Multimedia Recommender Systems: Algorithms and Challenges

Deldjoo, Yashar; Schedl, Markus; Hidasi, Balázs; Wei, Yinwei; He, Xiangnan

doi:10.1007/978-1-0716-2197-4_25

Cited by 45 publications

(32 citation statements)

References 91 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is difficult for users to get the information they need directly and quickly from the massive amount of information. Therefore, recommendation algorithms are usually used to solve the problem of information overload, and the research of various recommendation methods [1,2,3,4] has become one of the main focuses of research in the field of computer science [5,6,7].…”

Section: Introductionmentioning

confidence: 99%

xLightGCN: A Simplified GCN-based Model for Multimedia Recommender System

Jingli

Siegal

Wang

et al. 2022

Preprint

View full text Add to dashboard Cite

With the gradual development of Internet technology, information resources are growing at a high speed and the problem of information overload has emerged. It is difficult for users to get the information they need directly and quickly from the massive amount of information. Therefore, recommendation algorithms are usually used to solve the problem of information overload, and the research of various recommendation methods. Depending on the implementation idea, recommendation algorithms are mainly classified into three categories: content-based recommendation, collaborative filtering-based recommendation, and hybrid recommendation methods. Collaborative filtering is the most widely used recommendation algorithm, and its main idea is to discover the correlation between users based on their preferences for products, and to make recommendations based on the correlation. Although these methods improve the performance of the recommendation system, when the number of users and products increases, the recommendation system may face the problems of sparsity and cold start, and thus cannot achieve personalized recommendation. The purpose of this paper is to leverage the multi-modal information to address the problem. Specifically, we devise a novel simplified GCN-based model which incorporates the content information extracted from the visual, acoustic, and textual modalities with CF signal by propagating along the item-user bipartite graph. Finally, conducting extensive experiments on public datasets, we demonstrate that our proposed model outperforms several state-of-the-art baselines.

show abstract

Section: Introductionmentioning

confidence: 99%

xLightGCN: A Simplified GCN-based Model for Multimedia Recommender System

Jingli

Siegal

Wang

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…If we can accurately obtain the preferred character of each user and the degree of preference for that character, we can be considered as being able to obtain the user's preference more accurately [1]. Therefore, it is necessary to study and implement micro-video recommendation system [2,3].…”

Section: Introductionmentioning

confidence: 99%

A micro-video recommendation system incorporating social connections

Fang

Wen

et al. 2022

Preprint

View full text Add to dashboard Cite

With the increasing number of micro-video community applications, social media platforms have started to attract more people through their built-in micro-video features. More and more people like to record and share their favorite people or events through micro-videos. The content of micro-videos is very diverse. If we can accurately obtain the preferred character of each user and the degree of preference for that character, we can be considered as being able to obtain the user’s preference more accurately. Therefore, it is necessary to study and implement a micro-video recommendation system. Currently, video-oriented recommendation algorithms mostly start from the following parts: user rating, video text description, video content, etc. The recommendation algorithm that starts with user ratings is similar to the recommendation algorithm of ordinary e-commerce platforms. Most of them will first ask users to rate the videos they have watched, and then find other users who also rate these videos and whose scores are closer to those of the target user, as the nearest neighbors of the target user, so as to obtain the user-item similarity matrix. The research goal of this paper is to design and implement a micro-video recommendation system that integrates social relationships in order to solve the current problem of micro-video information overload on social platforms, which makes it difficult for users to find videos that meet their preferences. We can get users’ preferences for video content by recognizing their portraits and their weights, and get their nearest neighbors and making video recommendations by improving the social relationship similarity, familiarity, and interest similarity between users. And through several experiments and a series of comparative experiments, it was confirmed that the algorithm has an advantage in the recommendation accuracy rate of the algorithm has some advantages.

show abstract

“…Second, it is more applicable, and deep learning can fine-tune the model by fine-tune methods [6,7] to get application-specific solutions for specific scenarios. In other words, based on deep learning, on the one hand, the accuracy of some algorithms is improved, on the other hand, some problems that cannot be better achieved by traditional machine learning methods can be achieved by deep learning [8].…”

Section: Introductionmentioning

confidence: 99%

Collaborative Filtering Recommendation model Based on Graph Neural Network and Attention Mechanism

Dahl

Ivan

Patko

et al. 2022

Preprint

View full text Add to dashboard Cite

With the popularity and development of the internet and mobile terminals, people can access a lot of information through them every day. Recommender systems have become one of the important technologies for various online platforms that aim to predict whether a user will interact with an item or not. Among them, collaborative filtering-based models have made effective progress in learning user and item representations by modeling historical user-item interactions. Recently, models based on GCN have been effective in recommendation, and the main function of GCN models is to improve the embedding representation of users and items by iteratively aggregating feature information from neighbors using graph connectivity to extract additional information. However, in previous works, dividing users into subgraphs without intersection only leads to a partial loss of information, ignoring the potential connections that may exist between different groups of users; and because only users are divided, the influence of commodity factors on the purchase outcome at the time of purchase is ignored in the learning process. Based on the above considerations, in this paper we propose a message-passing recommendation model. The model uses intersects users and items in separate subgraphs and uses an optimized attention mechanism to obtain the final node embedding to optimize the embedding representation by introducing multiple embedding propagation layers that encode higher-order connectivity relationships. We conduct extensive experiments to evaluate the proposed model. The results show that our model can effectively improve the performance of the recommendation.

show abstract

Multimedia Recommender Systems: Algorithms and Challenges

Cited by 45 publications

References 91 publications

xLightGCN: A Simplified GCN-based Model for Multimedia Recommender System

xLightGCN: A Simplified GCN-based Model for Multimedia Recommender System

A micro-video recommendation system incorporating social connections

Collaborative Filtering Recommendation model Based on Graph Neural Network and Attention Mechanism

Contact Info

Product

Resources

About