SaviorRec: Semantic-Behavior Alignment for Cold-Start Recommendation

TL;DR

SaviorRec introduces a lightweight semantic-behavior alignment framework that enhances cold-start recommendation by aligning multimodal item representations with user behavior space, improving CTR prediction and online performance.

Contribution

The paper proposes a novel semantic-behavior alignment method using residual quantized semantic IDs to improve cold-start recommendation without complex pre-trained encoders.

Findings

0.83% offline AUC increase

13.21% clicks increase in online A/B test

13.44% orders increase in online A/B test

Abstract

In recommendation systems, predicting Click-Through Rate (CTR) is crucial for accurately matching users with items. To improve recommendation performance for cold-start and long-tail items, recent studies focus on leveraging item multimodal features to model users' interests. However, obtaining multimodal representations for items relies on complex pre-trained encoders, which incurs unacceptable computation cost to train jointly with downstream ranking models. Therefore, it is important to maintain alignment between semantic and behavior space in a lightweight way. To address these challenges, we propose a Semantic-Behavior Alignment for Cold-start Recommendation framework, which mainly focuses on utilizing multimodal representations that align with the user behavior space to predict CTR. First, we leverage domain-specific knowledge to train a multimodal encoder to generate behavior-aware semantic representations. Second, we use residual quantized semantic ID to dynamically bridge the gap between multimodal representations and the ranking model, facilitating the continuous semantic-behavior alignment. We conduct our offline and online experiments on the Taobao, one of the world's largest e-commerce platforms, and have achieved an increase of 0.83% in offline AUC, 13.21% clicks increase and 13.44% orders increase in the online A/B test, emphasizing the efficacy of our method.