Spherical and hyperbolic embeddings of data
- Submitting institution
-
University of York
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 54874556
- Type
- D - Journal article
- DOI
-
10.1109/TPAMI.2014.2316836
- Title of journal
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Article number
- -
- First page
- 2255
- Volume
- 36
- Issue
- 11
- ISSN
- 0162-8828
- Open access status
- Out of scope for open access requirements
- Month of publication
- April
- Year of publication
- 2014
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
3
- Research group(s)
-
-
- Citation count
- 26
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This is the first method for embedding non-euclidean data in spherical and hyperbolic spaces of arbitrary dimension without optimisation. Proposes a very efficient non-iterative approximate embedding methods which is many times faster than previous methods and an optimisation step to provide very accurate results. Non-euclidean data is increasingly common, and this algorithm is a significant step forward in dealing with such data. Major output of EU FET project SIMBAD, rated excellent by all three external reviews. It has been influential on the development of hyperbolic GCNNs (Chami et al Stanford, Bachmann ETH).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -