On Softmax Direct Preference Optimization for Recommendation

Abstract

Recommender systems aim to predict personalized rankings based on user preference data. With the rise of Language Models (LMs), LM-based recommenders have been widely explored due to their extensive world knowledge and powerful reasoning abilities. Most of the LM-based recommenders convert historical interactions into language prompts, pairing with a positive item as the target response and fine-tuning LM with a language modeling loss. However, the current objective fails to fully leverage preference data and is not optimized for personalized ranking tasks, which hinders the performance of LM-based recommenders. Inspired by the current advancement of Direct Preference Optimization (DPO) in human preference alignment and the success of softmax loss in recommendations, we propose Softmax-DPO (S-DPO) to instill ranking information into the LM to help LM-based recommenders distinguish preferred items from negatives, rather than solely focusing on positives. Specifically, we incorporate multiple negatives in user preference data and devise an alternative version of DPO loss tailored for LM-based recommenders, connected to softmax sampling strategies. Theoretically, we bridge S-DPO with the softmax loss over negative sampling and find that it has a side effect of mining hard negatives, which assures its exceptional capabilities in recommendation tasks. Empirically, extensive experiments conducted on three real-world datasets demonstrate the superiority of S-DPO to effectively model user preference and further boost recommendation performance while mitigating the data likelihood decline issue of DPO. Our codes are available at https://github.com/chenyuxin1999/S-DPO.

Publication
In NeurIPS 2024

Citation:

@inproceedings{2024SDPO,
  title={On Softmax Direct Preference Optimization for Recommendation},
  author={Yuxin Chen and Junfei Tan and An Zhang and Zhengyi Yang and Leheng Sheng and Enzhi Zhang and Xiang Wang and Tat-Seng Chua},
  booktitle={NeurIPS},
  year={2024}
}
Junfei Tan
Junfei Tan
谭骏飞
Zhengyi Yang
Zhengyi Yang
杨正一
Xiang Wang
Xiang Wang
王翔 教授