Small Sample Learning in Big Data Era

By Jun Shu, Zongben Xu, Deyu Meng. 2018

81 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Chao Yu
2. Jiming Liu
3. Shamim Nemati
4. Qian Zhao
5. Zongben Xu
6. Jun Shu
7. Jyoti Prakash Sahoo
8. Lixuan Yi

Citations in the corpus

• Reinforcement Learning in Healthcare: A Survey (2019, background): “Albeit conceptually reasonable, it is impossible to learn new things without sufficient exploration, while there still exist many domains lacking sufficient training samples, specifically in some healthcare domains [209].”
• Generalizing from a Few Examples (2019, neutral): “1In comparison to existing survey [104], they focus on concept learning and experience learning for small sample.”
• Meta-Weight-Net: Learning an Explicit Mapping For Sample Weighting (2019, methodology): “Inspired by meta-learning developments [47, 48, 49, 37, 50], recently some methods were proposed to learn an adaptive weighting scheme from data to make the learning more automatic and reliable.”
• A Two-Stage Approach to Few-Shot Learning for Image Recognition (2019, background): “For a more comprehensive survey on few-shot learning, one can refer to [47], [48].”
• A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities (2022, background): “In many previous papers [4], [5], [3], [118], metric learning is always introduced separately.”