7 February 2023 in ACM Transactions on Information Systems
Knowledge graphs (KGs) can provide users with semantic information and relations among numerous entities and nodes, which can greatly facilitate the performance of recommender systems. However, existing KG-based approaches still suffer from severe data sparsity and may not be effective in capturing the preference features of similar entities across domains. Therefore, in this article, we propose a P reference-aware G raph A ttention network model with C ollaborative K nowledge G raph ( PGACKG ) for cross-domain recommendations. Preference-aware entity embeddings with some collaborative signals are first obtained by exploiting the graph-embedding model, which can transform entities and items in the collaborative knowledge graph into semantic preference spaces. To better learn user preference features, we devise a preference-aware graph attention network framework that aggregates the preference features of similar entities within domains and across domains. In this framework, multi-hop reasoning is employed to assist in the generation of preference features within domains, and the node random walk based on frequency visits is proposed to gather similar preferences across domains for target entities. Then, the final preference features of entities are fused, while a novel C ross-domain B ayesian P ersonalized R anking ( CBPR ) is proposed to improve cross-domain recommendation accuracy. Extensive empirical experiments on four real-world datasets demonstrate that our proposed approach consistently outperforms state-of-the-art baselines. Furthermore, our PGACKG achieves strong performance in different ablation scenarios, and the interaction sparsity experiments also demonstrate that our proposed approach can significantly alleviate the data sparsity issue.
25 May 2020 in IEEE Access
Rating predictions, as an application that is widely used in recommender systems, have gradually become a valuable way which can help user narrow down their choices quickly and make wise decisions from the vast amount of information. However, most existing collaborative recommendation models suffer from poor accuracy due to data sparsity and cold start problems that recommender systems contain only a few explicit data. To solve this problem, a new implicit trust recommendation approach (ITRA) is proposed to generate item rating prediction by mining and utilizing user implicit information in recommender systems. Specifically, user trust neighbor set that has similar preference and taste with a target user is first obtained by trust expansion strategy via user trust diffusion features in a trust network. Then, the trust ratings mined from user trust neighbors are used to compute trust similarity among users based on user collaborative filtering model. Finally, using the above filtered trust ratings and user trust similarity, the prediction results are generated by a trust weighting method. In addition, the empirical experiments are conducted on three real-world datasets, and the results demonstrate that our rating prediction model has obvious advantages over the state-of-the-art comparison methods in terms of the accuracy of recommendations.
11 July 2023 in Expert Systems with Applications
19 April 2024 in IEEE Transactions on Knowledge and Data Engineering
Cross-domain recommendations (CDRs), which can leverage the relatively abundant information from a richer domain to improve the recommendation performance in a sparser domain, have attracted great attention due to their flexible recommendation strategies. Nevertheless, existing CDR approaches still suffer from severe data sparsity and low semantic sampling efficiency issues, and hardly employ existing reinforcement learning models to improve cross-domain recommendation accuracy. To this end, we propose a new Knowledge-aware and Deep Reinforced Cross-Domain Recommendation framework over Collaborative Knowledge Graph (KRCDR). Specifically, we formalize the cross-domain recommendation task as a Markov Decision Process, and propose a knowledge-aware dual state representation approach to enhance state representations within and across domains for target users by leveraging knowledge graph information. Then, to improve the training performance, we propose a Constrained Self-supervised Actor-Critic network (CSAC) model, in which a constrained neighbor pruning strategy is devised to narrow the exploration space and improve the sampling efficiency, and the CSAC is developed to improve the recommendation policy. Additionally, in our proposed CSAC model, a self-supervised output layer within domains is used as an actor network to generate the recommendation policy, and a Q-learning output layer across domains is used as a critic network to feedback reward signals. Finally, based on the KRCDR approach, we design a new algorithm to assist in generating cross-domain recommendation results. Extensive experiments have been conducted on several real-world datasets, which demonstrate the superiority of our proposed approach compared with state-of-the-art baseline methods.
25 November 2019 in IEEE Access
Recommender systems can provide users with an ordered list of various items, which greatly assists users to purchase products that they are satisfied with. However, item recommendation has been confronted with some inherent problems, such as sparse ratings and long-tail distribution, resulting in low accuracy of recommendations and insignificant marketing. In this paper, we propose a novel learning model based on trust diffusion and global item (TDGIL) to improve the accuracy of item rating prediction for recommender systems. Specifically, first, the rating information on items is mined and aggregated to the greatest extent based on trust diffusion characteristics among users. The benchmark prediction of item recommendation is updated by a user trust neighbor set and its item ratings, which are obtained by a trust diffusion algorithm. Then, the difference weights and compensation coefficients for all items are defined to learn users’ potential preferences in the proposed global item model. Finally, the TDGIL learning algorithm is presented to train and learn the target networks by random gradient descent. The extensive experiments and results on two real-world datasets demonstrated that our proposed model can achieve significant improvements in the accuracy of rating prediction compared with some state-of-the-art methods.