GFlowGR: Fine-tuning Generative Recommendation Frameworks with Generative Flow Networks

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wang, Yejing, Zhou, Shengyu, Lu, Jinyu, Liu, Qidong, Li, Xinhang, Zhang, Wenlin, Li, Feng, Wang, Pengjie, Yu, Chuan, Xu, Jian, Zheng, Bo, Zhao, Xiangyu
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917553970872320
author Wang, Yejing
Zhou, Shengyu
Lu, Jinyu
Liu, Qidong
Li, Xinhang
Zhang, Wenlin
Li, Feng
Wang, Pengjie
Yu, Chuan
Xu, Jian
Zheng, Bo
Zhao, Xiangyu
author_facet Wang, Yejing
Zhou, Shengyu
Lu, Jinyu
Liu, Qidong
Li, Xinhang
Zhang, Wenlin
Li, Feng
Wang, Pengjie
Yu, Chuan
Xu, Jian
Zheng, Bo
Zhao, Xiangyu
contents Generative recommendations (GR), which usually include item tokenizers and generative Large Language Models (LLMs), have demonstrated remarkable success across a wide range of scenarios. The majority of existing research efforts primarily concentrate on developing powerful item tokenizers or advancing LLM decoding strategies to attain superior performance. However, the critical fine-tuning step in GR frameworks, which is essential for adapting LLMs to recommendation data, remains largely unexplored. Current approaches predominantly rely on either the next-token prediction loss of supervised fine-tuning (SFT) or recommendationspecific direct preference optimization (DPO) strategies. Both methods ignore the exploration of possible positive unobserved samples, which is commonly referred to as the exposure bias problem. To mitigate this problem, this paper treats the GR as a multi-step generation task and constructs a GFlowNets-based fine-tuning framework (GFlowGR). The proposed framework integrates collaborative knowledge from traditional recommender systems to create an adaptive trajectory sampler and a comprehensive reward model. Leveraging the diverse generation property of GFlowNets, along with sampling and heuristic weighting techniques, GFlowGR emerges as a promising approach to mitigate the exposure bias problem. Extensive empirical results on two real-world datasets and with two different GR backbones highlight the effectiveness and robustness of GFlowGR.
format Preprint
id arxiv_https___arxiv_org_abs_2506_16114
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GFlowGR: Fine-tuning Generative Recommendation Frameworks with Generative Flow Networks
Wang, Yejing
Zhou, Shengyu
Lu, Jinyu
Liu, Qidong
Li, Xinhang
Zhang, Wenlin
Li, Feng
Wang, Pengjie
Yu, Chuan
Xu, Jian
Zheng, Bo
Zhao, Xiangyu
Information Retrieval
Artificial Intelligence
Generative recommendations (GR), which usually include item tokenizers and generative Large Language Models (LLMs), have demonstrated remarkable success across a wide range of scenarios. The majority of existing research efforts primarily concentrate on developing powerful item tokenizers or advancing LLM decoding strategies to attain superior performance. However, the critical fine-tuning step in GR frameworks, which is essential for adapting LLMs to recommendation data, remains largely unexplored. Current approaches predominantly rely on either the next-token prediction loss of supervised fine-tuning (SFT) or recommendationspecific direct preference optimization (DPO) strategies. Both methods ignore the exploration of possible positive unobserved samples, which is commonly referred to as the exposure bias problem. To mitigate this problem, this paper treats the GR as a multi-step generation task and constructs a GFlowNets-based fine-tuning framework (GFlowGR). The proposed framework integrates collaborative knowledge from traditional recommender systems to create an adaptive trajectory sampler and a comprehensive reward model. Leveraging the diverse generation property of GFlowNets, along with sampling and heuristic weighting techniques, GFlowGR emerges as a promising approach to mitigate the exposure bias problem. Extensive empirical results on two real-world datasets and with two different GR backbones highlight the effectiveness and robustness of GFlowGR.
title GFlowGR: Fine-tuning Generative Recommendation Frameworks with Generative Flow Networks
topic Information Retrieval
Artificial Intelligence
url https://arxiv.org/abs/2506.16114