高级检索

    融合层注意力机制的多视角图对比学习推荐方法

    Multi-Perspective Graph Contrastive Learning Recommendation Method with Layer Attention Mechanism

    • 摘要: 图对比学习因其可有效缓解数据稀疏问题被广泛应用在推荐系统中. 然而,目前大多数基于图对比学习的推荐算法均采用单一视角进行学习,这极大地限制了模型的泛化能力,且图卷积网络本身存在的过度平滑问题,也影响着模型的稳定性. 基于此,提出一种融合层注意力机制的多视角图对比学习推荐方法. 一方面,该方法提出2种不同视角下的3种对比学习,在视图级视角下,通过对原始图添加随机噪声构建扰动增强视图,利用奇异值分解重组构建SVD(singular value decomposition)增强视图,对这2个增强视图进行视图级对比学习;在节点视角下,利用节点间的语义信息分别进行候选节点和候选结构邻居对比学习,并将3种对比学习辅助任务和推荐任务进行多任务学习优化,以提高节点嵌入的质量,从而提升模型的泛化能力. 另一方面,在图卷积网络学习用户和项目的节点嵌入时,采用层注意力机制的方式聚合最终的节点嵌入,提高模型的高阶连通性,以缓解过度平滑问题. 在 4 个公开数据集LastFM, Gowalla, Ifashion, Yelp上与10个经典模型进行对比,结果表明该方法在Recall, Precision, NDCG这3个指标上分别平均提升3.12%, 3.22%, 4.03%,这说明所提方法是有效的.

       

      Abstract: Graph contrastive learning is widely employed in recommender system due to its effectiveness in mitigating data sparsity issue. However, most current recommendation algorithms based on graph contrastive learning start to learn from only a single perspective, severely limiting the model's generalization capability. Furthermore, the over-smoothing problem inherent in graph convolutional networks also affects the model's stability. Based on this, we propose the Multi-Perspective Graph Contrastive Learning recommendation method with Layer Attention mechanism. On the one hand, this method proposes three contrastive learning approaches from two different perspectives. From a view-level perspective, it constructs perturbation-enhanced view by adding random noise for the original graph and employing singular value decomposition recombination to establish SVD-enhanced view. It then performs view-level contrastive learning on these two enhanced views. From a node-level perspective, it conducts contrastive learning on candidate nodes and candidate structural neighbors using semantic information between nodes, Optimize multi-task learning with three contrastive auxiliary tasks and a recommendation task to enhance the quality of node embeddings, thereby improving the model's generalization ability. On the other hand, in the context of learning for user and item node embeddings by graph convolutional network, a layer attention mechanism is employed to aggregate the final node embeddings. This enhances the model's higher-order connectivity and mitigates the over-smoothing issue. When compared with ten classic models on four publicly available datasets - LastFM, Gowalla, Ifashion, and Yelp, the results indicate that this method achieves an average improvement of 3.12% in Recall, 3.22% in Precision, and 4.03% in NDCG. This demonstrates the effectiveness of the approach proposed in this work.

       

    /

    返回文章
    返回