Matches in SemOpenAlex for { <https://semopenalex.org/work/W3177187794> ?p ?o ?g. }
Showing items 1 to 61 of
61
with 100 items per page.
- W3177187794 endingPage "15802" @default.
- W3177187794 startingPage "15801" @default.
- W3177187794 abstract "Learning low-dimensional embeddings of graph data in curved Riemannian manifolds has gained traction due to their desirable property of acting as effective geometrical inductive biases. More specifically, models of Hyperbolic geometry such as Poincar'{e} Ball and Lorentz/Hyperboloid Model have found applications for learning data with hierarchical anatomy. Gromov's hyperbolicity measures whether a graph can be isometrically embedded in hyperbolic space. This paper shows that adversarial attacks that perturb the network structure also affect the hyperbolicity of graphs rendering hyperbolic space less effective for learning low-dimensional node embeddings of the graph. To circumvent this problem, we introduce learning embeddings in pseudo-Riemannian manifolds such as Lorentzian manifolds and show empirically that they are robust to adversarial perturbations. Despite the recent proliferation of adversarial robustness methods in the graph data, this is the first work exploring the relationship between adversarial attacks and hyperbolicity while also providing resolution to navigate such vulnerabilities." @default.
- W3177187794 created "2021-07-05" @default.
- W3177187794 creator A5031053524 @default.
- W3177187794 creator A5073121051 @default.
- W3177187794 date "2021-05-18" @default.
- W3177187794 modified "2023-09-27" @default.
- W3177187794 title "Dethroning Aristocracy in Graphs via Adversarial Perturbations (Student Abstract)" @default.
- W3177187794 cites W2107940991 @default.
- W3177187794 cites W2265753182 @default.
- W3177187794 doi "https://doi.org/10.1609/aaai.v35i18.17897" @default.
- W3177187794 hasPublicationYear "2021" @default.
- W3177187794 type Work @default.
- W3177187794 sameAs 3177187794 @default.
- W3177187794 citedByCount "0" @default.
- W3177187794 crossrefType "journal-article" @default.
- W3177187794 hasAuthorship W3177187794A5031053524 @default.
- W3177187794 hasAuthorship W3177187794A5073121051 @default.
- W3177187794 hasBestOaLocation W31771877941 @default.
- W3177187794 hasConcept C132525143 @default.
- W3177187794 hasConcept C154945302 @default.
- W3177187794 hasConcept C192939610 @default.
- W3177187794 hasConcept C202444582 @default.
- W3177187794 hasConcept C2524010 @default.
- W3177187794 hasConcept C33923547 @default.
- W3177187794 hasConcept C37736160 @default.
- W3177187794 hasConcept C41008148 @default.
- W3177187794 hasConcept C80444323 @default.
- W3177187794 hasConcept C83677898 @default.
- W3177187794 hasConcept C99564226 @default.
- W3177187794 hasConceptScore W3177187794C132525143 @default.
- W3177187794 hasConceptScore W3177187794C154945302 @default.
- W3177187794 hasConceptScore W3177187794C192939610 @default.
- W3177187794 hasConceptScore W3177187794C202444582 @default.
- W3177187794 hasConceptScore W3177187794C2524010 @default.
- W3177187794 hasConceptScore W3177187794C33923547 @default.
- W3177187794 hasConceptScore W3177187794C37736160 @default.
- W3177187794 hasConceptScore W3177187794C41008148 @default.
- W3177187794 hasConceptScore W3177187794C80444323 @default.
- W3177187794 hasConceptScore W3177187794C83677898 @default.
- W3177187794 hasConceptScore W3177187794C99564226 @default.
- W3177187794 hasIssue "18" @default.
- W3177187794 hasLocation W31771877941 @default.
- W3177187794 hasOpenAccess W3177187794 @default.
- W3177187794 hasPrimaryLocation W31771877941 @default.
- W3177187794 hasRelatedWork W2945796017 @default.
- W3177187794 hasRelatedWork W2953770707 @default.
- W3177187794 hasRelatedWork W2964583308 @default.
- W3177187794 hasRelatedWork W3034334914 @default.
- W3177187794 hasRelatedWork W3052570231 @default.
- W3177187794 hasRelatedWork W3168561516 @default.
- W3177187794 hasRelatedWork W3177187794 @default.
- W3177187794 hasRelatedWork W4288293779 @default.
- W3177187794 hasRelatedWork W4302283439 @default.
- W3177187794 hasRelatedWork W4309127433 @default.
- W3177187794 hasVolume "35" @default.
- W3177187794 isParatext "false" @default.
- W3177187794 isRetracted "false" @default.
- W3177187794 magId "3177187794" @default.
- W3177187794 workType "article" @default.