A Causality-Aligned Structure Rationalization Scheme Against Adversarial Biased Perturbations for Graph Neural Networks
The graph neural networks (GNNs) are susceptible to adversarial perturbations and distribution biases, which pose potential security concerns for real-world applications. Current endeavors mainly focus on graph matching, while the subtle relationships between the nodes and structures of graph-struct...
Saved in:
Main Authors: | JIA, Ju, MA, Siqi, LIU, Yang, WANG, Lina, DENG, Robert H. |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2023
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/8501 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
CAUSAL RECOMMENDER SYSTEMS
by: WANG WENJIE
Published: (2023) -
Fluorescence Correlation Methods for Imaging Cellular Behavior of Sphingolipid-Interacting Probes
by: Kraut, R., et al.
Published: (2014) -
APPLICATIONS OF PERTURBATION ANALYSIS IN PROBABILISTIC MODEL CHECKING
by: YAMILET ROSARIO SERRANO LLERENA
Published: (2018) -
Adversarial learning for coordinate regression through k-layer penetrating representation
by: JIANG, Mengxi, et al.
Published: (2024) -
ON MIXING RATES FOR RANDOM PERTURBATIONS
by: DU ZHIKUN
Published: (2015)