div2vec: Diversity-Emphasized Node Embedding
This addresses the need for more diverse recommendations to enhance user experiences in real-world systems, representing an incremental improvement over existing methods like DeepWalk and node2vec.
The paper tackled the problem of low diversity in graph-based recommender systems by proposing div2vec, a node embedding method that samples nodes inversely proportional to their degree, which improved both accuracy and diversity in offline experiments on MovieLens and real-world services like WATCHA and LINE Wallet Coupon.
Recently, the interest of graph representation learning has been rapidly increasing in recommender systems. However, most existing studies have focused on improving accuracy, but in real-world systems, the recommendation diversity should be considered as well to improve user experiences. In this paper, we propose the diversity-emphasized node embedding div2vec, which is a random walk-based unsupervised learning method like DeepWalk and node2vec. When generating random walks, DeepWalk and node2vec sample nodes of higher degree more and nodes of lower degree less. On the other hand, div2vec samples nodes with the probability inversely proportional to its degree so that every node can evenly belong to the collection of random walks. This strategy improves the diversity of recommendation models. Offline experiments on the MovieLens dataset showed that our new method improves the recommendation performance in terms of both accuracy and diversity. Moreover, we evaluated the proposed model on two real-world services, WATCHA and LINE Wallet Coupon, and observed the div2vec improves the recommendation quality by diversifying the system.