the similarity matrix. Preliminary experiments show that the magnitude of the eigenvalue is proportional to the accuracy of recommendations for that user and therefore it can provide reliable measure of confidence.

Massimo Quadrana, Paolo Cremonesi, Dietmar Jannach

Recommender systems are one of the most successful applications of data mining and machine learning technology in practice. Academic research in the field is historically often based on the matrix completion problem formulation, where for each user-item-pair only one interaction (e.g., a rating) is considered. In many application domains, however, multiple user-item interactions of different types can be recorded over time. And, a number of recent works have shown that this information can be used to build richer individual user models and to discover additional behavioral patterns that can be leveraged in the recommendation process. In this work we review existing works that consider information from such sequentially-ordered user- item interaction logs in the recommendation process. Based on this review, we propose a categorization of the corresponding recommendation tasks and goals, summarize existing algorithmic solutions, discuss methodological approaches when benchmarking what we call sequence-aware recommender systems, and outline open challenges in the area.

Paolo Cremonesi, Chiara Francalanci, Alessandro Poli et al.

This paper proposes a novel adaptive algorithm for the automated short-term trading of financial instrument. The algorithm adopts a semantic sentiment analysis technique to inspect the Twitter posts and to use them to predict the behaviour of the stock market. Indeed, the algorithm is specifically developed to take advantage of both the sentiment and the past values of a certain financial instrument in order to choose the best investment decision. This allows the algorithm to ensure the maximization of the obtainable profits by trading on the stock market. We have conducted an investment simulation and compared the performance of our proposed with a well-known benchmark (DJTATO index) and the optimal results, in which an investor knows in advance the future price of a product. The result shows that our approach outperforms the benchmark and achieves the performance score close to the optimal result.

Massimo Quadrana, Alexandros Karatzoglou, Balázs Hidasi et al.

Session-based recommendations are highly relevant in many modern on-line services (e.g. e-commerce, video streaming) and recommendation settings. Recently, Recurrent Neural Networks have been shown to perform very well in session-based settings. While in many session-based recommendation domains user identifiers are hard to come by, there are also domains in which user profiles are readily available. We propose a seamless way to personalize RNN models with cross-session information transfer and devise a Hierarchical RNN model that relays end evolves latent hidden states of the RNNs across user sessions. Results on two industry datasets show large improvements over the session-only RNNs.

Yashar Deldjoo, Massimo Quadrana, Mehdi Elahi et al.

Item features play an important role in movie recommender systems, where recommendations can be generated by using explicit or implicit preferences of users on traditional features (attributes) such as tag, genre, and cast. Typically, movie features are human-generated, either editorially (e.g., genre and cast) or by leveraging the wisdom of the crowd (e.g., tag), and as such, they are prone to noise and are expensive to collect. Moreover, these features are often rare or absent for new items, making it difficult or even impossible to provide good quality recommendations. In this paper, we show that user's preferences on movies can be better described in terms of the mise-en-scène features, i.e., the visual aspects of a movie that characterize design, aesthetics and style (e.g., colors, textures). We use both MPEG-7 visual descriptors and Deep Learning hidden layers as example of mise-en-scène features that can visually describe movies. Interestingly, mise-en-scène features can be computed automatically from video files or even from trailers, offering more flexibility in handling new items, avoiding the need for costly and error-prone human-based tagging, and providing good scalability. We have conducted a set of experiments on a large catalogue of 4K movies. Results show that recommendations based on mise-en-scène features consistently provide the best performance with respect to richer sets of more traditional features, such as genre and tag.

Roberto Pagano, Massimo Quadrana, Mehdi Elahi et al.

One of the main challenges in Recommender Systems (RSs) is the New User problem which happens when the system has to generate personalised recommendations for a new user whom the system has no information about. Active Learning tries to solve this problem by acquiring user preference data with the maximum quality, and with the minimum acquisition cost. Although there are variety of works in active learning for RSs research area, almost all of them have focused only on the single-domain recommendation scenario. However, several real-world RSs operate in the cross-domain scenario, where the system generates recommendations in the target domain by exploiting user preferences in both the target and auxiliary domains. In such a scenario, the performance of active learning strategies can be significantly influenced and typical active learning strategies may fail to perform properly. In this paper, we address this limitation, by evaluating active learning strategies in a novel evaluation framework, explicitly suited for the cross-domain recommendation scenario. We show that having access to the preferences of the users in the auxiliary domain may have a huge impact on the performance of active learning strategies w.r.t. the classical, single-domain scenario.

Yashar Deldjoo, Shengping Zhang, Bahman Zanj et al.

Recently, sparse representation based visual tracking methods have attracted increasing attention in the computer vision community. Although achieve superior performance to traditional tracking methods, however, a basic problem has not been answered yet --- that whether the sparsity constrain is really needed for visual tracking? To answer this question, in this paper, we first propose a robust non-sparse representation based tracker and then conduct extensive experiments to compare it against several state-of-the-art sparse representation based trackers. Our experiment results and analysis indicate that the proposed non-sparse tracker achieved competitive tracking accuracy with sparse trackers while having faster running speed, which support our non-sparse tracker to be used in practical applications.