Residual Multi-Task Learner for Applied Ranking
Open Access
- 24 August 2024
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 4974-4985
Abstract
Modern e-commerce platforms rely heavily on modeling diverse user feedback to provide personalized services. Consequently, multi-task learning has become an integral part of their ranking systems. However, existing multi-task learning methods encounter two main challenges: some lack explicit modeling of task relationships, resulting in inferior performance, while others have limited applicability due to being computationally intensive, having scalability issues, or relying on strong assumptions. To address these limitations and better fit our real-world scenario, pre-rank in Shopee Search, we introduce in this paper ResFlow, a lightweight multi-task learning framework that enables efficient cross-task information sharing via residual connections between corresponding layers of task networks. Extensive experiments on datasets from various scenarios and modalities demonstrate its superior performance and adaptability over state-of-the-art methods. The online A/B tests in Shopee Search showcase its practical value in large-scale industrial applications, evidenced by a 1.29% increase in OPU (order-per-user) without additional system latency. ResFlow is now fully deployed in the pre-rank module of Shopee Search. To facilitate efficient online deployment, we propose a novel offline metric Weighted Recall@K, which aligns well with our online metric OPU, addressing the longstanding online-offline metric misalignment issue. Besides, we propose to fuse scores from the multiple tasks additively when ranking items, which outperforms traditional multiplicative fusion.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (U22B2020)
This publication has 27 references indexed in Scilit:
- Adding Conditional Control to Text-to-Image Diffusion Models2023
- DCMT: A Direct Entire-Space Causal Multi-Task Framework for Post-Click Conversion Estimation2023
- Multi-view Multi-behavior Contrastive Learning in Recommendation2022
- A survey of recommender systems with multi-objective optimizationNeurocomputing, 2022
- AliExpress Learning-To-Rank: Maximizing Online Model Performance without Going OnlineIEEE Transactions on Knowledge and Data Engineering, 2021
- A Survey on Multi-Task LearningIEEE Transactions on Knowledge and Data Engineering, 2021
- Deep Residual Learning for Image Recognition2016
- Cross-Stitch Networks for Multi-task Learning2016
- Learning deep structured semantic models for web search using clickthrough data2013
- A comparative analysis of offline and online evaluations and discussion of research paper recommender system evaluation2013