Year: 2022
Type: preprint
Abstract: We define edit distance for hierarchically structured data compatible with the hierarchical multi-instance learning paradigm. Example of such data is dataset represented in JSON format where inner Array objects are interpreted as unordered bags of elements. We prove correct analytical properties of the defined distance.
Source: arXiv (Cornell University)
Authors: Šopík, Břetislav, Strenáčik, Tomáš
Language: English
Subfield: Computer Networks and Communications
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4289598809