ECAT: A Entire space Continual and Adaptive Transfer Learning Framework for Cross-Domain Recommendation

TL;DR

ECAT is a novel transfer learning framework for cross-domain recommendation that effectively utilizes the entire sample space and adaptive knowledge transfer to improve recommendation performance in industrial settings.

Contribution

The paper introduces ECAT, a framework that combines sample selection and adaptive knowledge distillation for continual transfer learning across the entire space.

Findings

ECAT achieves +13.6% CVR improvement on Taobao datasets.

ECAT outperforms state-of-the-art methods in offline recommendation metrics.

Demonstrates effective full-space utilization and negative migration avoidance.

Abstract

In industrial recommendation systems, there are several mini-apps designed to meet the diverse interests and needs of users. The sample space of them is merely a small subset of the entire space, making it challenging to train an efficient model. In recent years, there have been many excellent studies related to cross-domain recommendation aimed at mitigating the problem of data sparsity. However, few of them have simultaneously considered the adaptability of both sample and representation continual transfer setting to the target task. To overcome the above issue, we propose a Entire space Continual and Adaptive Transfer learning framework called ECAT which includes two core components: First, as for sample transfer, we propose a two-stage method that realizes a coarse-to-fine process. Specifically, we perform an initial selection through a graph-guided method, followed by a fine-grained selection using domain adaptation method. Second, we propose an adaptive knowledge distillation method for continually transferring the representations from a model that is well-trained on the entire space dataset. ECAT enables full utilization of the entire space samples and representations under the supervision of the target task, while avoiding negative migration. Comprehensive experiments on real-world industrial datasets from Taobao show that ECAT advances state-of-the-art performance on offline metrics, and brings +13.6% CVR and +8.6% orders for Baiyibutie, a famous mini-app of Taobao.