Please use this identifier to cite or link to this item: http://oaps.umac.mo/handle/10692.1/359
Full metadata record
DC FieldValueLanguage
dc.contributor.authorCHOI, WAN IOI(蔡昀叡)-
dc.date.accessioned2024-07-16T08:54:08Z-
dc.date.available2024-07-16T08:54:08Z-
dc.date.issued2024-
dc.identifier.citationCHOI, W.I. (2024). Efficient Higher Order Self Attention Via Tensor Operations With Topology Enhanced Graph Neural Network For Molecular Graph Classification (Outstanding Academic Papers by Students (OAPS)). Retrieved from University of Macau, Outstanding Academic Papers by Students Repository.en_US
dc.identifier.urihttp://oaps.umac.mo/handle/10692.1/359-
dc.description.abstractWe modify a recently proposed higher order generalization of self attention mechanism and reduce its time complexity using tensor operations. Then the modified higher order self attention is applied to a graph neural network with a novel structural encoding based on cell complex from algebraic topology. Experiments on molecular graph benchmarks show that our modified higher order self attention is more efficient than the original higher order self attention, and our proposed structural encoding improves the performance of the graph neural network.en_US
dc.language.isoenen_US
dc.subjectself attentionen_US
dc.subjecttensor decompositionen_US
dc.subjectmolecular property predictionen_US
dc.subjectgraph neural networken_US
dc.subjectcell complexen_US
dc.titleEfficient Higher Order Self Attention Via Tensor Operations With Topology Enhanced Graph Neural Network For Molecular Graph Classificationen_US
dc.typeOAPSen_US
dc.contributor.departmentDepartment of Mathematicsen_US
dc.description.instructorProf. Kou Kit Ianen_US
dc.description.programmeBachelor of Science in Mathematics (Mathematics and Applications Stream)en_US
Appears in Collections:FST OAPS 2024



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.