Through the Dual-Prism: A Spectral Perspective on Graph Data Augmentation for Graph Classification
Not on the map. Why?
Abstract (arXiv)
Graph Neural Networks have become the preferred tool to process graph data, with their efficacy being boosted through graph data augmentation techniques. Despite the evolution of augmentation methods, issues like graph property distortions and restricted structural changes persist. This leads to the question: Is it possible to develop more property-conserving and structure-sensitive augmentation methods? Through a spectral lens, we investigate the interplay between graph properties, their augmentation, and their spectral behavior, and observe that keeping the low-frequency eigenvalues unchanged can preserve the critical properties at a large scale when generating augmented graphs. These observations inform our introduction of the Dual-Prism (DP) augmentation methods, including DP-Noise and DP-Mask, which retain essential graph properties while diversifying augmented graphs. Extensive experiments validate the efficiency of our approach, providing a new and promising direction for graph data augmentation.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 37 of its 58 references that are in the map. First posted on arXiv 18 Jan 2024.
Builds on
37 of 58 references.
References · 37
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
- 2017Inductive Representation Learning on Large Graphscited by 6,284
- 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
- 2018How Powerful are Graph Neural Networks?cited by 4,355
- 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
- 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
- 2016node2vec: Scalable Feature Learning for Networkscited by 1,913
- 2016Variational Graph Auto-Encoderscited by 1,373
- 2020Graph Contrastive Learning with Augmentationscited by 1,203
- 2018Deep Graph Infomaxcited by 1,101
- 2019Strategies for Pre-training Graph Neural Networkscited by 964
- 2016Automatic chemical design using a data-driven continuous representation of moleculescited by 762
25 more
- 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 718
- 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 679
- 2020Contrastive Multi-View Representation Learning on Graphscited by 651
- 2019InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximizationcited by 441
- 2017Graph Signal Processing: Overview, Challenges and Applicationscited by 409
- 2021Beyond Low-frequency Information in Graph Convolutional Networkscited by 361
- 2021Spectral Temporal Graph Neural Network for Multivariate Time-series Forecastingcited by 298
- 2021Graph Contrastive Learning Automatedcited by 287
- 2019Revisiting Graph Neural Networks: All We Have is Low-Pass Filterscited by 260
- 2017graph2vec: Learning Distributed Representations of Graphscited by 228
- 2020Graph Random Neural Network for Semi-Supervised Learning on Graphscited by 213
- 2021Adversarial Graph Augmentation to Improve Graph Contrastive Learningcited by 200
- 2022G-Mixup: Graph Data Augmentation for Graph Classificationcited by 145
- 2023Spatio-Temporal Graph Neural Networks for Predictive Learning in Urban Computing: A Surveycited by 140
- 2022Data Augmentation for Deep Graph Learning: A Surveycited by 132
- 2020Graph signal processing for machine learning: A review and new perspectivescited by 73
- 2022Graph Data Augmentation for Graph Machine Learning: A Surveycited by 61
- 2022Revisiting Graph Contrastive Learning from the Perspective of Graph Spectrumcited by 43
- 2022Spectral Augmentation for Self-Supervised Learning on Graphscited by 38
- 2019Metrics for Graph Comparison: A Practitioner's Guidecited by 37
- 2021Graph Transplant: Node Saliency-Guided Graph Mixup with Local Structure Preservationcited by 30
- 2021A New Perspective on the Effects of Spectrum in Graph Neural Networkscited by 24
- 2022Model-Agnostic Augmentation for Accurate Graph Classificationcited by 21
- 2023Graph Mixup with Soft Alignmentscited by 15
- 2023Towards Expressive Spectral-Temporal Graph Neural Networks for Time Series Forecastingcited by 8
Built on by
Citing papers per year: 2024: 1; 2025: 1.
2 papers.