DSKReG: Differentiable Sampling on Knowledge Graph for Recommendation with Relational GNN
This work improves recommendation accuracy for users in cold-start scenarios by better leveraging knowledge graphs, representing an incremental advancement over existing KG-based approaches.
The paper tackles the cold-start problem in recommender systems by addressing skewed node degrees and irrelevant interactions in knowledge graphs, proposing DSKReG which learns relevance distributions and uses differentiable sampling to outperform state-of-the-art KG-based methods.
In the information explosion era, recommender systems (RSs) are widely studied and applied to discover user-preferred information. A RS performs poorly when suffering from the cold-start issue, which can be alleviated if incorporating Knowledge Graphs (KGs) as side information. However, most existing works neglect the facts that node degrees in KGs are skewed and massive amount of interactions in KGs are recommendation-irrelevant. To address these problems, in this paper, we propose Differentiable Sampling on Knowledge Graph for Recommendation with Relational GNN (DSKReG) that learns the relevance distribution of connected items from KGs and samples suitable items for recommendation following this distribution. We devise a differentiable sampling strategy, which enables the selection of relevant items to be jointly optimized with the model training procedure. The experimental results demonstrate that our model outperforms state-of-the-art KG-based recommender systems. The code is available online at https://github.com/YuWang-1024/DSKReG.