A Soft-partitioned Semi-supervised Collaborative Transfer Learning Approach for Multi-Domain Recommendation

TL;DR

This paper introduces SSCTL, a novel transfer learning method for multi-domain recommendation that dynamically balances domain data and mitigates overfitting, leading to significant online performance improvements.

Contribution

The paper proposes a soft-partitioned semi-supervised transfer learning approach that adaptively generates parameters and uses pseudo-labels to improve multi-domain recommendation performance.

Findings

Online GMV increased by 0.54% to 2.90%.

CTR improved by 0.22% to 1.69%.

Effective in handling imbalanced domain data.

Abstract

In industrial practice, Multi-domain Recommendation (MDR) plays a crucial role. Shared-specific architectures are widely used in industrial solutions to capture shared and unique attributes via shared and specific parameters. However, with imbalanced data across different domains, these models face two key issues: (1) Overwhelming: Dominant domain data skews model performance, neglecting non-dominant domains. (2) Overfitting: Sparse data in non-dominant domains leads to overfitting in specific parameters. To tackle these challenges, we propose Soft-partitioned Semi-supervised Collaborative Transfer Learning (SSCTL) for multi-domain recommendation. SSCTL generates dynamic parameters to address the overwhelming issue, thus shifting focus towards samples from non-dominant domains. To combat overfitting, it leverages pseudo-labels with weights from dominant domain instances to enhance non-dominant domain data. We conduct comprehensive experiments, both online and offline, to validate the efficacy of our proposed method. Online tests yielded significant improvements across various domains, with increases in GMV ranging from 0.54% to 2.90% and enhancements in CTR ranging from 0.22% to 1.69%.