Tree edit distance for hierarchical data compatible with HMIL paradigm
arXiv:2208.00782v11 citationsh-index: 3
Originality Synthesis-oriented
AI Analysis
This work addresses a domain-specific need for structured data analysis, but it appears incremental as it builds on existing paradigms without broad impact claims.
The authors tackled the problem of measuring similarity for hierarchical data by defining an edit distance compatible with hierarchical multi-instance learning, and they proved its correct analytical properties.
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.