Multi-view improved sequence behavior with adaptive multi-task learning in ranking

Yingshuai Wang

doi:10.1007/s10489-022-04088-w

2022-10-06

PRE

Yingshuai Wang *

Dezheng Zhang

Aziguli Wulamu

DOI：10.1007/s10489-022-04088-w

原文链接

原文求助

摘要

En 中文

Click through rate (CTR) and Conversion Rate (CVR) are core tasks in e-commerce recommender systems. Sequence behavior and multi-task learning have been widely used in CTR and CVR. Based on the concept of a transformer, we develop a technique of time and space feature representation for the prediction, which can capture high-level information better. In order to formulate user's different interests from historical sequence behavior, we design multi-task learning to improve multiple objectives simultaneously. It is difficult to turn the super parameters as the tasks increasing. In this paper, we propose an adaptive learning mixture-of-experts approach, which tackles this challenge and can learn super parameters among tasks automatically. It not only saves resources but also improves the performance with cognitive of the model. Furthermore, to enhance the flexibility, we improve the loss function with a constrained joint strategy and introduce RESNET mechanism. We design feature-cross-unit module, augment-expert module, and topK-dispatch module, which assist multi-task learning to improve better. Experiments on public dataset and our library dataset demonstrate the superiority of our model over the state-of-art method. Our method achieves + 2.29% AUC gain in the CTR task and + 1.81% AUC gain in the CVR task, which is a significant improvement and demonstrates the effectiveness of proposed approach.

Keyword:

Adaptive multi-task

Joint learning

Loss constraint

Resnet multi-layer

Sequence behavior

Feature cross unit

Augment expert

Top-k dispatch