This repository is a curated list of academic papers focusing on pre-training techniques for recommendation systems, including those leveraging large language models (LLMs). It serves researchers and practitioners in the field of recommender systems looking to understand and implement state-of-the-art pre-training methodologies.

How It Works

The repository organizes papers by sub-topics within recommendation system pre-training, such as sequential/session-based recommendation, user representation pre-training, and the application of LLMs. It provides links to papers, code, datasets, and sometimes blog posts, facilitating a comprehensive overview of the research landscape.

Quick Start & Requirements

This is a curated list of papers and does not have a direct installation or execution command. Access to the listed papers requires navigating to the provided links.

Highlighted Details

• Comprehensive coverage of surveys and reviews on pre-training for recommendation systems.
• Extensive collection of papers on sequential, user representation, and two-tower pre-training models.
• Significant focus on the integration of Large Language Models (LLMs) into recommendation systems, including prompt learning and LLM-based evaluation.
• Inclusion of benchmark datasets and code repositories for many of the listed papers.

Maintenance & Community

The repository is maintained by Xiangyang Li from Peking University. Contributions are welcomed via issues or pull requests. A related hub for LLMs in RecSys is also linked.

Licensing & Compatibility

The repository itself is hosted on GitHub, implying a standard open-source approach. Individual papers retain their original publication licenses. Compatibility for commercial use depends on the licenses of the linked papers and datasets.

Limitations & Caveats

This is a paper list, not a software library, and thus does not offer direct functionality. The content is research-oriented and may require significant effort to translate into practical applications. The recruitment advertisement for Huawei Noah Ark Recommendation&Search Lab is a long-term offering.