Probabilistic Entity Representation Model for Reasoning over Knowledge Graphs

dc.contributor.authorChoudhary, Nurendraen
dc.contributor.authorRao, Nikhilen
dc.contributor.authorKatariya, Sumeeten
dc.contributor.authorSubbian, Karthiken
dc.contributor.authorReddy, Chandan K.en
dc.date.accessioned2022-02-06T04:47:58Zen
dc.date.available2022-02-06T04:47:58Zen
dc.date.issued2021-10-26en
dc.date.updated2022-02-06T04:47:57Zen
dc.description.abstractLogical reasoning over Knowledge Graphs (KGs) is a fundamental technique that can provide efficient querying mechanism over large and incomplete databases. Current approaches employ spatial geometries such as boxes to learn query representations that encompass the answer entities and model the logical operations of projection and intersection. However, their geometry is restrictive and leads to non-smooth strict boundaries, which further results in ambiguous answer entities. Furthermore, previous works propose transformation tricks to handle unions which results in non-closure and, thus, cannot be chained in a stream. In this paper, we propose a Probabilistic Entity Representation Model (PERM) to encode entities as a Multivariate Gaussian density with mean and covariance parameters to capture its semantic position and smooth decision boundary, respectively. Additionally, we also define the closed logical operations of projection, intersection, and union that can be aggregated using an end-to-end objective function. On the logical query reasoning problem, we demonstrate that the proposed PERM significantly outperforms the state-of-the-art methods on various public benchmark KG datasets on standard evaluation metrics. We also evaluate PERM’s competence on a COVID-19 drugrepurposing case study and show that our proposed work is able to recommend drugs with substantially better F1 than current methods. Finally, we demonstrate the working of our PERM’s query answering process through a low-dimensional visualization of the Gaussian representations.en
dc.description.versionAccepted versionen
dc.format.mimetypeapplication/pdfen
dc.identifier.orcidReddy, Chandan [0000-0003-2839-3662]en
dc.identifier.urihttp://hdl.handle.net/10919/108149en
dc.language.isoenen
dc.rightsIn Copyrighten
dc.rights.urihttp://rightsstatements.org/vocab/InC/1.0/en
dc.titleProbabilistic Entity Representation Model for Reasoning over Knowledge Graphsen
dc.typeArticle - Refereeden
dc.type.dcmitypeTexten
pubs.organisational-group/Virginia Techen
pubs.organisational-group/Virginia Tech/Engineeringen
pubs.organisational-group/Virginia Tech/Engineering/Computer Scienceen
pubs.organisational-group/Virginia Tech/Faculty of Health Sciencesen
pubs.organisational-group/Virginia Tech/All T&R Facultyen
pubs.organisational-group/Virginia Tech/Engineering/COE T&R Facultyen

Files

Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
NeurIPS21[1].pdf
Size:
1.25 MB
Format:
Adobe Portable Document Format
Description:
Accepted version