Measuring the Feasibility of Analogical Transfer using Complexity
This work addresses the under-explored issue of transferability in analogical reasoning, which is incremental as it builds on existing complexity-based methods for solving analogies.
The paper tackles the problem of quantifying the feasibility of analogical transfer, proposing a method based on complexity minimization to measure how well a source case can solve a target problem, and demonstrates this on morphological analogies with connections to machine learning like Unsupervised Domain Adaptation.
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.