DGCN: Diversified Recommendation with Graph Convolutional Networks
arXiv:2108.06952 · doi:10.1145/3442381.3449835
Abstract
These years much effort has been devoted to improving the accuracy or relevance of the recommendation system. Diversity, a crucial factor which measures the dissimilarity among the recommended items, received rather little scrutiny. Directly related to user satisfaction, diversification is usually taken into consideration after generating the candidate items. However, this decoupled design of diversification and candidate generation makes the whole system suboptimal. In this paper, we aim at pushing the diversification to the upstream candidate generation stage, with the help of Graph Convolutional Networks (GCN). Although GCN based recommendation algorithms have shown great power in modeling complex collaborative filtering effect to improve the accuracy of recommendation, how diversity changes is ignored in those advanced works. We propose to perform rebalanced neighbor discovering, category-boosted negative sampling and adversarial learning on top of GCN. We conduct extensive experiments on real-world datasets. Experimental results verify the effectiveness of our proposed method on diversification. Further ablation studies validate that our proposed method significantly alleviates the accuracy-diversity dilemma.
WWW'21
References in corpus (14)
- Semi-Supervised Classification with Graph Convolutional Networks
- BPR: Bayesian Personalized Ranking from Implicit Feedback
- Unsupervised Domain Adaptation by Backpropagation
- KGAT: Knowledge Graph Attention Network for Recommendation
- On the Convergence of Adam and Beyond
- Simplifying Graph Convolutional Networks
- Graph Convolutional Matrix Completion
- Knowledge Graph Convolutional Networks for Recommender Systems
- DeepFM: A Factorization-Machine based Neural Network for CTR Prediction
- Deep Learning Recommendation Model for Personalization and Recommendation Systems
- NPA: Neural News Recommendation with Personalized Attention
- Expectation-Maximization for Learning Determinantal Point Processes
- Pixie: A System for Recommending 3+ Billion Items to 200+ Million Users in Real-Time
- Recent Advances in Diversified Recommendation