Options
Measuring the Feasibility of Analogical Transfer using Complexity
Publikationstyp
Conference Paper
Date Issued
2022-07
Sprache
English
Author(s)
First published in
Number in series
3174
Start Page
62
End Page
74
Citation
CEUR Workshop Proceedings 3174 : 62-74 (2022)
Contribution to Conference
Scopus ID
Publisher
RWTH Aachen
Analogies are 4-ary relations of the form “A is to B as C is to D". While focus has been mostly on how to solve an analogy, i.e. how to find correct values of D given A, B and C, less attention has been drawn on whether solving such an analogy was actually feasible. In this paper, we propose a quantification of the transferability of a source case (A and B) to solve a target problem C. This quantification is based on a complexity minimization principle which has been demonstrated to be efficient for solving analogies. We illustrate these notions on morphological analogies and show its connections with machine learning, and in particular with Unsupervised Domain Adaptation.
Subjects
Analogical reasoning
Analogical transfer
Domain adaptation
Minimum Message Length