Common-Description Learning: A Framework for Learning Algorithms and Generating Subproblems from Few Examples

TL;DR

This paper introduces common-description learning (CDL), a new framework that enables models to learn complex algorithms from few examples, with interpretable models that adaptively break down problems into simpler subproblems.

Contribution

The paper proposes a novel CDL framework that learns complex algorithms from limited data and produces interpretable models capable of recursive problem decomposition.

Findings

Successfully learned algorithms from few examples on 32 datasets

Models are perfectly interpretable and adapt their depth to problem complexity

Framework enhances language understanding by discovering complex data relations

Abstract

Current learning algorithms face many difficulties in learning simple patterns and using them to learn more complex ones. They also require more examples than humans do to learn the same pattern, assuming no prior knowledge. In this paper, a new learning framework is introduced that is called common-description learning (CDL). This framework has been tested on 32 small multi-task datasets, and the results show that it was able to learn complex algorithms from a few number of examples. The final model is perfectly interpretable and its depth depends on the question. What is meant by depth here is that whenever needed, the model learns to break down the problem into simpler subproblems and solves them using previously learned models. Finally, we explain the capabilities of our framework in discovering complex relations in data and how it can help in improving language understanding in machines.