基于多粒度的图对比学习推荐算法

Multi-Granularity Graph Contrastive Learning Recommender Algorithm

现有的图对比学习推荐算法,多局限于节点级或图级的对比学习,未能综合利用图的信息。针对这个问题,提出了一种基于多粒度的图对比学习推荐算法(Multi-Granularity Graph Contrastive Learning,MGGCL)。该算法通过融合节点级、子图级和全图级的对比学习,实现对用户和项目的跨粒度建模。在节点级别引入邻域对比学习方法;在子图级别采用随机游走生成不同局部结构,进行子图级对比学习;在全图级别通过采用相似子图–原图采样的组合方式,构建全图级别的对比视图。最后利用多任务策略对推荐监督任务和对比学习任务进行联合优化,提升推荐效果。在真实数据集Yelp和Amazon-Book上进行实验,采用Recall和NDCG指标进行评估。实验结果表明,提出的模型在两个数据集上相较于基线模型,Recall@20分别提升了4.24%和6.85%,NDCG@20分别提升了4.04%和9.66%。

The existing graph contrastive learning-based recommendation algorithms are often constrained to node-level or graph-level contrastive learning,limiting their ability to fully leverage the information present in the graph.To address this limitation,a Multi-Granularity Graph Contrastive Learning(MGGCL)approach was proposed for recommendation.The MGGCL approach integrates contrastive learning at multiple granularities to enable modeling of users and items across different scales.At the node level,a neighborhood contrastive learning method is introduced.At the subgraph level,diverse local structures are generated using random walks for subgraph-level contrastive learning.At the full graph level,a contrastive view of the entire graph is constructed by combining similar subgraphs with the original graph through sampling.In the end,a multi-task strategy is employed to jointly optimize the recommendation supervision task and the contrastive learning task,resulting in improved recommendation performance.Experimental evaluations conducted on real-world datasets,namely Yelp and Amazon-Book,employ the Recall and NDCG metrics for assessment.The results demonstrate significant enhancements of the proposed model compared to the baseline models,with Recall@20 improving by 4.24%and 6.85%,and NDCG@20 improving by 4.04%and 9.66%on the Yelp and Amazon-Book datasets,respectively.