A Unified Manifold Similarity Measure Enhancing Few-Shot, Transfer, and Reinforcement Learning in Manifold-Distributed Datasets

TL;DR

This paper introduces a novel similarity measure for manifold structures that improves transfer learning, few-shot classification, and reinforcement learning in datasets with manifold distributions, especially when labels are scarce.

Contribution

The study presents a new method to assess manifold similarity and a few-shot learning approach that leverages transfer learning based on this similarity, enhancing performance in limited-label scenarios.

Findings

Effective manifold similarity measure for transfer learning

High accuracy in few-shot classification with limited labels

Successful application to reinforcement learning and image recognition

Abstract

Training a classifier with high mean accuracy from a manifold-distributed dataset can be challenging. This problem is compounded further when there are only few labels available for training. For transfer learning to work, both the source and target datasets must have a similar manifold structure. As part of this study, we present a novel method for determining the similarity between two manifold structures. This method can be used to determine whether the target and source datasets have a similar manifold structure suitable for transfer learning. We then present a few-shot learning method to classify manifold-distributed datasets with limited labels using transfer learning. Based on the base and target datasets, a similarity comparison is made to determine if the two datasets are suitable for transfer learning. A manifold structure and label distribution are learned from the base and target datasets. When the structures are similar, the manifold structure and its relevant label information from the richly labeled source dataset is transferred to target dataset. We use the transferred information, together with the labels and unlabeled data from the target dataset, to develop a few-shot classifier that produces high mean classification accuracy on manifold-distributed datasets. In the final part of this article, we discuss the application of our manifold structure similarity measure to reinforcement learning and image recognition.