• Corpus ID: 246863555

G-Mixup: Graph Data Augmentation for Graph Classification

  title={G-Mixup: Graph Data Augmentation for Graph Classification},
  author={Xiaotian Han and Zhimeng Jiang and Ninghao Liu and Xia Hu},
This work develops mixup for graph data . Mixup has shown superiority in improving the generalization and robustness of neural networks by interpolating features and labels between two random samples. Traditionally, Mixup can work on regular, grid-like, and Euclidean data such as image or tabular data. However, it is challenging to directly adopt Mixup to augment graph data because different graphs typically: 1) have different numbers of nodes; 2) are not readily aligned; and 3) have unique… 

GraphMAD: Graph Mixup for Data Augmentation using Data-Driven Convex Clustering

This work proposes to project graphs onto the latent space of continuous random graph models known as graphons, leverage convex clustering in this latent space to generate nonlinear data-driven mix up functions, and investigates the use of different mixup functions for labels and data samples.

ifMixup: Interpolating Graph Pair to Regularize Graph Classification

IfMixup is proposed, which adds dummy nodes to make two graphs have the same input size and then simultaneously performs linear in- terpolation between the aligned node feature vectors and the aligned edge representations of the two graphs, resulting in superior predictive accuracy to popular graph augmentation and GNN methods.

Data Augmentation for Deep Graph Learning: A Survey

A taxonomy for graph data augmentation is proposed and a structured review by categorizing the related work based on the augmented information modalities is provided, focusing on the two challenging problems in DGL (i.e., optimal graph learning and low-resource graph learning).

Data Augmentation for Graph Data: Recent Advancements

This survey of the existing GDA techniques based on different graph tasks provides a reference to the research community of GDA but also provides the necessary information to the researchers of other domains.

Data Augmentation on Graphs: A Survey

A comprehensively review and summarize the existing graph data augmentation (GDAug) techniques, which first summarize a variety of feasible taxonomies, and then classify existing GDAug studies based on fine-grained graph elements.

Data Augmentation for Deep Graph Learning

A taxonomy for graph data augmentation techniques is proposed and a structured review by categorizing the related work based on the augmented information modalities is provided, which summarizes the applications of graph data Augmentation in two representative problems in data-centric deep graph learning.

Every Node Counts: Improving the Training of Graph Neural Networks on Node Classification

This paper proposes novel objective terms for the training of GNNs for node classification, aiming to exploit all the available data and improve accuracy, and proposes a cross-validating gradients approach to enhance the learning from labelled data.

Out-Of-Distribution Generalization on Graphs: A Survey

This paper comprehensively survey OOD generalization on graphs and presents a detailed review of recent advances and categorizes existing methods into three classes from conceptually different perspectives, i.e., data, model, and learning strategy.

GraphTTA: Test Time Adaptation on Graph Neural Networks

A novel test time adaptation strategy named Graph Adversarial Pseudo Group Contrast (GAPGC), for graph neural networks TTA, to better adapt to the Out Of Distribution (OOD) test data and theoretical evidence that GAPGC can extract minimal sufficient information for the main task from information theory perspective is provided.

A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainability

A systematical survey of MixDA in terms of its taxonomy, methodology, applications, and explainability is provided to serve as a roadmap to MixDA techniques and application reviews while providing promising directions for researchers interested in this exciting area.



Mixup for Node and Graph Classification

The two-stage Mixup framework is proposed, which uses each node’s neighbors’ representations before Mixup for graph convolutions, which effectively regularizes popular graph neural networks for better generalization without increasing their time complexity.

GraphCrop: Subgraph Cropping for Graph Classification

A new method to regularize graph neural networks (GNNs) for better generalization in graph classification by preserving the valid structure contexts for graph classification, and enhances the popular GNNs to outperform the baseline methods.

Graph Transplant: Node Saliency-Guided Graph Mixup with Local Structure Preservation

This work presents the first Mixup-like graph augmentation method called Graph Transplant, which mixes irregular graphs in data space to be well defined on various scales of the graph and identifies the sub-structure as a mix unit that can preserve the local information.

Intrusion-Free Graph Mixup

This work theoretically proves that its mixing strategy can recover the source graphs from the mixed graph, and guarantees that the mixed graphs are manifold intrusion free, and empirically shows that the method can effectively regularize the graph classification learning, resulting in superior predictive accuracy over popular graph augmentation baselines.

Metropolis-Hastings Data Augmentation for Graph Neural Networks

This paper proposes a novel framework Metropolis-Hastings Data Augmentation (MH-Aug) that draws augmented graphs from an explicit target distribution for semi-supervised learning and demonstrates that MH-Aug can generate a sequence of samples according to the target distribution to improve the performance of GNNs.

GraphMix: Improved Training of GNNs for Semi-Supervised Learning

We present GraphMix, a regularization method for Graph Neural Network based semi-supervised object classification, whereby we propose to train a fully-connected network jointly with the graph neural

Data Augmentation for Graph Convolutional Network on Semi-Supervised Classification

This paper proposes an attentional integrating model to weighted sum the hidden node embeddings encoded by these GCNs into the final node embeddeddings, and conducts cosine similarity based cross operation on the original features to create new graph features, including new node attributes and new graph topologies.

Graph Data Augmentation for Graph Machine Learning: A Survey


Data Augmentation for Graph Neural Networks

This work shows that neural edge predictors can effectively encode class-homophilic structure to promote intra- class edges and demote inter-class edges in given graph structure, and introduces the GAug graph data augmentation framework, which leverages these insights to improve performance in GNN-based node classification via edge prediction.

Multi-Channel Graph Neural Networks

Motivated by the underlying mechanisms developed in convolutional neural networks, the MuchGNN is proposed, which defines the tailored graph convolutions to learn a series of graph channels at each layer, and shrink the graphs hierarchically to encode the pooled structures.