Beyond One-Size-Fits-All: Adaptive Subgraph Denoising for Zero-Shot Graph Learning with Large Language Models

2026-03-03

AI Summary

This work addresses the challenge in zero-shot graph learning where generic subgraph extraction strategies often introduce structural noise, thereby degrading the reasoning performance of large language models. To overcome this limitation, the authors propose GraphSSR, a novel framework that implements a task-adaptive “Sampling–Selection–Reasoning” (SSR) pipeline for subgraph extraction and denoising. GraphSSR introduces a dynamic denoising mechanism that adapts to task-specific contexts and integrates SSR-SFT (supervised fine-tuning) with a two-stage reinforcement learning strategy—SSR-RL—that incorporates both fidelity enhancement and denoising augmentation. This approach transcends the constraints of conventional static subgraph extraction methods. Experimental results demonstrate that GraphSSR significantly improves zero-shot graph reasoning accuracy, enabling models to achieve high-precision predictions based on cleaner, more concise subgraphs.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Reasoning under Uncertainty: Graphical Models
• Knowledge Representation and Reasoning: Computational Complexity of Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Graph-based tasks in the zero-shot setting remain a significant challenge due to data scarcity and the inability of traditional Graph Neural Networks (GNNs) to generalize to unseen domains or label spaces. While recent advancements have transitioned toward leveraging Large Language Models (LLMs) as predictors to enhance GNNs, these methods often suffer from cross-modal alignment issues. A recent paradigm (i.e., Graph-R1) overcomes the aforementioned architectural dependencies by adopting a purely text-based format and utilizing LLM-based graph reasoning, showing improved zero-shot generalization. However, it employs a task-agnostic, one-size-fits-all subgraph extraction strategy, which inevitably introduces significant structural noise--irrelevant neighbors and edges--that distorts the LLMs' receptive field and leads to suboptimal predictions. To address this limitation, we introduce GraphSSR, a novel framework designed for adaptive subgraph extraction and denoising in zero-shot LLM-based graph reasoning. Specifically, we propose the SSR pipeline, which dynamically tailors subgraph extraction to specific contexts through a "Sample-Select-Reason" process, enabling the model to autonomously filter out task-irrelevant neighbors and overcome the one-size-fits-all issue. To internalize this capability, we develop SSR-SFT, a data synthesis strategy that generates high-quality SSR-style graph reasoning traces for supervised fine-tuning of LLMs. Furthermore, we propose SSR-RL, a two-stage reinforcement learning framework that explicitly regulates sampling and selection operations within the proposed SSR pipeline designed for adaptive subgraph denoising. By incorporating Authenticity-Reinforced and Denoising-Reinforced RL, we guide the model to achieve accurate predictions using parsimonious, denoised subgraphs for reasoning.

Problem

• zero-shot graph learning
• subgraph denoising
• large language models
• structural noise
• task-agnostic subgraph extraction

Innovation

• adaptive subgraph extraction
• zero-shot graph learning
• LLM-based graph reasoning
• subgraph denoising
• reinforcement learning