• Login
    View Item 
    •   Home
    • Research
    • Preprints
    • View Item
    •   Home
    • Research
    • Preprints
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Browse

    All of KAUSTCommunitiesIssue DateSubmit DateThis CollectionIssue DateSubmit Date

    My Account

    Login

    Quick Links

    Open Access PolicyORCID LibguidePlumX LibguideSubmit an Item

    Statistics

    Display statistics

    FLAG: Adversarial Data Augmentation for Graph Neural Networks

    • CSV
    • RefMan
    • EndNote
    • BibTex
    • RefWorks
    Thumbnail
    Name:
    Preprintfile1.pdf
    Size:
    426.2Kb
    Format:
    PDF
    Description:
    Pre-print
    Download
    Type
    Preprint
    Authors
    Kong, Kezhi
    Li, Guohao
    Ding, Mucong
    Wu, Zuxuan
    Zhu, Chen
    Ghanem, Bernard cc
    Taylor, Gavin
    Goldstein, Tom
    KAUST Department
    Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
    Electrical Engineering Program
    VCC Analytics Research Group
    Date
    2020-10-19
    Permanent link to this record
    http://hdl.handle.net/10754/665805
    
    Metadata
    Show full item record
    Abstract
    Data augmentation helps neural networks generalize better, but it remains an open question how to effectively augment graph data to enhance the performance of GNNs (Graph Neural Networks). While most existing graph regularizers focus on augmenting graph topological structures by adding/removing edges, we offer a novel direction to augment in the input node feature space for better performance. We propose a simple but effective solution, FLAG (Free Large-scale Adversarial Augmentation on Graphs), which iteratively augments node features with gradient-based adversarial perturbations during training, and boosts performance at test time. Empirically, FLAG can be easily implemented with a dozen lines of code and is flexible enough to function with any GNN backbone, on a wide variety of large-scale datasets, and in both transductive and inductive settings. Without modifying a model's architecture or training setup, FLAG yields a consistent and salient performance boost across both node and graph classification tasks. Using FLAG, we reach state-of-the-art performance on the large-scale ogbg-molpcba, ogbg-ppa, and ogbg-code datasets.
    Publisher
    arXiv
    arXiv
    2010.09891
    Additional Links
    https://arxiv.org/pdf/2010.09891
    Collections
    Preprints; Electrical Engineering Program; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

    entitlement

     
    DSpace software copyright © 2002-2021  DuraSpace
    Quick Guide | Contact Us | Send Feedback
    Open Repository is a service hosted by 
    Atmire NV
     

    Export search results

    The export option will allow you to export the current search results of the entered query to a file. Different formats are available for download. To export the items, click on the button corresponding with the preferred download format.

    By default, clicking on the export buttons will result in a download of the allowed maximum amount of items. For anonymous users the allowed maximum amount is 50 search results.

    To select a subset of the search results, click "Selective Export" button and make a selection of the items you want to export. The amount of items that can be exported at once is similarly restricted as the full export.

    After making a selection, click one of the export format buttons. The amount of items that will be exported is indicated in the bubble next to export format.