GARNET: A Spectral Approach to Robust and Scalable Graph Neural Networks
Graph neural networks (GNNs) have been increasingly deployed in various applications that involve learning on non-Euclidean data. However, recent studies show that GNNs are vulnerable to graph adversarial attacks. Although there are several defense methods to improve GNN adversarial robustness, they fail to perform well on low homophily graphs. In addition, few of those defense models can scale to large graphs due to their high computational complexity and memory usage. In this paper, we propose GARNET, a scalable spectral method to boost the adversarial robustness of GNN models for both homophilic and heterophilic graphs. GARNET first computes a reduced-rank yet sparse approximation of the adversarial graph by exploiting an efficient spectral graph embedding and sparsification scheme. Next, GARNET trains an adaptive graph filter on the reduced-rank graph for node representation refinement, which is subsequently leveraged to guide label propagation for further enhancing the quality of node embeddings. GARNET has been evaluated on both homophilic and heterophilic datasets, including a large graph with millions of nodes. Our extensive experiment results show that GARNET increases adversarial accuracy over state-of-the-art GNN (defense) models by up to $9.96\%$ and $15.17\%$ on homophilic and heterophilic graphs, respectively.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial RobustnessGraph EmbeddingSimilar Papers 제목 키워드 기반
GARNET: Reduced-Rank Topology Learning for Robust and Scalable Graph Neural Networks
Graph neural networks (GNNs) have been increasingly deployed in various applications that involve learning on non-Euclidean data. However, recent studies show that GNNs are vulnerable to graph adversarial attacks. Althou…
Adversarial RobustnessMachine Learning guided high-throughput search of non-oxide garnets
Garnets, known since the early stages of human civilization, have found important applications in modern technologies including magnetorestriction, spintronics, lithium batteries, etc. The overwhelming majority of experi…
Band GapVocal Bursts Intensity PredictionLaGarNet: Goal-Conditioned Recurrent State-Space Models for Pick-and-Place Garment Flattening
We present a novel goal-conditioned recurrent state space (GC-RSSM) model capable of learning latent dynamics of pick-and-place garment manipulation. Our proposed method LaGarNet matches the state-of-the-art performance …
Towards Scalable Spectral Clustering via Spectrum-Preserving Sparsification
The eigendeomposition of nearest-neighbor (NN) graph Laplacian matrices is the main computational bottleneck in spectral clustering. In this work, we introduce a highly-scalable, spectrum-preserving graph sparsification …
ClusteringSF-SGL: Solver-Free Spectral Graph Learning from Linear Measurements
This work introduces a highly-scalable spectral graph densification framework (SGL) for learning resistor networks with linear measurements, such as node voltages and currents. We show that the proposed graph learning ap…
Graph Learning