Knowledge Graph Self-Supervised Rationalization for Recommendation

Yang, Yuhao; Huang, Chao; Xia, Lianghao; Huang, Chunzhen

doi:10.1145/3580305.3599400

Cited by 31 publications

(2 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To ensure that the views of the elements are aligned, we use contrasting lenses. Inspired by [2], and to mitigate over-fitting and eliminate spurious negative effects, formally, we characterize our contrastive misfortune as:…”

Section: Knowledge-aware Contrastive Learningmentioning

confidence: 99%

Knowledge graph self-supervised contrastive learning for recommendation

Wang,

Jiang,

Chen

et al. 2024

Third International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2024)

View full text Add to dashboard Cite

Knowledge graphs play a central role in the field of recommender systems, and their quality directly impacts their performance in deep applications. Real-world knowledge graphs are often subject to noise, which disrupts the precise representation of user preferences. This paper proposes a Knowledge Graph-based Contrastive Learning framework, KGRSL, aiming to enhance perceptual capabilities through an augmented knowledge graph. Simultaneously, we employ self-supervised signals to lead the contrastive learning example, further restrain noise. The proposed model demonstrates effectiveness, as evidenced by improved recall rates and NDCG scores across three public datasets-Last.FM, MIND, and Yelp2018. The results indicate that our proposed framework KGRSL has shown improvements of 3.47%, 6.22%, and 11.02% in Recall@20 compared to recent baseline models.

show abstract

Section: Knowledge-aware Contrastive Learningmentioning

confidence: 99%

Knowledge graph self-supervised contrastive learning for recommendation

Wang,

Jiang,

Chen

et al. 2024

Third International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2024)

View full text Add to dashboard Cite

show abstract

“…Sun et al [51] designed a hybrid structure of a knowledge graph and a user-item graph to explore self-supervised contrastive learning by generating different data augmentation views. Yang et al [52] designed a new generative task in the form of masking-reconstructing by calculating rational scores for knowledge triplets, aiming to generate a recommender model with noise-resistant performance.…”

Section: Ssl-based Recommendationmentioning

confidence: 99%

Knowledge-Aware Graph Self-Supervised Learning for Recommendation

Li,

Jia,

et al. 2023

Electronics

View full text Add to dashboard Cite

Collaborative filtering (CF) based on graph neural networks (GNN) can capture higher-order relationships between nodes, which in turn improves recommendation performance. Although effective, GNN-based methods still face the challenges of sparsity and noise in real scenarios. In recent years, researchers have introduced graph self-supervised learning (SSL) techniques into CF to alleviate the sparse supervision problem. The technique first augments the data to obtain contrastive views and then utilizes the mutual information maximization to provide self-supervised signals for the contrastive views. However, the existing approaches based on graph self-supervised signals still face the following challenges: (i) Most of the works fail to effectively mine and exploit the supervised information from the item knowledge graph, resulting in suboptimal performance. (ii) Existing data augmentation methods are unable to fully exploit the potential of contrastive learning, because they primarily focus on the contrastive view of data structure changes and neglect the adjacent relationship among users and items. To address these issues, we propose a novel self-supervised learning approach, namely Knowledge-aware Graph Self-supervised Learning (KGSL). Specifically, we calculate node similarity based on semantic relations between items in the knowledge graph to generate a semantic-based item similarity graph. Then, the self-supervised learning contrast views are generated from both the user–item interaction graph and the item similarity graph, respectively. Maximization of the information from these contrastive views provides additional self-supervised signals to enhance the node representation capacity. Finally, we establish a joint training strategy for the self-supervised learning task and the recommendation task to further optimize the learning process of KGSL. Extensive comparative experiments as well as ablation experiments are conducted on three real-world datasets to verify the effectiveness of KGSL.

show abstract