MPFormer: Adaptive Framework for Industrial Multi-Task Personalized Sequential Retriever

2025-08-28 · Yijia Sun, Shanshan Huang, Linxiao Che, Haitao Lu, Qiang Luo, Kun Gai, Guorui Zhou arxiv

Modern industrial recommendation systems encounter a core challenge of multi-stage optimization misalignment: a significant semantic gap exists between the multi-objective optimization paradigm widely used in the ranking phase and the single-objective modeling in the retrieve phase. Although the mainstream industry solution achieves multi-objective coverage through parallel multi-path single-objective retrieval, this approach leads to linear growth of training and serving resources with the number of objectives and has inherent limitations in handling loosely coupled objectives. This paper proposes the MPFormer, a dynamic multi-task Transformer framework, which systematically addresses the aforementioned issues through three innovative mechanisms. First, an objective-conditioned transformer that jointly encodes user behavior sequences and multi-task semantics through learnable attention modulation; second, personalized target weights are introduced to achieve dynamic adjustment of retrieval results; finally, user personalization information is incorporated into token representations and the Transformer structure to further enhance the model's representation ability. This framework has been successfully integrated into Kuaishou short video recommendation system, stably serving over 400 million daily active users. It significantly improves user daily engagement and system operational efficiency. Practical deployment verification shows that, compared with traditional solutions, it effectively optimizes the iterative paradigm of multi-objective retrieval while maintaining service response speed, providing a scalable multi-objective solution for industrial recommendation systems.

📄 PDF Abstract BibTeX arXiv:2508.20400

Code (0)

등록된 구현이 없습니다.

Tasks

Recommendation Systems

StampFormer: A Physics-Guided Material-Geometry-Coupled Multimodal Model for Rapid Prediction of Physical Fields in Sheet Metal Stamping

2026-05-13 · Jiajie Luo, Mohamed Mohamed, Osama Hassan, Haosu Zhou 외 arxiv

Traditional sheet metal forming relies on time-consuming and expensive Finite Element Analysis (FEA) for design validation, a process that significantly prolongs design cycles. While surrogate models offer faster iterati…

Test-Time Compensated Representation Learning for Extreme Traffic Forecasting

2023-09-16 · Zhiwei Zhang, Weizhong Zhang, Yaowei Huang, Kani Chen

Traffic forecasting is a challenging task due to the complex spatio-temporal correlations among traffic series. In this paper, we identify an underexplored problem in multivariate traffic series prediction: extreme event…

Representation Learning

AAD-LLM: Adaptive Anomaly Detection Using Large Language Models

2024-11-01 · Alicia Russell-Gilbert, Alexander Sommers, Andrew Thompson, Logan Cummins 외

For data-constrained, complex and dynamic industrial environments, there is a critical need for transferable and multimodal methodologies to enhance anomaly detection and therefore, prevent costs associated with system f…

Anomaly Detection

Adaptive Federated Learning and Digital Twin for Industrial Internet of Things

2020-10-25 · Wen Sun, Shiyu Lei, Lu Wang, Zhiqiang Liu 외

Industrial Internet of Things (IoT) enables distributed intelligent services varying with the dynamic and realtime industrial devices to achieve Industry 4.0 benefits. In this paper, we consider a new architecture of dig…

Clustering Deep Reinforcement Learning Federated Learning Reinforcement Learning (RL)

Adaptive Pattern Extraction Multi-Task Learning for Multi-Step Conversion Estimations

2023-01-06 · Xuewen Tao, Mingming Ha, Xiaobo Guo, Qiongxu Ma 외

Multi-task learning (MTL) has been successfully used in many real-world applications, which aims to simultaneously solve multiple tasks with a single model. The general idea of multi-task learning is designing kinds of g…

Multi-Task Learning Representation Learning