Macro Graph of Experts for Billion-Scale Multi-Task Recommendation
This work addresses a critical problem for large-scale recommender systems by enabling effective multi-task learning with graph structures, though it appears incremental as it builds on existing multi-task and graph-based approaches.
The paper tackles the challenge of graph-based multi-task learning at billion-scale by introducing the Macro Graph of Experts (MGOE) framework, which leverages macro graph embeddings to capture task-specific features and model expert correlations, resulting in superior performance over state-of-the-art methods in offline experiments and online A/B tests.
Graph-based multi-task learning at billion-scale presents a significant challenge, as different tasks correspond to distinct billion-scale graphs. Traditional multi-task learning methods often neglect these graph structures, relying solely on individual user and item embeddings. However, disregarding graph structures overlooks substantial potential for improving performance. In this paper, we introduce the Macro Graph of Expert (MGOE) framework, the first approach capable of leveraging macro graph embeddings to capture task-specific macro features while modeling the correlations between task-specific experts. Specifically, we propose the concept of a Macro Graph Bottom, which, for the first time, enables multi-task learning models to incorporate graph information effectively. We design the Macro Prediction Tower to dynamically integrate macro knowledge across tasks. MGOE has been deployed at scale, powering multi-task learning for the homepage of a leading billion-scale recommender system. Extensive offline experiments conducted on three public benchmark datasets demonstrate its superiority over state-of-the-art multi-task learning methods, establishing MGOE as a breakthrough in multi-task graph-based recommendation. Furthermore, online A/B tests confirm the superiority of MGOE in billion-scale recommender systems.