ImprovedGCN: An efficient and accurate recommendation system employing lightweight graph convolutional networks in social media
作者:
Highlights:
• Simplifies the model by including only the necessary parts for recommendation.
• Improved graph convolution and layer concatenation.
• Make a contrast with other models.
• Prove the rationality and efficiency of ImprovedGCN.
• Future work is to individualize the layer concatenation weights.
摘要
•Simplifies the model by including only the necessary parts for recommendation.•Improved graph convolution and layer concatenation.•Make a contrast with other models.•Prove the rationality and efficiency of ImprovedGCN.•Future work is to individualize the layer concatenation weights.
论文关键词:Recommendation system,Graph neural network,Embedding,Collaborative filtering
论文评审过程:Received 10 November 2021, Revised 14 June 2022, Accepted 10 August 2022, Available online 13 August 2022, Version of Record 29 August 2022.
论文官网地址:https://doi.org/10.1016/j.elerap.2022.101191