Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385474429> ?p ?o ?g. }
Showing items 1 to 49 of
49
with 100 items per page.
- W4385474429 abstract "The use of graph neural networks has produced significant advances in point cloud problems, such as those found in high energy physics. The question of how to produce a graph structure in these problems is usually treated as a matter of heuristics, employing fully connected graphs or K-nearest neighbors. In this work, we elevate this question to utmost importance as the Topology Problem. We propose an attention mechanism that allows a graph to be constructed in a learned space that handles geometrically the flow of relevance, providing one solution to the Topology Problem. We test this architecture, called GravNetNorm, on the task of top jet tagging, and show that it is competitive in tagging accuracy, and uses far fewer computational resources than all other comparable models." @default.
- W4385474429 created "2023-08-02" @default.
- W4385474429 creator A5011421008 @default.
- W4385474429 date "2023-07-31" @default.
- W4385474429 modified "2023-09-23" @default.
- W4385474429 title "Graph Structure from Point Clouds: Geometric Attention is All You Need" @default.
- W4385474429 doi "https://doi.org/10.48550/arxiv.2307.16662" @default.
- W4385474429 hasPublicationYear "2023" @default.
- W4385474429 type Work @default.
- W4385474429 citedByCount "0" @default.
- W4385474429 crossrefType "posted-content" @default.
- W4385474429 hasAuthorship W4385474429A5011421008 @default.
- W4385474429 hasBestOaLocation W43854744291 @default.
- W4385474429 hasConcept C111919701 @default.
- W4385474429 hasConcept C114614502 @default.
- W4385474429 hasConcept C127705205 @default.
- W4385474429 hasConcept C131979681 @default.
- W4385474429 hasConcept C132525143 @default.
- W4385474429 hasConcept C154945302 @default.
- W4385474429 hasConcept C184720557 @default.
- W4385474429 hasConcept C33923547 @default.
- W4385474429 hasConcept C41008148 @default.
- W4385474429 hasConcept C80444323 @default.
- W4385474429 hasConceptScore W4385474429C111919701 @default.
- W4385474429 hasConceptScore W4385474429C114614502 @default.
- W4385474429 hasConceptScore W4385474429C127705205 @default.
- W4385474429 hasConceptScore W4385474429C131979681 @default.
- W4385474429 hasConceptScore W4385474429C132525143 @default.
- W4385474429 hasConceptScore W4385474429C154945302 @default.
- W4385474429 hasConceptScore W4385474429C184720557 @default.
- W4385474429 hasConceptScore W4385474429C33923547 @default.
- W4385474429 hasConceptScore W4385474429C41008148 @default.
- W4385474429 hasConceptScore W4385474429C80444323 @default.
- W4385474429 hasLocation W43854744291 @default.
- W4385474429 hasOpenAccess W4385474429 @default.
- W4385474429 hasPrimaryLocation W43854744291 @default.
- W4385474429 hasRelatedWork W1522517976 @default.
- W4385474429 hasRelatedWork W1708618853 @default.
- W4385474429 hasRelatedWork W1756885467 @default.
- W4385474429 hasRelatedWork W2034983601 @default.
- W4385474429 hasRelatedWork W2359226974 @default.
- W4385474429 hasRelatedWork W2560284304 @default.
- W4385474429 hasRelatedWork W2884576438 @default.
- W4385474429 hasRelatedWork W2905364337 @default.
- W4385474429 hasRelatedWork W3042941765 @default.
- W4385474429 hasRelatedWork W4236152845 @default.
- W4385474429 isParatext "false" @default.
- W4385474429 isRetracted "false" @default.
- W4385474429 workType "article" @default.