Data Augmentation for Deep Graph Learning: A Survey

• URL: http://arxiv.org/abs/2202.08235v1
• Date: Wed, 16 Feb 2022 18:30:33 GMT
• Title: Data Augmentation for Deep Graph Learning: A Survey
• Authors: Kaize Ding, Zhe Xu, Hanghang Tong and Huan Liu
• Abstract summary: We first propose a taxonomy for graph data augmentation and then provide a structured review by categorizing the related work based on the augmented information modalities. Focusing on the two challenging problems in DGL (i.e., optimal graph learning and low-resource graph learning), we also discuss and review the existing learning paradigms which are based on graph data augmentation.
• Score: 66.04015540536027
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Graph neural networks, as powerful deep learning tools to model graph-structured data, have demonstrated remarkable performance on numerous graph learning tasks. To counter the data noise and data scarcity issues in deep graph learning (DGL), increasing graph data augmentation research has been conducted lately. However, conventional data augmentation methods can hardly handle graph-structured data which is defined on non-Euclidean space with multi-modality. In this survey, we formally formulate the problem of graph data augmentation and further review the representative techniques in this field. Specifically, we first propose a taxonomy for graph data augmentation and then provide a structured review by categorizing the related work based on the augmented information modalities. Focusing on the two challenging problems in DGL (i.e., optimal graph learning and low-resource graph learning), we also discuss and review the existing learning paradigms which are based on graph data augmentation. Finally, we point out a few directions and challenges on promising future works.

Related papers

• Parametric Graph Representations in the Era of Foundation Models: A Survey and Position [69.48708136448694]
  Graphs have been widely used in the past decades of big data and AI to model comprehensive relational data. Identifying meaningful graph laws can significantly enhance the effectiveness of various applications.
  arXiv  Detail & Related papers  (2024-10-16T00:01:31Z)
• A Survey of Data-Efficient Graph Learning [16.053913182723143]
  We introduce a novel concept of Data-Efficient Graph Learning (DEGL) as a research frontier. We systematically review recent advances on several key aspects, including self-supervised graph learning, semi-supervised graph learning, and few-shot graph learning.
  arXiv  Detail & Related papers  (2024-02-01T09:28:48Z)
• Graph Domain Adaptation: Challenges, Progress and Prospects [61.9048172631524]
  We propose graph domain adaptation as an effective knowledge-transfer paradigm across graphs. GDA introduces a bunch of task-related graphs as source graphs and adapts the knowledge learnt from source graphs to the target graphs. We outline the research status and challenges, propose a taxonomy, introduce the details of representative works, and discuss the prospects.
  arXiv  Detail & Related papers  (2024-02-01T02:44:32Z)
• A Topology-aware Graph Coarsening Framework for Continual Graph Learning [8.136809136959302]
  Continual learning on graphs tackles the problem of training a graph neural network (GNN) where graph data arrive in a streaming fashion. Traditional continual learning strategies such as Experience Replay can be adapted to streaming graphs. We propose TA$mathbbCO$, a (t)opology-(a)ware graph (co)arsening and (co)ntinual learning framework.
  arXiv  Detail & Related papers  (2024-01-05T22:22:13Z)
• Data-centric Graph Learning: A Survey [37.849198493911736]
  We propose a novel taxonomy based on the stages in the graph learning pipeline. We analyze some potential problems embedded in graph data and discuss how to solve them in a data-centric manner.
  arXiv  Detail & Related papers  (2023-10-08T03:17:22Z)
• Towards Data-centric Graph Machine Learning: Review and Outlook [120.64417630324378]
  We introduce a systematic framework, Data-centric Graph Machine Learning (DC-GML), that encompasses all stages of the graph data lifecycle. A thorough taxonomy of each stage is presented to answer three critical graph-centric questions. We pinpoint the future prospects of the DC-GML domain, providing insights to navigate its advancements and applications.
  arXiv  Detail & Related papers  (2023-09-20T00:40:13Z)
• A Comprehensive Survey on Graph Summarization with Graph Neural Networks [21.337505372979066]
  In the past, most graph summarization techniques sought to capture the most important part of a graph statistically. Today, the high dimensionality and complexity of modern graph data are making deep learning techniques more popular. Our investigation includes a review of the current state-of-the-art approaches, including recurrent GNNs, convolutional GNNs, graph autoencoders, and graph attention networks.
  arXiv  Detail & Related papers  (2023-02-13T05:43:24Z)
• State of the Art and Potentialities of Graph-level Learning [54.68482109186052]
  Graph-level learning has been applied to many tasks including comparison, regression, classification, and more. Traditional approaches to learning a set of graphs rely on hand-crafted features, such as substructures. Deep learning has helped graph-level learning adapt to the growing scale of graphs by extracting features automatically and encoding graphs into low-dimensional representations.
  arXiv  Detail & Related papers  (2023-01-14T09:15:49Z)
• Learning Graph Structure from Convolutional Mixtures [119.45320143101381]
  We propose a graph convolutional relationship between the observed and latent graphs, and formulate the graph learning task as a network inverse (deconvolution) problem. In lieu of eigendecomposition-based spectral methods, we unroll and truncate proximal gradient iterations to arrive at a parameterized neural network architecture that we call a Graph Deconvolution Network (GDN) GDNs can learn a distribution of graphs in a supervised fashion, perform link prediction or edge-weight regression tasks by adapting the loss function, and they are inherently inductive.
  arXiv  Detail & Related papers  (2022-05-19T14:08:15Z)
• Graph Data Augmentation for Graph Machine Learning: A Survey [19.372562034069084]
  This paper aims to clarify the landscape of existing literature in graph data augmentation and motivate additional work in this area. We first categorize graph data augmentation operations based on the components of graph data they modify or create. Next, we introduce recent advances in graph data augmentation, separating by their learning objectives and methodologies.
  arXiv  Detail & Related papers  (2022-02-17T19:14:17Z)

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.