STEM: Unleashing the Power of Embeddings for Multi-task Recommendation

TL;DR

This paper introduces STEM, a novel multi-task recommendation framework that combines shared and task-specific embeddings, significantly improving performance and positive transfer on multiple datasets.

Contribution

The paper proposes STEM, a new paradigm with shared and task-specific embeddings, and a model STEM-Net with gating mechanisms, addressing negative transfer issues in multi-task recommendation.

Findings

STEM-Net outperforms state-of-the-art models on three datasets.

It effectively captures task-specific user preferences.

Demonstrates positive transfer on comparable samples.

Abstract

Multi-task learning (MTL) has gained significant popularity in recommender systems as it enables simultaneous optimization of multiple objectives. A key challenge in MTL is negative transfer, but existing studies explored negative transfer on all samples, overlooking the inherent complexities within them. We split the samples according to the relative amount of positive feedback among tasks. Surprisingly, negative transfer still occurs in existing MTL methods on samples that receive comparable feedback across tasks. Existing work commonly employs a shared-embedding paradigm, limiting the ability of modeling diverse user preferences on different tasks. In this paper, we introduce a novel Shared and Task-specific EMbeddings (STEM) paradigm that aims to incorporate both shared and task-specific embeddings to effectively capture task-specific user preferences. Under this paradigm, we propose a simple model STEM-Net, which is equipped with an All Forward Task-specific Backward gating network to facilitate the learning of task-specific embeddings and direct knowledge transfer across tasks. Remarkably, STEM-Net demonstrates exceptional performance on comparable samples, achieving positive transfer. Comprehensive evaluation on three public MTL recommendation datasets demonstrates that STEM-Net outperforms state-of-the-art models by a substantial margin. Our code is released at https://github.com/LiangcaiSu/STEM.