Robust Optimization as Data Augmentation for Large-scale Graphs

Kezhi Kong, Guohao Li, Mucong Ding, Zuxuan Wu, Chen Zhu, Bernard Ghanem, Gavin Taylor, Tom Goldstein

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Scopus citations

Abstract

Data augmentation helps neural networks generalize better by enlarging the training set, 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 manipulating graph topological structures by adding/removing edges, we offer a method to augment node features for better performance. We propose FLAG (Free Large-scale Adversarial Augmentation on Graphs), which iteratively augments node features with gradient-based adversarial perturbations during training. By making the model invariant to small fluctuations in input data, our method helps models generalize to out-of-distribution samples and boosts model performance at test time. FLAG is a general-purpose approach for graph data, which universally works in node classification, link prediction, and graph classification tasks. FLAG is also highly flexible and scalable, and is deployable with arbitrary GNN backbones and large-scale datasets. We demon-strate the efficacy and stability of our method through ex-tensive experiments and ablation studies. We also provide intuitive observations for a deeper understanding of our method. We open source our implementation at https://github.com/devnkong/FLAG.
Original languageEnglish (US)
Title of host publication2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
PublisherIEEE
Pages60-69
Number of pages10
DOIs
StatePublished - Sep 27 2022

Bibliographical note

KAUST Repository Item: Exported on 2022-12-19
Acknowledgements: Kezhi Kong and Tom Goldstein were supported by DARPA GARD, Office of Naval Research, AFOSR MURI program, the DARPA Young Faculty Award, and the National Science Foundation Division of Mathematical Sciences. Additional support was provided by Capital One Bank and JP Morgan Chase. Guohao Li and Bernard Ghanem were supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research through the Visual Computing Center (VCC) funding.

Fingerprint

Dive into the research topics of 'Robust Optimization as Data Augmentation for Large-scale Graphs'. Together they form a unique fingerprint.

Cite this