S-Mixup: Structural Mixup for Graph Neural Networks

• URL: http://arxiv.org/abs/2308.08097v1
• Date: Wed, 16 Aug 2023 02:08:46 GMT
• Title: S-Mixup: Structural Mixup for Graph Neural Networks
• Authors: Junghurn Kim, Sukwon Yun, Chanyoung Park
• Abstract summary: We propose a novel mixup augmentation for node classification called Structural Mixup (S-Mixup) S-Mixup obtains pseudo-labels for unlabeled nodes in a graph along with their prediction confidence via a Graph Neural Network (GNN) classifier. We demonstrate the effectiveness of S-Mixup evaluated on the node classification task.
• Score: 18.681950665186005
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Existing studies for applying the mixup technique on graphs mainly focus on graph classification tasks, while the research in node classification is still under-explored. In this paper, we propose a novel mixup augmentation for node classification called Structural Mixup (S-Mixup). The core idea is to take into account the structural information while mixing nodes. Specifically, S-Mixup obtains pseudo-labels for unlabeled nodes in a graph along with their prediction confidence via a Graph Neural Network (GNN) classifier. These serve as the criteria for the composition of the mixup pool for both inter and intra-class mixups. Furthermore, we utilize the edge gradient obtained from the GNN training and propose a gradient-based edge selection strategy for selecting edges to be attached to the nodes generated by the mixup. Through extensive experiments on real-world benchmark datasets, we demonstrate the effectiveness of S-Mixup evaluated on the node classification task. We observe that S-Mixup enhances the robustness and generalization performance of GNNs, especially in heterophilous situations. The source code of S-Mixup can be found at \url{https://github.com/SukwonYun/S-Mixup}

Related papers

• GeoMix: Towards Geometry-Aware Data Augmentation [76.09914619612812]
  Mixup has shown considerable success in mitigating the challenges posed by limited labeled data in image classification. We propose Geometric Mixup (GeoMix), a simple and interpretable Mixup approach leveraging in-place graph editing.
  arXiv  Detail & Related papers  (2024-07-15T12:58:04Z)
• NodeMixup: Tackling Under-Reaching for Graph Neural Networks [27.393295683072406]
  Graph Neural Networks (GNNs) have become mainstream methods for solving the semi-supervised node classification problem. Due to the uneven location distribution of labeled nodes in the graph, labeled nodes are only accessible to a small portion of unlabeled nodes, leading to the emphunder-reaching issue. To tackle under-reaching for GNNs, we propose an architecture-agnostic method dubbed NodeMixup.
  arXiv  Detail & Related papers  (2023-12-20T13:56:27Z)
• On the Equivalence of Graph Convolution and Mixup [70.0121263465133]
  This paper investigates the relationship between graph convolution and Mixup techniques. Under two mild conditions, graph convolution can be viewed as a specialized form of Mixup. We establish this equivalence mathematically by demonstrating that graph convolution networks (GCN) and simplified graph convolution (SGC) can be expressed as a form of Mixup.
  arXiv  Detail & Related papers  (2023-09-29T23:09:54Z)
• Fused Gromov-Wasserstein Graph Mixup for Graph-level Classifications [44.15102300886821]
  We propose a novel graph mixup algorithm called FGWMixup, which seeks a midpoint of source graphs in the Fused Gromov-Wasserstein metric space. Experiments conducted on five datasets demonstrate that FGWMixup effectively improves the generalizability and robustness of GNNs.
  arXiv  Detail & Related papers  (2023-06-28T07:00:12Z)
• Graph Mixup with Soft Alignments [49.61520432554505]
  We study graph data augmentation by mixup, which has been used successfully on images. We propose S-Mixup, a simple yet effective mixup method for graph classification by soft alignments.
  arXiv  Detail & Related papers  (2023-06-11T22:04:28Z)
• Deep Graph Clustering via Mutual Information Maximization and Mixture Model [6.488575826304023]
  We introduce a contrastive learning framework for learning clustering-friendly node embedding. Experiments on real-world datasets demonstrate the effectiveness of our method in community detection.
  arXiv  Detail & Related papers  (2022-05-10T21:03:55Z)
• Exploiting Neighbor Effect: Conv-Agnostic GNNs Framework for Graphs with Heterophily [58.76759997223951]
  We propose a new metric based on von Neumann entropy to re-examine the heterophily problem of GNNs. We also propose a Conv-Agnostic GNN framework (CAGNNs) to enhance the performance of most GNNs on heterophily datasets.
  arXiv  Detail & Related papers  (2022-03-19T14:26:43Z)
• Learning Hierarchical Graph Neural Networks for Image Clustering [81.5841862489509]
  We propose a hierarchical graph neural network (GNN) model that learns how to cluster a set of images into an unknown number of identities. Our hierarchical GNN uses a novel approach to merge connected components predicted at each level of the hierarchy to form a new graph at the next level.
  arXiv  Detail & Related papers  (2021-07-03T01:28:42Z)
• GraphMixup: Improving Class-Imbalanced Node Classification on Graphs by Self-supervised Context Prediction [25.679620842010422]
  This paper presents GraphMixup, a novel mixup-based framework for improving class-imbalanced node classification on graphs. We develop a emphReinforcement Mixup mechanism to adaptively determine how many samples are to be generated by mixup for those minority classes. Experiments on three real-world datasets show that GraphMixup yields truly encouraging results for class-imbalanced node classification tasks.
  arXiv  Detail & Related papers  (2021-06-21T14:12:16Z)
• Sequential Graph Convolutional Network for Active Learning [53.99104862192055]
  We propose a novel pool-based Active Learning framework constructed on a sequential Graph Convolution Network (GCN) With a small number of randomly sampled images as seed labelled examples, we learn the parameters of the graph to distinguish labelled vs unlabelled nodes. We exploit these characteristics of GCN to select the unlabelled examples which are sufficiently different from labelled ones.
  arXiv  Detail & Related papers  (2020-06-18T00:55:10Z)

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.