Self-derived Knowledge Graph Contrastive Learning for Recommendation
Abstract: Knowledge Graphs (KGs) serve as valuable auxiliary information to improve the accuracy of recommendation systems. Previous methods have leveraged the knowledge graph to enhance item representation and thus achieve excellent performance. However, these approaches heavily rely on high-quality knowledge graphs and learn enhanced representations with the assistance of carefully designed triplets. Furthermore, the emergence of knowledge graphs has led to models that ignore the inherent relationships between items and entities. To address these challenges, we propose a Self-Derived Knowledge Graph Contrastive Learning framework (CL-SDKG) to enhance recommendation systems. Specifically, we employ the variational graph reconstruction technique to estimate the Gaussian distribution of user-item nodes corresponding to the graph neural network aggregation layer. This process generates multiple KGs, referred to as self-derived KGs. The self-derived KG acquires more robust perceptual representations through the consistency of the estimated structure. Besides, the self-derived KG allows models to focus on user-item interactions and reduce the negative impact of miscellaneous dependencies introduced by conventional KGs. Finally, we apply contrastive learning to the self-derived KG to further improve the robustness of CL-SDKG through the traditional KG contrast-enhanced process. We conducted comprehensive experiments on three public datasets, and the results demonstrate that our CL-SDKG outperforms state-of-the-art baselines.
Primary Subject Area: [Engagement] Multimedia Search and Recommendation
Secondary Subject Area: [Systems] Data Systems Management and Indexing
Relevance To Conference: Our CL-SDKG utilizes variational graph reconstruction to integrate information from various modalities to estimate the Gaussian distribution of nodes in the graph neural network aggregation layer, thereby obtaining a multimodal perceptual representation.In addition, the derived KGs allow the model to capture complex relationships between items and entities of different modalities, enabling the model to focus on user item interactions, reducing the negative impact of miscellaneous dependencies introduced by traditional KGs, and thereby enhancing the recommendation process.By combining contrastive learning, the CL-SDKG can effectively obtain more robust perceptual representations from different modalities, thereby enhancing its ability to capture subtle relationships between items and entities in different modalities.
Submission Number: 5651
Loading