DREAM: Dual-Standard Semantic Homogeneity with Dynamic Optimization for Graph Learning with Label Noise

2026-01-24

AI Summary

This work addresses the challenge that graph neural networks often struggle to discern node reliability under label noise and frequently overlook relational information embedded in graph topology. To tackle this issue, the authors propose DREAM, a method featuring a dynamic optimization framework that iteratively evaluates the reliability of node labels. DREAM introduces a dual-criterion anchor selection strategy that integrates node proximity with global topological structure, guided by semantic homophily to steer the optimization process. Notably, it is the first to incorporate a relation-aware dual-criterion semantic homophily mechanism, enabling robust handling of label noise. Extensive experiments on six cross-domain graph datasets demonstrate that DREAM consistently outperforms existing baselines across three distinct label noise settings, confirming its effectiveness and robustness.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

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

Abstract

Graph neural networks (GNNs) have been widely used in various graph machine learning scenarios. Existing literature primarily assumes well-annotated training graphs, while the reliability of labels is not guaranteed in real-world scenarios. Recently, efforts have been made to address the problem of graph learning with label noise. However, existing methods often (i) struggle to distinguish between reliable and unreliable nodes, and (ii) overlook the relational information embedded in the graph topology. To tackle this problem, this paper proposes a novel method, Dual-Standard Semantic Homogeneity with Dynamic Optimization (DREAM), for reliable, relation-informed optimization on graphs with label noise. Specifically, we design a relation-informed dynamic optimization framework that iteratively reevaluates the reliability of each labeled node in the graph during the optimization process according to the relation of the target node and other nodes. To measure this relation comprehensively, we propose a dual-standard selection strategy that selects a set of anchor nodes based on both node proximity and graph topology. Subsequently, we compute the semantic homogeneity between the target node and the anchor nodes, which serves as guidance for optimization. We also provide a rigorous theoretical analysis to justify the design of DREAM. Extensive experiments are performed on six graph datasets across various domains under three types of graph label noise against competing baselines, and the results demonstrate the effectiveness of the proposed DREAM.

Problem

• graph neural networks
• label noise
• semantic homogeneity
• graph topology
• node reliability

Innovation

• label noise
• graph neural networks
• semantic homogeneity
• dynamic optimization
• dual-standard selection