Enhancing Domain-Level and User-Level Adaptivity in Diversified Recommendation

Recommender systems are playing a vital role in online platforms due to the ability of incorporating users' personal tastes. Beyond accuracy, diversity has been recognized as a key factor to broaden users' horizons as well as to promote enterprises' sales. However, the trade-off between accuracy and diversity remains to be a big challenge. More importantly, none of existing methods has explored the domain and user biases toward diversity. In this paper, we focus on enhancing both domain-level and user-level adaptivity in diversified recommendation. Specifically, we first encode domain-level diversity into a generalized bi-lateral branch network with an adaptive balancing strategy. We further capture user-level diversity by developing a two-way adaptive metric learning backbone network inside each branch. We conduct extensive experiments on three real-world datasets. Results demonstrate that our proposed approach consistently outperforms the state-of-the-art baselines.