When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty

2025/05/20 by Wen, Yanzhe, Xunkai Li, Li, Xunkai +9
Computer Science · #Advanced Graph Neural Networks #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning in Healthcare #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2505.13989

openalex publication_date 2025/05/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Recently, large language models (LLMs) have significantly advanced text-attributed graph (TAG) learning. However, existing methods inadequately handle data uncertainty in open-world scenarios, especially concerning limited labeling and unknown-class nodes. Prior solutions typically rely on isolated semantic or structural approaches for unknown-class rejection, lacking effective annotation pipelines. To address these limitations, we propose Open-world Graph Assistant (OGA), an LLM-based framework that combines adaptive label traceability, which integrates semantics and topology for unknown-class rejection, and a graph label annotator to enable model updates using newly annotated nodes. Comprehensive experiments demonstrate OGA's effectiveness and practicality.

Citations

• Graph Synthetic Out-of-Distribution Exposure with Large Language Models
• Bounded and Uniform Energy-based Out-of-distribution Detection for Graphs
• Decoupled Graph Energy-based Model for Node Out-of-Distribution Detection on Heterophilic Graphs
• GOLD: Graph Out-of-Distribution Detection via Implicit Adversarial Latent Generation
• SAMGPT: Text-free Graph Foundation Model for Multi-domain Pre-training and Cross-domain Adaptation
• LEGO-Learn: Label-Efficient Graph Open-Set Learning
• GOFA: A Generative One-For-All Model for Joint Graph Language Modeling
• ARC: A Generalist Graph Anomaly Detector with In-Context Learning
• Graph Continual Learning with Debiased Lossless Memory Replay
• Beyond the Known: Novel Class Discovery for Open-world Graph Learning
• Open-World Semi-Supervised Learning for Node Classification
• Contrastive Augmented Graph2Graph Memory Interaction for Few Shot Continual Learning
• Label-free Node Classification on Graphs with Large Language Models (LLMS)
• Universal Graph Continual Learning
• Open-world Semi-supervised Novel Class Discovery
• Energy-based Out-of-Distribution Detection for Graph Neural Networks
• Reinforced Continual Learning for Graphs
• Hierarchical Prototype Networks for Continual Graph Representation Learning
• Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification
• Continual Learning of Knowledge Graph Embeddings
• Uncertainty Aware Semi-Supervised Learning on Graph Data
• Disentangle-based Continual Graph Representation Learning
• Graph-Based Continual Learning
• How Powerful are Graph Neural Networks?
• Graph Attention Networks
• Inductive Representation Learning on Large Graphs
• Semi-Supervised Classification with Graph Convolutional Networks
• GLIP-OOD: Zero-Shot Graph OOD Detection with Graph Foundation Model

Related

• Unlocking Graph Structure Learning with Tree-Guided Large Language Models
• Distilling Large Language Models for Text-Attributed Graph Learning
• Model Generalization on Text Attribute Graphs: Principles with Large Language Models
• Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks
• UniGraph: Learning a Unified Cross-Domain Foundation Model for Text-Attributed Graphs