Files and links (1)
SubmittedarXiv.org - Non-exclusive license to distribute, Open
Conference proceeding
Towards an Efficient and General Framework of Robust Training for Graph Neural Networks
ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), v 2020-, pp 8479-8483
May 2020
Abstract
Graph Neural Networks (GNNs) have made significant advances on several fundamental inference tasks. As a result, there is a surge of interest in using these models for making potentially important decisions in high-regret applications. However, despite GNNs' impressive performance, it has been observed that carefully crafted perturbations on graph structures (or nodes attributes) lead them to make wrong predictions. Presence of these adversarial examples raises serious security concerns. Most of the existing robust GNN design/training methods are only applicable to white-box settings where model parameters are known and gradient based methods can be used by performing convex relaxation of the discrete graph domain. More importantly, these methods are not efficient and scalable which make them infeasible in time sensitive tasks and massive graph datasets. To overcome these limitations, we propose a general framework which leverages the greedy search algorithms and zeroth-order methods to obtain robust GNNs in a generic and an efficient manner. On several applications, we show that the proposed techniques are significantly less computationally expensive and, in some cases, more robust than the state-of-the-art methods making them suitable to large-scale problems which were out of the reach of traditional robust training methods.
Metrics
Details
- Title
- Towards an Efficient and General Framework of Robust Training for Graph Neural Networks
- Creators
- Kaidi Xu - Northeastern UniversitySijia Liu - IBM Research,MIT-IBM Watson AI LabPin-Yu Chen - IBM Research,MIT-IBM Watson AI LabMengshu Sun - Northeastern UniversityCaiwen Ding - University of ConnecticutBhavya Kailkhura - Lawrence Livermore National LaboratoryXue Lin - Northeastern University
- Publication Details
- ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), v 2020-, pp 8479-8483
- Publisher
- IEEE
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- Computer Science (Computing)
- Web of Science ID
- WOS:000615970408150
- Scopus ID
- 2-s2.0-85091188093
- Other Identifier
- 991021871368404721
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Collaboration types
- Industry collaboration
- Domestic collaboration
- Web of Science research areas
- Acoustics
- Engineering, Electrical & Electronic