Small Sample Learning in Big Data Era

TL;DR

This paper surveys Small Sample Learning (SSL), a promising AI paradigm, discussing its techniques, categories, neuroscience basis, challenges, and future directions, highlighting its role in mimicking human learning with limited data.

Contribution

It provides a comprehensive overview of SSL techniques, categorizing them into concept and experience learning, and discusses their relation to human cognition and future research challenges.

Findings

SSL techniques are mainly divided into concept and experience learning.

Neuroscience evidence supports the rationality of SSL approaches.

The paper discusses key challenges and future directions in SSL research.

Abstract

As a promising area in artificial intelligence, a new learning paradigm, called Small Sample Learning (SSL), has been attracting prominent research attention in the recent years. In this paper, we aim to present a survey to comprehensively introduce the current techniques proposed on this topic. Specifically, current SSL techniques can be mainly divided into two categories. The first category of SSL approaches can be called "concept learning", which emphasizes learning new concepts from only few related observations. The purpose is mainly to simulate human learning behaviors like recognition, generation, imagination, synthesis and analysis. The second category is called "experience learning", which usually co-exists with the large sample learning manner of conventional machine learning. This category mainly focuses on learning with insufficient samples, and can also be called small data learning in some literatures. More extensive surveys on both categories of SSL techniques are introduced and some neuroscience evidences are provided to clarify the rationality of the entire SSL regime, and the relationship with human learning process. Some discussions on the main challenges and possible future research directions along this line are also presented.