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

• URL: http://arxiv.org/abs/2506.16114v1
• Date: Thu, 19 Jun 2025 08:04:31 GMT
• Title: GFlowGR: Fine-tuning Generative Recommendation Frameworks with Generative Flow Networks
• Authors: Yejing Wang, Shengyu Zhou, Jinyu Lu, Qidong Liu, Xinhang Li, Wenlin Zhang, Feng Li, Pengjie Wang, Jian Xu, Bo Zheng, Xiangyu Zhao,
• Abstract summary: This paper treats the Generative Recommendations (GR) as a multi-step generation task and constructs a GFlowNets-based fine-tuning framework (GFlowGR)<n>The proposed framework integrates collaborative knowledge from traditional recommender systems to create an adaptive trajectory sampler and a comprehensive reward model.
• Score: 36.39484385717512
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Proxy-Free GFlowNet [39.964801793885485]
  Generative Flow Networks (GFlowNets) are designed to sample diverse, high-reward structures by modeling distributions over compositional objects.<n>Most existing methods adopt a model-based approach, learning a proxy model from the dataset to approximate the reward function.<n>We propose textbfTrajectory-Distilled GFlowNet (TD-GFN), a emphproxy-free training framework that eliminates the need for out-of-dataset reward queries.
  arXiv  Detail & Related papers  (2025-05-26T15:12:22Z)
• Action is All You Need: Dual-Flow Generative Ranking Network for Recommendation [25.30922374657862]
  We introduce a Dual-Flow Generative Ranking Network (DFGR) for recommendation scenarios.<n> DFGR employs a dual-flow mechanism to optimize interaction modeling.<n>Experiments in open-source and real industrial datasets show that DFGR outperforms DLRM.
  arXiv  Detail & Related papers  (2025-05-22T14:58:53Z)
• Self-Boost via Optimal Retraining: An Analysis via Approximate Message Passing [58.52119063742121]
  Retraining a model using its own predictions together with the original, potentially noisy labels is a well-known strategy for improving the model performance.<n>This paper addresses the question of how to optimally combine the model's predictions and the provided labels.<n>Our main contribution is the derivation of the Bayes optimal aggregator function to combine the current model's predictions and the given labels.
  arXiv  Detail & Related papers  (2025-05-21T07:16:44Z)
• Generative Diffusion Models for Resource Allocation in Wireless Networks [77.36145730415045]
  We train a policy to imitate an expert and generate new samples from the optimal distribution.<n>We achieve near-optimal performance through the sequential execution of the generated samples.<n>We present numerical results in a case study of power control.
  arXiv  Detail & Related papers  (2025-04-28T21:44:31Z)
• Killing Two Birds with One Stone: Unifying Retrieval and Ranking with a Single Generative Recommendation Model [71.45491434257106]
  Unified Generative Recommendation Framework (UniGRF) is a novel approach that integrates retrieval and ranking into a single generative model.<n>To enhance inter-stage collaboration, UniGRF introduces a ranking-driven enhancer module.<n>UniGRF significantly outperforms existing models on benchmark datasets.
  arXiv  Detail & Related papers  (2025-04-23T06:43:54Z)
• Ignite Forecasting with SPARK: An Efficient Generative Framework for Refining LLMs in Temporal Knowledge Graph Forecasting [13.402856325579236]
  We introduce SPARK, a Sequence-level Proxy framework for refining Large Language Models in TKG forecasting.<n>Inspired by inference-time algorithms, SPARK offers a cost-effective, plug-and-play solution through two key innovations.<n> Experiments across diverse datasets validate SPARK's forecasting performance, robust generalization capabilities, and high efficiency.
  arXiv  Detail & Related papers  (2025-03-27T03:02:02Z)
• Looking Backward: Retrospective Backward Synthesis for Goal-Conditioned GFlowNets [27.33222647437964]
  Generative Flow Networks (GFlowNets) have demonstrated remarkable capabilities to generate diverse sets of high-reward candidates.<n>However, training such models is challenging due to extremely sparse rewards.<n>We propose a novel method called textbfRetrospective textbfBackward textbfSynthesis (textbfRBS) to address these problems.
  arXiv  Detail & Related papers  (2024-06-03T09:44:10Z)
• Ant Colony Sampling with GFlowNets for Combinatorial Optimization [68.84985459701007]
  Generative Flow Ant Colony Sampler (GFACS) is a novel meta-heuristic method that hierarchically combines amortized inference and parallel search.<n>Our method first leverages Generative Flow Networks (GFlowNets) to amortize a emphmulti-modal prior distribution over solution space.<n>This prior is updated via parallel search in the spirit of Ant Colony Optimization (ACO) leading to the posterior distribution that generates near-optimal solutions.
  arXiv  Detail & Related papers  (2024-03-11T16:26:06Z)
• Chasing Fairness in Graphs: A GNN Architecture Perspective [73.43111851492593]
  We propose textsfFair textsfMessage textsfPassing (FMP) designed within a unified optimization framework for graph neural networks (GNNs) In FMP, the aggregation is first adopted to utilize neighbors' information and then the bias mitigation step explicitly pushes demographic group node presentation centers together. Experiments on node classification tasks demonstrate that the proposed FMP outperforms several baselines in terms of fairness and accuracy on three real-world datasets.
  arXiv  Detail & Related papers  (2023-12-19T18:00:15Z)
• DAG Matters! GFlowNets Enhanced Explainer For Graph Neural Networks [30.19635147123557]
  We propose a generative structure -- GFlowNets-based GNN Explainer (GFlowExplainer) Our GFlowExplainer aims to learn a policy that generates a distribution of subgraphs for which the probability of a subgraph is proportional to its' reward. We conduct extensive experiments on both synthetic and real datasets, and both qualitative and quantitative results show the superiority of our GFlowExplainer.
  arXiv  Detail & Related papers  (2023-03-04T16:15:25Z)
• Stochastic Generative Flow Networks [89.34644133901647]
  Generative Flow Networks (or GFlowNets) learn to sample complex structures through the lens of "inference as control" Existing GFlowNets can be applied only to deterministic environments, and fail in more general tasks with dynamics. This paper introduces GFlowNets, a new algorithm that extends GFlowNets to environments.
  arXiv  Detail & Related papers  (2023-02-19T03:19:40Z)
• GFlowCausal: Generative Flow Networks for Causal Discovery [27.51595081346858]
  We propose a novel approach to learning a Directed Acyclic Graph (DAG) from observational data called GFlowCausal. GFlowCausal aims to learn the best policy to generate high-reward DAGs by sequential actions with probabilities proportional to predefined rewards. We conduct extensive experiments on both synthetic and real datasets, and results show the proposed approach to be superior and also performs well in a large-scale setting.
  arXiv  Detail & Related papers  (2022-10-15T04:07:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.