Prior Knowledge for Few-shot Learning—Inductive Reasoning and Distribution Calibration

Anonymous

Keywords: few-shot learning, prior knowledge, distribution estimation, bias correction

Abstract: Few-shot learning is an important technique that can improve the learning capabilities of machine intelligence and practical adaptive applications. Previous researchers apply the meta-learning strategy to endow the new model with the ability or leverage transfer learning to alleviate the challenge of data-hungry. Moreover, prior knowledge such as knowledge graphs can also be modeled under the few-shot setting. This post gives an overview of recent works about how prior knowledge can address the problem of few-shot learning, and discusses a simple and efficient few-shot learning approach that estimates the novel class distributions derived inductively from the base classes.

ICLR Paper: https://openreview.net/forum?id=JWOiYxMG92s