Matches in SemOpenAlex for { <https://semopenalex.org/work/W4298083795> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W4298083795 abstract "Graph neural network (GNN) is achieving remarkable performances in a variety of application domains. However, GNN is vulnerable to noise and adversarial attacks in input data. Making GNN robust against noises and adversarial attacks is an important problem. The existing defense methods for GNNs are computationally demanding and are not scalable. In this paper, we propose a generic framework for robustifying GNN known as Weighted Laplacian GNN (RWL-GNN). The method combines Weighted Graph Laplacian learning with the GNN implementation. The proposed method benefits from the positive semi-definiteness property of Laplacian matrix, feature smoothness, and latent features via formulating a unified optimization framework, which ensures the adversarial/noisy edges are discarded and connections in the graph are appropriately weighted. For demonstration, the experiments are conducted with Graph convolutional neural network(GCNN) architecture, however, the proposed framework is easily amenable to any existing GNN architecture. The simulation results with benchmark dataset establish the efficacy of the proposed method, both in accuracy and computational efficiency. Code can be accessed at https://github.com/Bharat-Runwal/RWL-GNN." @default.
- W4298083795 created "2022-10-01" @default.
- W4298083795 creator A5000738825 @default.
- W4298083795 creator A5044880204 @default.
- W4298083795 creator A5076285276 @default.
- W4298083795 date "2022-08-03" @default.
- W4298083795 modified "2023-09-29" @default.
- W4298083795 title "Robust Graph Neural Networks using Weighted Graph Laplacian" @default.
- W4298083795 doi "https://doi.org/10.48550/arxiv.2208.01853" @default.
- W4298083795 hasPublicationYear "2022" @default.
- W4298083795 type Work @default.
- W4298083795 citedByCount "0" @default.
- W4298083795 crossrefType "posted-content" @default.
- W4298083795 hasAuthorship W4298083795A5000738825 @default.
- W4298083795 hasAuthorship W4298083795A5044880204 @default.
- W4298083795 hasAuthorship W4298083795A5076285276 @default.
- W4298083795 hasBestOaLocation W42980837951 @default.
- W4298083795 hasConcept C11413529 @default.
- W4298083795 hasConcept C115178988 @default.
- W4298083795 hasConcept C119857082 @default.
- W4298083795 hasConcept C124101348 @default.
- W4298083795 hasConcept C132525143 @default.
- W4298083795 hasConcept C13280743 @default.
- W4298083795 hasConcept C134306372 @default.
- W4298083795 hasConcept C153180895 @default.
- W4298083795 hasConcept C154945302 @default.
- W4298083795 hasConcept C165700671 @default.
- W4298083795 hasConcept C185798385 @default.
- W4298083795 hasConcept C205649164 @default.
- W4298083795 hasConcept C33923547 @default.
- W4298083795 hasConcept C41008148 @default.
- W4298083795 hasConcept C48044578 @default.
- W4298083795 hasConcept C77088390 @default.
- W4298083795 hasConcept C80444323 @default.
- W4298083795 hasConcept C81363708 @default.
- W4298083795 hasConceptScore W4298083795C11413529 @default.
- W4298083795 hasConceptScore W4298083795C115178988 @default.
- W4298083795 hasConceptScore W4298083795C119857082 @default.
- W4298083795 hasConceptScore W4298083795C124101348 @default.
- W4298083795 hasConceptScore W4298083795C132525143 @default.
- W4298083795 hasConceptScore W4298083795C13280743 @default.
- W4298083795 hasConceptScore W4298083795C134306372 @default.
- W4298083795 hasConceptScore W4298083795C153180895 @default.
- W4298083795 hasConceptScore W4298083795C154945302 @default.
- W4298083795 hasConceptScore W4298083795C165700671 @default.
- W4298083795 hasConceptScore W4298083795C185798385 @default.
- W4298083795 hasConceptScore W4298083795C205649164 @default.
- W4298083795 hasConceptScore W4298083795C33923547 @default.
- W4298083795 hasConceptScore W4298083795C41008148 @default.
- W4298083795 hasConceptScore W4298083795C48044578 @default.
- W4298083795 hasConceptScore W4298083795C77088390 @default.
- W4298083795 hasConceptScore W4298083795C80444323 @default.
- W4298083795 hasConceptScore W4298083795C81363708 @default.
- W4298083795 hasLocation W42980837951 @default.
- W4298083795 hasOpenAccess W4298083795 @default.
- W4298083795 hasPrimaryLocation W42980837951 @default.
- W4298083795 hasRelatedWork W112744582 @default.
- W4298083795 hasRelatedWork W1666765134 @default.
- W4298083795 hasRelatedWork W1980318028 @default.
- W4298083795 hasRelatedWork W2348925352 @default.
- W4298083795 hasRelatedWork W2949389737 @default.
- W4298083795 hasRelatedWork W2963556241 @default.
- W4298083795 hasRelatedWork W2982368516 @default.
- W4298083795 hasRelatedWork W3085581207 @default.
- W4298083795 hasRelatedWork W3093612317 @default.
- W4298083795 hasRelatedWork W2624039590 @default.
- W4298083795 isParatext "false" @default.
- W4298083795 isRetracted "false" @default.
- W4298083795 workType "article" @default.