DREAM: Dual-Standard Semantic Homogeneity with Dynamic Optimization for Graph Learning with Label Noise
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 50 of its 105 references that are in the map. First posted on arXiv 24 Jan 2026.
Builds on
50 of 105 references.
References · 50
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
- 2017Graph Attention Networkscited by 8,854
- 2017Inductive Representation Learning on Large Graphscited by 6,284
- 2018How Powerful are Graph Neural Networks?cited by 4,355
- 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
- 2019Simplifying Graph Convolutional Networkscited by 1,470
- 2020Graph Contrastive Learning with Augmentationscited by 1,203
- 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,099
- 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,053
- 2018Pitfalls of Graph Neural Network Evaluationcited by 994
- 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 718
- 2020Benchmarking Graph Neural Networkscited by 672
38 more
- 2016Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approachcited by 663
- 2019Symmetric Cross Entropy for Robust Learning with Noisy Labelscited by 499
- 2019How does Disagreement Help Generalization against Label Corruption?cited by 390
- 2019Unsupervised Label Noise Modeling and Loss Correctioncited by 327
- 2018Session-based Recommendation with Graph Neural Networkscited by 312
- 2020Combating noisy labels by agreement: A joint training method with co-regularizationcited by 289
- 2020Normalized Loss Functions for Deep Learning with Noisy Labelscited by 257
- 2020Does label smoothing mitigate label noise?cited by 204
- 2021Re-labeling ImageNet: from Single to Multi-Labels, from Global to Localized Labelscited by 117
- 2019Meta Label Correction for Noisy Label Learningcited by 108
- 2021FINE Samples for Learning with Noisy Labelscited by 82
- 2022UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learningcited by 77
- 2021NRGNN: Learning a Label Noise-Resistant Graph Neural Network on Sparsely and Noisily Labeled Graphscited by 73
- 2022Towards Robust Graph Neural Networks for Noisy Graphs with Sparse Labelscited by 63
- 2022The Devil is in the Labels: Noisy Label Correction for Robust Scene Graph Generationcited by 60
- 2020Graph Policy Network for Transferable Active Learning on Graphscited by 49
- 2022Investigating Why Contrastive Learning Benefits Robustness Against Label Noisecited by 46
- 2021ConsisRec: Enhancing GNN for Social Recommendation via Consistent Neighbor Aggregationcited by 39
- 2021Towards Understanding Deep Learning from Noisy Labels with Small-Loss Criterioncited by 36
- 2022Self-Filtering: A Noise-Aware Sample Selection for Label Noise with Confidence Penalizationcited by 33
- 2019Learning Graph Neural Networks with Noisy Labelscited by 29
- 2022GALAXY: Graph-based Active Learning at the Extremecited by 29
- 2022Robust Training of Graph Neural Networks via Noise Governancecited by 29
- 2022Uncertainty-Aware Learning Against Label Noise on Imbalanced Datasetscited by 28
- 2023Learning on Graphs under Label Noisecited by 22
- 2021Unified Robust Training for Graph NeuralNetworks against Label Noisecited by 21
- 2021Noise-robust Graph Learning by Estimating and Leveraging Pairwise Interactionscited by 20
- 2023Neural Relation Graph: A Unified Framework for Identifying Label Noise and Outlier Datacited by 20
- 2023Robust Data Pruning under Label Noise via Maximizing Re-labeling Accuracycited by 20
- 2020Weak-shot Fine-grained Classification via Similarity Transfercited by 18
- 2024Distributionally Robust Graph-based Recommendation Systemcited by 17
- 2024NoisyGL: A Comprehensive Benchmark for Graph Neural Networks under Label Noisecited by 16
- 2023ERASE: Error-Resilient Representation Learning on Graphs for Label Noise Tolerancecited by 11
- 2022Instance-dependent Label Distribution Estimation for Learning with Label Noisecited by 9
- 2023Regroup Median Loss for Combating Label Noisecited by 8
- 2023Interactive Reweighting for Mitigating Label Quality Issuescited by 7
- 2024Mitigating Label Noise on Graph via Topological Sample Selectioncited by 6
- 2025Uncertainty-Aware Graph Structure Learningcited by 4
Built on by
Not cited yet.