Graph-GRPO: Training Graph Flow Models with Reinforcement Learning

• URL: http://arxiv.org/abs/2603.10395v1
• Date: Wed, 11 Mar 2026 04:20:45 GMT
• Title: Graph-GRPO: Training Graph Flow Models with Reinforcement Learning
• Abstract summary: We propose Graph-GRPO, an online reinforcement learning framework for training graph flow models (GFMs) under verifiable rewards.<n>With only 50 denoising steps, our method achieves 95.0% and 97.5% Valid-Unique-Novelty scores on the planar and tree datasets.
• Score: 14.937302684130257
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Graph generation is a fundamental task with broad applications, such as drug discovery. Recently, discrete flow matching-based graph generation, \aka, graph flow model (GFM), has emerged due to its superior performance and flexible sampling. However, effectively aligning GFMs with complex human preferences or task-specific objectives remains a significant challenge. In this paper, we propose Graph-GRPO, an online reinforcement learning (RL) framework for training GFMs under verifiable rewards. Our method makes two key contributions: (1) We derive an analytical expression for the transition probability of GFMs, replacing the Monte Carlo sampling and enabling fully differentiable rollouts for RL training; (2) We propose a refinement strategy that randomly perturbs specific nodes and edges in a graph, and regenerates them, allowing for localized exploration and self-improvement of generation quality. Extensive experiments on both synthetic and real datasets demonstrate the effectiveness of Graph-GRPO. With only 50 denoising steps, our method achieves 95.0\% and 97.5\% Valid-Unique-Novelty scores on the planar and tree datasets, respectively. Moreover, Graph-GRPO achieves state-of-the-art performance on the molecular optimization tasks, outperforming graph-based and fragment-based RL methods as well as classic genetic algorithms.

Related papers

• Approximate Subgraph Matching with Neural Graph Representations and Reinforcement Learning [15.3743761404157]
  This paper proposes a Reinforcement Learning based Approximate Subgraph Matching (RL-ASM) algorithm.<n>Our model is built upon the branch-and-bound algorithm that selects one pair of nodes from the two input graphs at a time for potential matches.<n>Experiments on both synthetic and real-world datasets demonstrate that our RL-ASM outperforms existing methods in terms of effectiveness and efficiency.
  arXiv  Detail & Related papers  (2026-03-18T21:53:23Z)
• Incorporating Spatial Information into Goal-Conditioned Hierarchical Reinforcement Learning via Graph Representations [37.10671332775445]
  The integration of graphs with Goal-conditioned Reinforcement Learning (GCHRL) has recently gained attention.<n>Existing approaches typically rely on domain-specific knowledge to construct these graphs.<n>This paper proposes a solution by developing a graph encoder-decoder to evaluate unseen states.
  arXiv  Detail & Related papers  (2025-11-14T00:58:39Z)
• G1: Teaching LLMs to Reason on Graphs with Reinforcement Learning [58.73279333365234]
  Reinforcement Learning (RL) on synthetic graph-theoretic tasks can significantly scale graph reasoning abilities.<n>With RL on Erdos, G1 obtains substantial improvements in graph reasoning, where our finetuned 3B model even outperforms Qwen2.5-72B-Instruct (24x size)<n>Our findings offer an efficient, scalable path for building strong graph reasoners by finetuning LLMs with RL on graph-theoretic tasks.
  arXiv  Detail & Related papers  (2025-05-24T04:33:41Z)
• GFM-RAG: Graph Foundation Model for Retrieval Augmented Generation [83.72561905487447]
  We introduce GFM-RAG, a novel graph foundation model (GFM) for retrieval augmented generation.<n>GFM-RAG is powered by an innovative graph neural network that reasons over graph structure to capture complex query-knowledge relationships.<n>It achieves state-of-the-art performance while maintaining efficiency and alignment with neural scaling laws.
  arXiv  Detail & Related papers  (2025-02-03T07:04:29Z)
• Revisiting Graph Neural Networks on Graph-level Tasks: Comprehensive Experiments, Analysis, and Improvements [54.006506479865344]
  We propose a unified evaluation framework for graph-level Graph Neural Networks (GNNs)<n>This framework provides a standardized setting to evaluate GNNs across diverse datasets.<n>We also propose a novel GNN model with enhanced expressivity and generalization capabilities.
  arXiv  Detail & Related papers  (2025-01-01T08:48:53Z)
• GALA: Graph Diffusion-based Alignment with Jigsaw for Source-free Domain Adaptation [13.317620250521124]
  Source-free domain adaptation is a crucial machine learning topic, as it contains numerous applications in the real world. Recent graph neural network (GNN) approaches can suffer from serious performance decline due to domain shift and label scarcity. We propose a novel method named Graph Diffusion-based Alignment with Jigsaw (GALA), tailored for source-free graph domain adaptation.
  arXiv  Detail & Related papers  (2024-10-22T01:32:46Z)
• LLM-Based Multi-Agent Systems are Scalable Graph Generative Models [73.28294528654885]
  GraphAgent-Generator (GAG) is a novel simulation-based framework for dynamic, text-attributed social graph generation.<n>GAG simulates the temporal node and edge generation processes for zero-shot social graph generation.<n>The resulting graphs exhibit adherence to seven key macroscopic network properties, achieving an 11% improvement in microscopic graph structure metrics.
  arXiv  Detail & Related papers  (2024-10-13T12:57:08Z)
• DeFoG: Discrete Flow Matching for Graph Generation [45.037260759871124]
  We introduce DeFoG, a graph generative framework that disentangles sampling from training.<n>We propose novel sampling methods that significantly enhance performance and reduce the required number of refinement steps.
  arXiv  Detail & Related papers  (2024-10-05T18:52:54Z)
• SimTeG: A Frustratingly Simple Approach Improves Textual Graph Learning [131.04781590452308]
  We present SimTeG, a frustratingly Simple approach for Textual Graph learning. We first perform supervised parameter-efficient fine-tuning (PEFT) on a pre-trained LM on the downstream task. We then generate node embeddings using the last hidden states of finetuned LM.
  arXiv  Detail & Related papers  (2023-08-03T07:00:04Z)
• Optimal Propagation for Graph Neural Networks [51.08426265813481]
  We propose a bi-level optimization approach for learning the optimal graph structure. We also explore a low-rank approximation model for further reducing the time complexity.
  arXiv  Detail & Related papers  (2022-05-06T03:37:00Z)
• Robust Optimization as Data Augmentation for Large-scale Graphs [117.2376815614148]
  We propose FLAG (Free Large-scale Adversarial Augmentation on Graphs), which iteratively augments node features with gradient-based adversarial perturbations during training. FLAG is a general-purpose approach for graph data, which universally works in node classification, link prediction, and graph classification tasks.
  arXiv  Detail & Related papers  (2020-10-19T21:51:47Z)

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.