GraphMixup: Improving Class-Imbalanced Node Classification on Graphs by Self-supervised Context Prediction

Wu, Lirong; Lin, Haitao; Gao, Zhangyang; Tan, Cheng; Li, Stan Z.

doi:10.48550/arxiv.2106.11133

Cited by 9 publications

(14 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[45] take a further step to unify these approaches into a Bayesian graph learning framework. Besides, an advanced data augmentation strategy namely Mixup is recently applied to DGL and is proved to be effective for several graph-related tasks [115,123,128]. On the other hand, there are some studies trying to explicitly impose regularization to the hypothesis space, i.e., building GNN models with some predefined constrains or inductive bias, which share the similar idea with approaches demonstrated in Section 2.4.2. p-Laplacian based GNNs [37] introduces a discrete p-Laplacian regularization framework to derive a new message passing scheme and impose GNNs to be effective for both homophilic and heterophilic graphs as well as improved the robustness on graphs with noisy edges.…”

Section: Enhancing Techniquesmentioning

confidence: 99%

A Survey of Trustworthy Graph Learning: Reliability, Explainability, and Privacy Protection

Wu¹,

Li²,

Yu³

et al. 2022

Preprint

View full text Add to dashboard Cite

Deep graph learning has achieved remarkable progresses in both business and scientific areas ranging from finance and e-commerce, to drug and advanced material discovery. Despite these progresses, how to ensure various deep graph learning algorithms behave in a socially responsible manner and meet regulatory compliance requirements becomes an emerging problem, especially in risk-sensitive domains. Trustworthy graph learning (TwGL) aims to solve the above problems from a technical viewpoint. In contrast to conventional graph learning research which mainly cares about model performance, TwGL considers various reliability and safety aspects of the graph

show abstract

Section: Enhancing Techniquesmentioning

confidence: 99%

A Survey of Trustworthy Graph Learning: Reliability, Explainability, and Privacy Protection

Wu¹,

Li²,

Yu³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Recently, some efforts have been made to improve the imbalanced node classification [7], [18]- [21]. For instance, DPGNN [19] proposes a class prototype-driven training loss to maintain the balance of different classes.…”

Section: A Class Imbalance Problemmentioning

confidence: 99%

“…As the mixing of graph topology is not well-defined, and mixed nodes may interfere with each other, it is non-trivial to apply this technique to the graph domain. There have been some attempts addressing these difficulties [21], [46], [47]. For example, [46] uses a separate MLP network to conduct mixup and transfer the knowledge to the graph neural network.…”

Section: Mixupmentioning

confidence: 99%

“…However, it is designed from the independent and identical distribution (i.i.d) assumption and is unsuitable for relational data structures. There are some pioneering works for imbalanced node classification [18]- [21], but they mainly rely on re-weighting or few-shot learning and are essentially different from our objective: extending SMOTE to augment imbalanced graphs.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Synthetic Over-sampling for Imbalanced Node Classification with Graph Neural Networks

Zhao¹,

Zhang²,

Wang³

2022

Preprint

View full text Add to dashboard Cite

In recent years, graph neural networks (GNNs) have achieved state-of-the-art performance for node classification. However, most existing GNNs would suffer from the graph imbalance problem. In many real-world scenarios, node classes are imbalanced, with some majority classes making up most parts of the graph. The message propagation mechanism in GNNs would further amplify the dominance of those majority classes, resulting in sub-optimal classification performance. In this work, we seek to address this problem by generating pseudo instances of minority classes to balance the training data, extending previous over-sampling-based techniques. This task is non-trivial, as those techniques are designed with the assumption that instances are independent. Neglection of relation information would complicate this oversampling process. Furthermore, the node classification task typically takes the semi-supervised setting with only a few labeled nodes, providing insufficient supervision for the generation of minority instances. Generated new nodes of low quality would harm the trained classifier. In this work, we address these difficulties by synthesizing new nodes in a constructed embedding space, which encodes both node attributes and topology information. Furthermore, an edge generator is trained simultaneously to model the graph structure and provide relations for new samples. To further improve the data efficiency, we also explore synthesizing mixed "in-between" nodes to utilize nodes from the majority class in this over-sampling process. Experiments on real-world datasets validate the effectiveness of our proposed framework.

show abstract

“…It is forthwith another problem: it is hard to identify the subgroup and give them special treatment without enough data about the subgroup users within the favored group. Prior researchers had done lots of works on data augmentation for graph data, such as GraphSomte [46], GraphMixup [40,41], GraphCrop [39], which expanded the training set by generating synthetic data. However, most data augmentation strategies focus on mitigating the class-imbalance issue but are not designed to provide data to help detect subgroups.…”

Section: Computational Graphs Of the Gnnmentioning

confidence: 99%

Subgroup Fairness in Graph-based Spam Detection

Liu¹,

Lyu²,

Zhang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Fake reviews are prevalent on review websites such as Amazon and Yelp. GNN is the state-of-the-art method that can detect suspicious reviewers by exploiting the topologies of the graph connecting reviewers, reviews, and target products. However, the discrepancy in the detection accuracy over different groups of reviewers causes discriminative treatment of different reviewers of the websites, leading to less engagement and trustworthiness of such websites. The complex dependencies over the review graph introduce difficulties in teasing out subgroups of reviewers that are hidden within larger groups and are treated unfairly. There is no previous study that defines and discovers the subtle subgroups to improve equitable treatment of reviewers. In this paper, we address the challenges of defining, discovering, and utilizing subgroup memberships for fair spam detection. We first define a subgroup membership that can lead to discrepant accuracy in the subgroups. Since the subgroup membership is usually not observable while also important to guide the GNN detector to balance the treatment, we design a model that jointly infers the hidden subgroup memberships and exploits the membership for calibrating the target GNN's detection accuracy across subgroups. Comprehensive results on two large Yelp review datasets demonstrate that the proposed model can be trained to treat the subgroups more fairly.

show abstract

GraphMixup: Improving Class-Imbalanced Node Classification on Graphs by Self-supervised Context Prediction

Cited by 9 publications

References 22 publications

A Survey of Trustworthy Graph Learning: Reliability, Explainability, and Privacy Protection

A Survey of Trustworthy Graph Learning: Reliability, Explainability, and Privacy Protection

Synthetic Over-sampling for Imbalanced Node Classification with Graph Neural Networks

Subgroup Fairness in Graph-based Spam Detection

Contact Info

Product

Resources

About