User Side Information Research Articles

Entities recommendations using contextual information

Generating entities recommendations has attracted considerable interest in recent years. Most recently published works mainly focus on providing a user with the most relevant and/or personalized entity recommendations that score highly against the query and/or the user’s preference. Some works consider user side information, such as the user network, user relations, and user’s demographic information, and propose to integrate them into the framework of recommender systems. These approaches have been shown to increase the users’ satisfaction and engagement with the system. In this paper, we investigate entities recommender systems and summarize the recent efforts in this domain by categorizing approaches. The first category presents different approaches that utilize knowledge graph as side information. The second category gathers work that consider both the current query, and the users’ previous interactions with the system. These latter works have considered the full user history to personalize the ranking of recommended entities related to the query. In this review paper, we emphasize contextual information-based approaches that utilize user’s context and feedback to improve the recommendations. We accomplished a summary of the literature and synthesized the papers according to different perceptions. Finally, a comparison between approaches is provided and some drawbacks are identified.

Mobility-Aware Offloading Decision for Multi-Access Edge Computing in 5G Networks.

Multi-access edge computing (MEC) is a key technology in the fifth generation (5G) of mobile networks. MEC optimizes communication and computation resources by hosting the application process close to the user equipment (UE) in network edges. The key characteristics of MEC are its ultra-low latency response and real-time applications in emerging 5G networks. However, one of the main challenges in MEC-enabled 5G networks is that MEC servers are distributed within the ultra-dense network. Hence, it is an issue to manage user mobility within ultra-dense MEC coverage, which causes frequent handover. In this study, our purposed algorithms include the handover cost while having optimum offloading decisions. The contribution of this research is to choose optimum parameters in optimization function while considering handover, delay, and energy costs. In this study, it assumed that the upcoming future tasks are unknown and online task offloading (TO) decisions are considered. Generally, two scenarios are considered. In the first one, called the online UE-BS algorithm, the users have both user-side and base station-side (BS) information. Because the BS information is available, it is possible to calculate the optimum BS for offloading and there would be no handover. However, in the second one, called the BS-learning algorithm, the users only have user-side information. This means the users need to learn time and energy costs throughout the observation and select optimum BS based on it. In the results section, we compare our proposed algorithm with recently published literature. Additionally, to evaluate the performance it is compared with the optimum offline solution and two baseline scenarios. The simulation results indicate that the proposed methods outperform the overall system performance.

Deep learning and Internet of Things for tourist attraction recommendations in smart cities

We propose a tourist attraction IoT-enabled deep learning-based recommendation system to enhance tourist experience in a smart city. Travelers will enter details about their travels (traveling alone or with a companion, type of companion such as partner or family with kids, traveling for business or leisure, etc.) as well as user side information (age of the traveler/s, hobbies, etc.) into the smart city app/website. Our proposed deep learning-based recommendation system will process this personal set of input features to recommend the tourist activities/attractions that best fit his/her profile. Furthermore, when the tourists are in the smart city, content-based information (already visited attractions) and context-related information (location, weather, time of day, etc.) are obtained in real time using IoT devices; this information will allow our proposed deep learning-based tourist attraction recommendation system to suggest additional activities and/or attractions in real time. Our proposed multi-label deep learning classifier outperforms other models (decision tree, extra tree, k-nearest neighbor and random forest) and can successfully recommend tourist attractions for the first case [(a) searching for and planning activities before traveling] with the loss, accuracy, precision, recall and F1-score of 0.5%, 99.7%, 99.9%, 99.9% and 99.8%, respectively. It can also successfully recommend tourist attractions for the second case [(b) looking for activities within the smart city] with the loss, accuracy, precision, recall and F1-score of 3.7%, 99.5%, 99.8%, 99.7% and 99.8%, respectively.

FSCR: A Deep Social Recommendation Model for Misleading Information

The popularity of intelligent terminals and a variety of applications have led to the explosive growth of information on the Internet. Some of the information is real, some is not real, and may mislead people’s behaviors. Misleading information refers to false information made up by some malicious marketer to create panic and seek benefits. In particular, when emergency events break out, many users may be misled by the misleading information on the Internet, which further leads them to buy things that are not in line with their actual needs. We call this kind of human activity ‘emergency consumption’, which not only fails to reflect users’ true interests but also causes the phenomenon of user preference deviation, and thus lowers the accuracy of the personal recommender system. Although traditional recommendation models have proven useful in capturing users’ general interests from user–item interaction records, learning to predict user interest accurately is still a challenging problem due to the uncertainty inherent in user behavior and the limited information provided by user–item interaction records. In addition, to deal with the misleading information, we divide user information into two types, namely explicit preference information (explicit comments or ratings) and user side information (which can show users’ real interests and will not be easily affected by misleading information), and then we create a deep social recommendation model which fuses user side information called FSCR. The FSCR model is significantly better than existing baseline models in terms of rating prediction and system robustness, especially in the face of misleading information; it can effectively identify the misleading users and complete the task of rating prediction well.

FeatureMF: An Item Feature Enriched Matrix Factorization Model for Item Recommendation

Matrix Factorization (MF) is one of the most successful Collaborative Filtering (CF) techniques used in recommender systems due to its effectiveness and ability to deal with very large user-item rating matrix. However, when the rating matrix sparseness increases its performance deteriorates. Expanding MF to include side-information of users and items has been shown by many researchers both to improve general recommendation performance and to help alleviate the data-sparsity and cold-start issues in CF. In regard to item feature side-information, most schemes incorporate this information through a two stage process: intermediate results (e.g., on item similarity) are first computed based on item attributes; these are then combined with MF. In this paper, focussing on item side-information, we propose a model that directly incorporates item features into the MF framework in a single step process. The model, which we name FeatureMF, does this by projecting every available attribute datum in each of the item features into the same latent factor space with users and items, thereby in effect enriching item representation in MF. Results are presented of comparative performance experiments of the model against three state-of-the-art item information enriched models, as well as against four reference benchmark models, using two public real-world datasets, Douban and Yelp, with four training:test ratio scenarios each. It is shown to yield the best recommendation performance over all these models across all contexts including data-sparsity situations, in particular, achieving over 0.9% to over 6.5% MAE recommendation performance improvement over the next best model, HERec. FeatureMF is also found to alleviate cold start and to scale well, almost linearly, in regard to computational time, as a function of dataset size.

Two-sided regularization model based on probabilistic matrix factorization and quantum similarity for recommender systems

Nowadays, with the advent of the age of Web 2.0, several social recommendation methods that use social network information have been proposed and achieved distinct developments. However, the most critical challenges for the existing majority of these methods are: (1) They tend to utilize only the available social relation between users and deal just with the cold-start user issue. (2) Besides, these methods are suffering from the lack of exploitation of content information such as social tagging, which can provide various sources to extract the item information to overcome the cold-start item and improve the recommendation quality. In this paper, we investigated the efficiency of data fusion by integrating multi-source of information. First, two essential factors, user-side information, and item-side information, are identified. Second, we developed a novel social recommendation model called Two-Sided Regularization (TSR), which is based on the probabilistic matrix factorization method. Finally, the effective quantum-based similarity method is adapted to measure the similarity between users and between items into the proposed model. Experimental results on the real dataset show that our proposed model TSR addresses both of cold-start user and item issues and outperforms state-of-the-art recommendation methods. These results indicate the importance of incorporating various sources of information in the recommendation process.

Top-N Recommendation Model Based on SDAE

Collaborative filtering is the mainstream approach to personalized recommendation. For the cold start problem faced in collaborative filtering, it is a hot research topic to introduce the user’s side information into the recommendation model. Different from the matrix decomposition idea adopted in the existing methods, we propose a Top-N recommendation model using the side information of the user based on the reconstruction function of the stacked denoising auto-encoder. Experimental results show that the model outperforms the existing method in Recall. In addition, we explore the influence of missing ratings and user side information vector into the loss computation. The experimental results show that ignoring the missing ratings in the loss function is beneficial to improve the performance of the model.

Neural Binary Representation Learning for Large-Scale Collaborative Filtering

Integrating hashing into collaborative filtering (CF) has been a promising solution to address the efficiency problem of large-scale recommender systems, i.e., hashing users and items into binary codes and then making recommendations in Hamming space. However, most of the existing hashing methods for CF solely focus on modeling the user-item similarity (a.k.a. preference) but omit the user-user and item-item similarities, which cannot well preserve the original geometry in the vector space. Another tough issue is how to effectively tackle the encoding loss from the continuous vector space to the discrete Hamming space. In this paper, we propose a neural binary representation (NBR) learning approach by combining hashing with a neural network for the large-scale CF tasks. Our NBR problem is formulated as a Hamming similarity loss plus two anchor smoothing terms, which jointly preserve the intrinsic user-item, user-user, and item-item similarities. To compensate the encoding loss introduced by hashing, the anchors for users and items are pre-learned using both user-item interactions and the side-information of users and items through an AutoEncoder model. In particular, to solve the NBR problem, we develop a computationally efficient algorithm, which learns the binary codes in a fast bit-by-bit way and achieves less quantization deviation than the conventional CF hashing schemes. The extensive experiments on three benchmarks validate the superiority of our NBR approach in comparison to the state-of-the-art CF hashing methods.