no code implementations • 16 Apr 2024 • Zhiyu Hu, Yang Zhang, Minghao Xiao, Wenjie Wang, Fuli Feng, Xiangnan He
The evolving paradigm of Large Language Model-based Recom- mendation (LLMRec) customizes Large Language Models (LLMs) through parameter-efficient fine-tuning (PEFT) using recommenda- tion data.
no code implementations • 5 Jul 2023 • Yang Zhang, Zhiyu Hu, Yimeng Bai, Fuli Feng, Jiancan Wu, Qifan Wang, Xiangnan He
In this work, we propose an Influence Function-based Recommendation Unlearning (IFRU) framework, which efficiently updates the model without retraining by estimating the influence of the unusable data on the model via the influence function.