Personalized TV Recommendation with Mixture Probabilistic Matrix Factorization

Recommender systems have been an efficient strategy to deal with information overload by producing personalized predictions. Recommendation systems based on deep learning have accomplished magnificent results, but most of these systems are traditional recommender systems that use a single rating. In this work, we introduce a multi-criteria collaborative filtering recommender by combining deep neural network and matrix factorization. Our model consists of two parts: the first part uses a fused model of deep neural network and matrix factorization to predict the criteria ratings and the second one employs a deep neural network to predict the overall rating. The experimental results on two datasets, including a real-world dataset, show that the proposed model outperformed several state-of-the-art methods across different datasets and performance evaluation metrics.

Forensic speaker recognition: A new method based on extracting accent and language information from short utterances

Classical matrix factorization approaches to collaborative filtering learn a latent vector for each user and each item, and recommendations are scored via the similarity between two such vectors, which are of the same dimension. In this work, we are motivated by the intuition that a user is a much more complicated entity than any single item, and cannot be well described by the same representation. Hence, the variety of a user's interests could be better captured by a more complex representation. We propose to model the user with a richer set of functions, specifically via a set of latent vectors, where each vector captures one of the user's latent interests or tastes. The overall recommendation model is then nonlinear where the matching score between a user and a given item is the maximum matching score over each of the user's latent interests with respect to the item's latent representation. We describe a simple, general and efficient algorithm for learning such a model, and apply it to large scale, real-world datasets from YouTube and Google Music, where our approach outperforms existing techniques.

Network Intrusion Detection Systems (NIDSs) are an increasingly important tool for the prevention and mitigation of cyber attacks. Over the past years, a lot of research efforts have aimed at leveraging the increasingly powerful models of Machine Learning (ML) for this purpose. A number of labelled synthetic datasets have been generated and made publicly available by researchers, and they have become the benchmarks via which new ML-based NIDS classifiers are being evaluated. Recently published results show excellent classification performance with these datasets, increasingly approaching 100 percent performance across key evaluation metrics such as Accuracy, F1 score, AUC, etc. Unfortunately, we have not yet seen these excellent academic research results translated into practical NIDS systems with such near-perfect performance. This motivated our research presented in this paper, where we analyse the statistical properties of the benign traffic in three of the more recent and relevant NIDS datasets, (CIC_IDS, UNSW_NB15, TON_IOT), by converting them into a common flow format. As a comparison, we consider two datasets obtained from real-world production networks, one from a university network and one from a medium size Internet Service Provider (ISP). Our results show that the two real-world datasets are quite similar among themselves in regards to most of the considered statistical features. Equally, the three synthetic datasets are also relatively similar within their group. However, and most importantly, our results show a distinct difference of most of the considered statistical features between the three synthetic datasets and the two real-world datasets. Since ML relies on the basic assumption of training and test datasets being sampled from the same distribution, this raises the question of how well the performance results of ML-classifiers trained on the considered synthetic datasets can translate and generalise to real-world networks. We believe this is an interesting and relevant question which provides motivation for further research in this space.

Recent sequential recommendation models rely increasingly on consecutive short-term user-item interaction sequences to model user interests. These approaches have, however, raised concerns about both short- and long-term interests. (1) short-term: interaction sequences may not result from a monolithic interest, but rather from several intertwined interests, even within a short period of time, resulting in their failures to model skip behaviors; (2) long-term: interaction sequences are primarily observed sparsely at discrete intervals, other than consecutively over the long run. This renders difficulty in inferring long-term interests, since only discrete interest representations can be derived, without taking into account interest dynamics across sequences. In this study, we address these concerns by learning (1) multi-scale representations of short-term interests; and (2) dynamics-aware representations of long-term interests. To this end, we present an Interest Dynamics modeling framework using generative Neural Processes, coined IDNP, to model user interests from a functional perspective. IDNP learns a global interest function family to define each user's long-term interest as a function instantiation, manifesting interest dynamics through function continuity. Specifically, IDNP first encodes each user's short-term interactions into multi-scale representations, which are then summarized as user context. By combining latent global interest with user context, IDNP then reconstructs long-term user interest functions and predicts interactions at upcoming query timestep. Moreover, IDNP can model such interest functions even when interaction sequences are limited and non-consecutive. Extensive experiments on four real-world datasets demonstrate that our model outperforms the state-of-the-art on various evaluation metrics.

Self-adaptive robust nonlinear regression for unknown noise via mixture of Gaussians

Abstract—Recommender systems are often used to provide useful recommendations for users. They use previous history of the users-items interactions, e.g. purchase history and/or users rating on items, to provide a suitable recommendation list for any target user. They may also use contextual information available about items and users. Collaborative filtering algorithm and its variants are the most successful recommendation algorithms that have been applied to many applications. Collaborative filtering method works by first finding the most similar users (or items) for a target user (or items), and then building the recommendation lists. There is no unique evaluation metric to assess the performance of recommendations systems, and one often choose the one most appropriate for the application in hand. This paper compares the performance of a number of well-known collaborative filtering algorithms on movie recommendation. To this end, a number of performance criteria are used to test the algorithms. The algorithms are ranked for each evaluation metric and a rank aggregation method is used to determine the wining algorithm. Our experiments show that the probabilistic matrix factorization has the top performance in this dataset, followed by item-based and user-based collaborative filtering. Non-negative matrix factorization and Slope 1 has the worst performance among the considered algorithms.
 Keywords—Social networks analysis and mining, big data, recommender systems, collaborative filtering.

Tensor factorization method based on review text semantic similarity for rating prediction

Recently, exploiting a knowledge graph (KG) to enrich the semantic representation of a news article have been proven to be effective for news recommendation. These solutions focus on the representation learning for news articles with additional information in the knowledge graph, where the user representations are mainly derived based on these news representations later. However, different users would hold different interests on the same news article. In other words, directly identifying the entities relevant to the user's interest and deriving the resultant user representation could enable a better news recommendation and explanation.

With the advent of online social networks, the use of information hidden in social networks for recommendation has been extensively studied. Unlike previous work regarded social influence as regularization terms, we take advantage of network embedding techniques and propose an embedding based recommendation method. Specifically, we first pre-train a network embedding model on the users' social network to map each user into a low dimensional space, and then incorporate them into a matrix factorization model, which combines both latent and pre-learned features for recommendation. The experimental results on two real-world datasets indicate that our proposed model is more effective and can reach better performance than other related methods.

Nowadays, a lot of people possess accounts on multiple online social networks, e.g., Facebook and Twitter. These networks are overlapped, but the correspondences between their users are not explicitly given. Mapping common users across these social networks will be beneficial for applications such as cross-network recommendation. In recent years, a lot of mapping algorithms have been proposed which exploited social and/or profile relations between users from different networks. However, there is still a lack of unified mapping framework which can well exploit high-order relational information in both social structures and profiles. In this paper, we propose a unified hypergraph learning framework named unified manifold alignment on hypergraph (UMAH) for this task. UMAH models social structures and user profile relations in a unified hypergraph where the relative weights of profile hyperedges are determined automatically. Given a set of training user correspondences, a common subspace is learned by preserving the hypergraph structure as well as the correspondence relations of labeled users. UMAH intrinsically performs semisupervised manifold alignment with profile information for calibration. For a target user in one network, UMAH ranks all the users in the other network by their probabilities of being the corresponding user (measured by similarity in the subspace). In experiments, we evaluate UMAH on three real world data sets and compare it to state-of-art baseline methods. Experimental results have demonstrated the effectiveness of UMAH in mapping users across networks.

Many studies utilizing review information to overcome the rating data sparsity obstacle in recommender systems because its abundant information and outstanding explainability. These methods consider reviews as attributes for users and items. They using aggregated review texts from a user and aggregated review texts for an item to model user and item respectively. However, on the one hand, reviews are actually a kind of interactive feature. The item-related features will be incorporated when modeling users by reviews and the same goes for modeling items. On the other hand, it’s a serious challenge for them to build accurate item features because of the reviews are from a lot of users who have different preference. The same goes for building user features with all user’s reviews. So it is more efficient to use review information to model the interaction characteristics between users and items. In this paper, we propose a collaborative filtering (CF) framework, Dual-Prior Review-based Matrix Factorization (DPRMF), a model integrates review information into probabilistic matrix factorization (PMF) model. DPRMF using convolutional neural networks (CNNs) to generate the review text information vector and considering the review information a prior constraint of interaction between user and item. Extensive experiments on benchmark datasets of Amazon and Yelp on different domains show that the proposed DPRMF model consistently outperforms the state-of-the-art review-based recommendation approaches, including PMF, HFT, DeepCoNN and NARRE. In addition, we use word-level vector weights in the embedding layer of our CNN architecture, which help us visualize the reviews and interpretate our model more intuitive.

Dynamic BIM component recommendation method based on probabilistic matrix factorization and grey model

With the development of e-commerce, a large amount of personalized information is produced daily. To utilize diverse personalized information to improve recommendation accuracy, we propose a hybrid recommendation model based on users' ratings, reviews, and social data. Our model consists of six steps, review transformation, feature generation, community detection, model training, feature blending, and prediction and evaluation. Three groups of experiments are performed in this paper. Experiments A are used to identify the regression algorithm used in our model, Experiments B are used to identify the model to analyze review texts and the algorithm to detect social communities, and Experiments C compare our hybrid recommendation model with conventional recommendation models, such as probabilistic matrix factorization, UserKNN, ItemKNN, and social network-based models, such as socialMF and TrustSVD. The experiment results show that recommendation accuracy can be improved significantly with our hybrid model based on review texts and social communities.

The rapid growth of edge data generated by mobile devices and applications deployed at the edge of the network has exacerbated the problem of information overload. As an effective way to alleviate information overload, recommender system can improve the quality of various services by adding application data generated by users on edge devices, such as visual and textual information, on the basis of sparse rating data. The visual information in the movie trailer is a significant part of the movie recommender system. However, due to the complexity of visual information extraction, data sparsity cannot be remarkably alleviated by merely using the rough visual features to improve the rating prediction accuracy. Fortunately, the convolutional neural network can be used to extract the visual features precisely. Therefore, the end-to-end neural image caption (NIC) model can be utilized to obtain the textual information describing the visual features of movie trailers. This paper proposes a trailer inception probabilistic matrix factorization model called Ti-PMF, which combines NIC, recurrent convolutional neural network, and probabilistic matrix factorization models as the rating prediction model. We implement the proposed Ti-PMF model with extensive experiments on three real-world datasets to validate its effectiveness. The experimental results illustrate that the proposed Ti-PMF outperforms the existing ones.