Complex-Valued Embeddings of Generic Proximity Data

Maximilian Münch*, Michiel Straat, Michael Biehl, Frank-Michael Schleif

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

4 Citations (Scopus)
457 Downloads (Pure)


Proximities are at the heart of almost all machine learning methods. In a more generic view, objects are compared by a (symmetric) similarity or dissimilarity measure, which may not obey particular mathematical properties. This renders many machine learning methods invalid, leading to convergence problems and the loss of generalization behavior. In many cases, the preferred dissimilarity measure is not metric. If the input data are non-vectorial, like text sequences, proximity-based learning is used or embedding techniques can be applied. Standard embeddings lead to the desired fixed-length vector encoding, but are costly and are limited in preserving the full information. As an information preserving alternative, we propose a complex-valued vector embedding of proximity data, to be used in respective learning approaches. In particular, we address supervised learning and use extensions of prototype-based learning. The proposed approach is evaluated on a variety of standard benchmarks showing good performance compared to traditional techniques in processing non-metric or non-psd proximity data.
Original languageEnglish
Title of host publicationStructural, Syntactic, and Statistical Pattern Recognition
Subtitle of host publicationJoint IAPR International Workshops on Statistical Techniques in Pattern Recognition (SPR) and Structural and Syntactic Pattern Recognition (SSPR)
EditorsAndrea Torsello, Luca Rossi, Marcello Pelillo, Battista Biggio, Antonio Robles-Kelly
Place of PublicationCham
PublisherSpringer International Publishing
Number of pages10
ISBN (Electronic)978-3-030-73973-7
ISBN (Print)978-3-030-73973-7
Publication statusPublished - 2021

Publication series

NameLecture Notes in Computer Science


Dive into the research topics of 'Complex-Valued Embeddings of Generic Proximity Data'. Together they form a unique fingerprint.

Cite this