Automated Data Augmentations for Graph Classification
- URL: http://arxiv.org/abs/2202.13248v1
- Date: Sat, 26 Feb 2022 23:00:34 GMT
- Title: Automated Data Augmentations for Graph Classification
- Authors: Youzhi Luo, Michael McThrow, Wing Yee Au, Tao Komikado, Kanji Uchino,
Koji Maruhash, Shuiwang Ji
- Abstract summary: We argue that the corechallenge of data augmentations lies in designing data transformations that preserve labels.
We propose GraphAug, a novelautomated data augmentation method aiming at computing label-invariant augmentations for graph classification.
- Score: 29.586994125536307
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Data augmentations are effective in improving the invariance of learning
machines. We argue that the corechallenge of data augmentations lies in
designing data transformations that preserve labels. This is
relativelystraightforward for images, but much more challenging for graphs. In
this work, we propose GraphAug, a novelautomated data augmentation method
aiming at computing label-invariant augmentations for graph
classification.Instead of using uniform transformations as in existing studies,
GraphAug uses an automated augmentationmodel to avoid compromising critical
label-related information of the graph, thereby producing
label-invariantaugmentations at most times. To ensure label-invariance, we
develop a training method based on reinforcementlearning to maximize an
estimated label-invariance probability. Comprehensive experiments show that
GraphAugoutperforms previous graph augmentation methods on various graph
classification tasks.
Related papers
- Contrastive General Graph Matching with Adaptive Augmentation Sampling [5.3459881796368505]
We introduce a novel Graph-centric Contrastive framework for Graph Matching (GCGM)
GCGM capitalizes on a vast pool of graph augmentations for contrastive learning, yet without needing any side information.
Our GCGM surpasses state-of-the-art self-supervised methods across various datasets.
arXiv Detail & Related papers (2024-06-25T01:08:03Z) - Through the Dual-Prism: A Spectral Perspective on Graph Data
Augmentation for Graph Classification [71.36575018271405]
We introduce the Dual-Prism (DP) augmentation method, comprising DP-Noise and DP-Mask.
We find that keeping the low-frequency eigenvalues unchanged can preserve the critical properties at a large scale when generating augmented graphs.
arXiv Detail & Related papers (2024-01-18T12:58:53Z) - Spectral Augmentations for Graph Contrastive Learning [50.149996923976836]
Contrastive learning has emerged as a premier method for learning representations with or without supervision.
Recent studies have shown its utility in graph representation learning for pre-training.
We propose a set of well-motivated graph transformation operations to provide a bank of candidates when constructing augmentations for a graph contrastive objective.
arXiv Detail & Related papers (2023-02-06T16:26:29Z) - COSTA: Covariance-Preserving Feature Augmentation for Graph Contrastive
Learning [64.78221638149276]
We show that the node embedding obtained via the graph augmentations is highly biased.
Instead of investigating graph augmentation in the input space, we propose augmentations on the hidden features.
We show that the feature augmentation with COSTA achieves comparable/better results than graph augmentation based models.
arXiv Detail & Related papers (2022-06-09T18:46:38Z) - Label-invariant Augmentation for Semi-Supervised Graph Classification [32.591130704357184]
Recently, contrastiveness-based augmentation surges a new climax in the computer vision domain.
Unlike images, it is much more difficult to design reasonable augmentations without changing the nature of graphs.
We propose a label-invariant augmentation for graph-structured data to address this challenge.
arXiv Detail & Related papers (2022-05-19T18:44:02Z) - Model-Agnostic Augmentation for Accurate Graph Classification [19.824105919844495]
Graph augmentation is an essential strategy to improve the performance of graph-based tasks.
In this work, we introduce five desired properties for effective augmentation.
Our experiments on social networks and molecular graphs show that NodeSam and SubMix outperform existing approaches in graph classification.
arXiv Detail & Related papers (2022-02-21T10:37:53Z) - Bootstrapping Informative Graph Augmentation via A Meta Learning
Approach [21.814940639910358]
In graph contrastive learning, benchmark methods apply various graph augmentation approaches.
Most of the augmentation methods are non-learnable, which causes the issue of generating unbeneficial augmented graphs.
We motivate our method to generate augmented graph by a learnable graph augmenter, called MEta Graph Augmentation (MEGA)
arXiv Detail & Related papers (2022-01-11T07:15:13Z) - Graph Contrastive Learning Automated [94.41860307845812]
Graph contrastive learning (GraphCL) has emerged with promising representation learning performance.
The effectiveness of GraphCL hinges on ad-hoc data augmentations, which have to be manually picked per dataset.
This paper proposes a unified bi-level optimization framework to automatically, adaptively and dynamically select data augmentations when performing GraphCL on specific graph data.
arXiv Detail & Related papers (2021-06-10T16:35:27Z) - Graph Contrastive Learning with Augmentations [109.23158429991298]
We propose a graph contrastive learning (GraphCL) framework for learning unsupervised representations of graph data.
We show that our framework can produce graph representations of similar or better generalizability, transferrability, and robustness compared to state-of-the-art methods.
arXiv Detail & Related papers (2020-10-22T20:13:43Z) - Robust Optimization as Data Augmentation for Large-scale Graphs [117.2376815614148]
We propose FLAG (Free Large-scale Adversarial Augmentation on Graphs), which iteratively augments node features with gradient-based adversarial perturbations during training.
FLAG is a general-purpose approach for graph data, which universally works in node classification, link prediction, and graph classification tasks.
arXiv Detail & Related papers (2020-10-19T21:51:47Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.