软件导刊2025，Vol.24Issue(3)：78-85,8.DOI:10.11907/rjdk.241150
MCPD:结合预训练与去噪图卷积网络的多任务学习推荐模型
MCPD:Multi-task Learning Recommender System Combining Pre-training and Denoising Graph Convolutional Network
摘要
Abstract
Currently,recommendation systems based on Graph Convolutional Networks(GCNs)commonly suffer from issues such as noise,low training efficiency,and inability to select appropriate loss functions for effective joint optimization.To this end,a multi task learning rec-ommendation model MCPD is proposed,which combines pre training and denoising graph convolutional networks.The graph convolutional net-work focuses on the collaborative signals between high-order neighbors to generate more accurate user and item embeddings.Firstly,pre train-ing is conducted on both the user and the project using bidirectional attention to improve the convergence speed and training time efficiency of the model.Secondly,a neighbor edge denoising autoencoder model is designed to combine traditional graph convolutional networks with atten-tion mechanisms in the neighbor edge denoising task to identify noisy edges.The embedding is encoded and decoded using a denoising autoen-coder DAE to reduce noise.Finally,select the cosine contrastive loss function with the best performance,and combine multi task learning to jointly optimize bidirectional attention aggregation pre training,neighbor edge denoising,and denoising autoencoder to ensure model recom-mendation accuracy.Experiments on three standard datasets showed that the Recall and NDCG metrics of the MCPD model reached 7.10,6.00,19.09 and 5.85,4.82,15.75,respectively,outperforming other baselines.In terms of recommendation accuracy,it has significant ad-vantages compared to GCN based recommendation systems.关键词
推荐系统/图卷积网络/协同过滤/去噪/多任务学习Key words
recommender system/graph convolutional networks/collaborative filtering/denoising/multi-task learning分类
信息技术与安全科学引用本文复制引用
范钰敏,袁卫华,王龙霄,孙倩..MCPD:结合预训练与去噪图卷积网络的多任务学习推荐模型[J].软件导刊,2025,24(3):78-85,8.基金项目
国家自然科学基金项目(62176142,62177031) （62176142,62177031）
山东省自然科学基金项目(ZR2021MF099,ZR2022MF334),山东省本科教学改革研究项目(M2021130,M2022245) （ZR2021MF099,ZR2022MF334）
山东省研究生优质教育教学资源项目(SDYAL2022155) （SDYAL2022155）
济南市市校融合发展战略工程项目(JNSX2023064) （JNSX2023064）
