Double-Wing Mixture of Experts for Streaming Recommendations

by   Yan Zhao, et al.

Streaming Recommender Systems (SRSs) commonly train recommendation models on newly received data only to address user preference drift, i.e., the changing user preferences towards items. However, this practice overlooks the long-term user preferences embedded in historical data. More importantly, the common heterogeneity in data stream greatly reduces the accuracy of streaming recommendations. The reason is that different preferences (or characteristics) of different types of users (or items) cannot be well learned by a unified model. To address these two issues, we propose a Variational and Reservoir-enhanced Sampling based Double-Wing Mixture of Experts framework, called VRS-DWMoE, to improve the accuracy of streaming recommendations. In VRS-DWMoE, we first devise variational and reservoir-enhanced sampling to wisely complement new data with historical data, and thus address the user preference drift issue while capturing long-term user preferences. After that, we propose a Double-Wing Mixture of Experts (DWMoE) model to first effectively learn heterogeneous user preferences and item characteristics, and then make recommendations based on them. Specifically, DWMoE contains two Mixture of Experts (MoE, an effective ensemble learning model) to learn user preferences and item characteristics, respectively. Moreover, the multiple experts in each MoE learn the preferences (or characteristics) of different types of users (or items) where each expert specializes in one underlying type. Extensive experiments demonstrate that VRS-DWMoE consistently outperforms the state-of-the-art SRSs.


page 5

page 13


Stratified and Time-aware Sampling based Adaptive Ensemble Learning for Streaming Recommendations

Recommender systems have played an increasingly important role in provid...

Mixture of Virtual-Kernel Experts for Multi-Objective User Profile Modeling

In many industrial applications like online advertising and recommendati...

Learning from History and Present: Next-item Recommendation via Discriminatively Exploiting User Behaviors

In the modern e-commerce, the behaviors of customers contain rich inform...

Generating Self-Serendipity Preference in Recommender Systems for Addressing Cold Start Problems

Classical accuracy-oriented Recommender Systems (RSs) typically face the...

Freudian and Newtonian Recurrent Cell for Sequential Recommendation

A sequential recommender system aims to recommend attractive items to us...

Improving Transformer-based Sequential Recommenders through Preference Editing

One of the key challenges in Sequential Recommendation (SR) is how to ex...

How to Retrain Recommender System? A Sequential Meta-Learning Method

Practical recommender systems need be periodically retrained to refresh ...