Search

Heterogeneous information network(HIN) contains rich semantic information,and the use of HIN for rating prediction has become an important way to alleviate the problem of data sparsity in recommender systems.However,the traditional methods using meta-paths to extract HIN semantic information ignore the rating information on the edges,making the meta-paths unable to accurately capture the semantic similarity between users and recommended items.And these methods also fail to distinguish the importance of different meta-paths.To address the two problems,rating constrained meta-path is proposed to obtain more accurate HIN semantic information which is then used to construct multi-layer homogeneous networks for users and items.Then,a neural network for rating prediction is designed by combining graph convolutional network and attention mechanism,which effectively represents various semantic information in HIN through multi-channel graph convolutional networks and distinguishes the importance of different meta-paths by using an attentional fusion function.Furthermore,the proposed model also integrates the attribute information of users and items to improve the accuracy of rating prediction.Experimental results on Douban Book and Yelp datasets show that the proposed model is significantly better than the comparative baseline models,especially in the case of sparse data,and the root mean square error reduces by up to 50% compared to the baseline model,thus verifying the superiority of the proposed model.

In this study, we employ coarse-grained molecular dynamics simulations to explore the microstructure of MSA (methanesulfonic acid)-type electroplating solution, containing Sn(MSA)2 as the primary salt, MSA as the stabilizer, amphiphilic alkylphenol ethoxylate (APEO) as surfactants and cinnamaldehyde (CA) as the brightener agents, as well as water as the solvent. Our simulation indicates that temperature variations can significantly affect the structural properties of the electroplating solution and the adsorption behavior of its key components onto the substrate. Specifically, at low temperatures, the primary salt ions aggregate into ionic clusters, and the amphiphilic APEO surfactants and CA molecules form micelles composed of hydrophobic cores and hydrophilic shells, which reduces the uniformity of the solution and hinders the adsorption of ions, CA and surfactants onto the substrate. Appropriately increasing the temperature can weaken the aggregation of these components in bulk solution due to the accelerated molecular movements and arouse their adsorption. However, on further increasing the temperature, the elevated kinetic energy of the components thoroughly overwhelms the adsorption interactions, and therefore, the ions, surfactants, and CA desorb from the substrate and redissolve into the solution. We systematically analyze the complex interactions between these components at different temperatures and clarify the mechanism of the non-monotonic dependence of adsorption strength on the temperature at the molecular level. Our simulations demonstrate that there is low-temperature scope for reprocessing/recycling and intermediate-temperature scope for substrate-adsorptions of the key components. This study confers insights into a fundamental understanding of the microscopic mechanism for electroplating and can provide guidance for the development of precise electroplatings. [ABSTRACT FROM AUTHOR]