Table of Links Abstract and 1 Introduction Methodology
Experiments
Conclusion and References 2. METHODOLOGY In this section, we first introduce the problem of multi-objective ranking for recommender systems. Second, we describe the general design of DML. Finally, we elaborate on the introduced components. 2.1 Multi-Objective Ranking for Recsys 2.2 Overall Design of DML Please refer to figure 1 for the overall network architecture of DML. With the existing MTL algorithms[25], the equation (1) can be further decomposed as below. For simplicity, we omit the subscript 𝑛 in this section. In this research, rather than 𝐺, we focus on the enhancement of upper-level networks for improved prediction performance. First, the shared component of CTFM is introduced, which leverages the attention mechanism to extract relevant information from the inputs of other task towers (the results of Equation (3)) as a complement to the target task. Please note that this attention is welldesigned to solve the task-awareness missing issue, for which the excessive encouragement of knowledge sharing is not conducive to the extraction of task-specific knowledge. With our design, the gradients computed from the target task’s loss will not impact the inputs of other task towers. 2.3 Cross Task Feature Mining Authors:
(1) Yi Ren, Tencent, Beijing, China (yiren_bj@outlook.com);
(2) Ying Du, Tencent, Beijing, China (yingdu@tencent.com);
(3) Bin Wang, Tencent, Beijing, China (hillmwang@tencent.com);
(4) Shenzheng Zhang, Tencent, Beijing, China (qjzcyzhang@tencent.com). This paper is available on arxiv under CC BY 4.0 DEED license. Table of Links Abstract and 1 Introduction Abstract and 1 Introduction Methodology Experiments Conclusion and References Methodology Methodology Experiments Experiments Conclusion and References Conclusion and References 2. METHODOLOGY In this section, we first introduce the problem of multi-objective ranking for recommender systems. Second, we describe the general design of DML. Finally, we elaborate on the introduced components. 2.1 Multi-Objective Ranking for Recsys 2.2 Overall Design of DML Please refer to figure 1 for the overall network architecture of DML. With the existing MTL algorithms[25], the equation (1) can be further decomposed as below. For simplicity, we omit the subscript 𝑛 in this section. In this research, rather than 𝐺, we focus on the enhancement of upper-level networks for improved prediction performance. First, the shared component of CTFM is introduced, which leverages the attention mechanism to extract relevant information from the inputs of other task towers (the results of Equation (3)) as a complement to the target task. Please note that this attention is welldesigned to solve the task-awareness missing issue, for which the excessive encouragement of knowledge sharing is not conducive to the extraction of task-specific knowledge. With our design, the gradients computed from the target task’s loss will not impact the inputs of other task towers. 2.3 Cross Task Feature Mining Authors: (1) Yi Ren, Tencent, Beijing, China (yiren_bj@outlook.com); (2) Ying Du, Tencent, Beijing, China (yingdu@tencent.com); (3) Bin Wang, Tencent, Beijing, China (hillmwang@tencent.com); (4) Shenzheng Zhang, Tencent, Beijing, China (qjzcyzhang@tencent.com). Authors: Authors: (1) Yi Ren, Tencent, Beijing, China (yiren_bj@outlook.com); (2) Ying Du, Tencent, Beijing, China (yingdu@tencent.com); (3) Bin Wang, Tencent, Beijing, China (hillmwang@tencent.com); (4) Shenzheng Zhang, Tencent, Beijing, China (qjzcyzhang@tencent.com). This paper is available on arxiv under CC BY 4.0 DEED license. This paper is available on arxiv under CC BY 4.0 DEED license. available on arxiv available on arxiv

Part of HackerNoon's growing list of open-source research papers, promoting free access to academic material.

Deep Mutual Learning Optimizes Multi-Task Recommender Systems with Cross Task Feature Mining

About Author

Comments

TOPICS

THIS ARTICLE WAS FEATURED IN

Related Stories

DML Boosts Multi-Task Recommender Performance with Enhanced Models and Real-World Gains

New Framework for Deep Mutual Learning (DML) to Improve Multi-task Recommender Systems

DML Boosts Multi-Task Recommender Performance with Enhanced Models and Real-World Gains

DML Revolutionizes Multi-Task Learning with Proven Effectiveness and Real-World Deployment

Bridging the Gap: How Senior Developers Can Pass Down Their Knowledge and Wisdom

Onboard New Developers with Better Coding Practices

DML Boosts Multi-Task Recommender Performance with Enhanced Models and Real-World Gains

New Framework for Deep Mutual Learning (DML) to Improve Multi-task Recommender Systems

DML Boosts Multi-Task Recommender Performance with Enhanced Models and Real-World Gains

DML Revolutionizes Multi-Task Learning with Proven Effectiveness and Real-World Deployment

Bridging the Gap: How Senior Developers Can Pass Down Their Knowledge and Wisdom

Onboard New Developers with Better Coding Practices

Light-Mode

Classic

Newspaper

Minty

Dark-Mode

Neon Noir

Minty

HN StartUps