Loading [MathJax]/extensions/TeX/euler_ieee.js
Robust Optimization as Data Augmentation for Large-scale Graphs | IEEE Conference Publication | IEEE Xplore

Robust Optimization as Data Augmentation for Large-scale Graphs


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 ...Show More

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.
Date of Conference: 18-24 June 2022
Date Added to IEEE Xplore: 27 September 2022
ISBN Information:

ISSN Information:

Conference Location: New Orleans, LA, USA

References

References is not available for this document.