An Unified Search and Recommendation Foundation Model for Cold-Start Scenario

Abstract

In modern commercial search engines and recommendation systems, data from multiple domains is available to jointly train the multi-domain model. Traditional methods train multi-domain models in the multi-task setting, with shared parameters to learn the similarity of multiple tasks, and task-specific parameters to learn the divergence of features, labels, and sample distributions of individual tasks. With the development of large language models, LLM can extract global domain-invariant text features that serve both search and recommendation tasks. We propose a novel framework called S\&R Multi-Domain Foundation, which uses LLM to extract domain invariant features, and Aspect Gating Fusion to merge the ID feature, domain invariant text features and task-specific heterogeneous sparse features to obtain the representations of query and item. Additionally, samples from multiple search and recommendation scenarios are trained jointly with Domain Adaptive Multi-Task module to obtain the multi-domain foundation model. We apply the S\&R Multi-Domain foundation model to cold start scenarios in the pretrain-finetune manner, which achieves better performance than other SOTA transfer learning methods. The S\&R Multi-Domain Foundation model has been successfully deployed in Alipay Mobile Application's online services, such as content query recommendation and service card recommendation, etc.

CIKM 2023,6 pages

References in corpus (6)

• LLaMA: Open and Efficient Foundation Language Models
• When Search Meets Recommendation: Learning Disentangled Search Representation for Recommendation
• M6-Rec: Generative Pretrained Language Models are Open-Ended Recommender Systems
• USER: A Unified Information Search and Recommendation Model based on Integrated Behavior Sequence
• Infer Implicit Contexts in Real-time Online-to-Offline Recommendation
• Prototypical Contrastive Learning and Adaptive Interest Selection for Candidate Generation in Recommendations

Cited by in corpus (1)

• A Multimodal Single-Branch Embedding Network for Recommendation in Cold-Start and Missing Modality Scenarios