Few-shot Learning for Unsupervised Feature Selection

TL;DR

This paper introduces a few-shot learning approach for unsupervised feature selection that effectively selects relevant features from limited unlabeled data by leveraging source tasks and permutation-invariant neural networks.

Contribution

It presents a novel few-shot learning framework for unsupervised feature selection using a feature selector and decoder trained on multiple source tasks.

Findings

Outperforms existing feature selection methods in experiments.

Effective in selecting relevant features with limited unlabeled data.

Utilizes permutation-invariant neural networks for task-specific encoding.

Abstract

We propose a few-shot learning method for unsupervised feature selection, which is a task to select a subset of relevant features in unlabeled data. Existing methods usually require many instances for feature selection. However, sufficient instances are often unavailable in practice. The proposed method can select a subset of relevant features in a target task given a few unlabeled target instances by training with unlabeled instances in multiple source tasks. Our model consists of a feature selector and decoder. The feature selector outputs a subset of relevant features taking a few unlabeled instances as input such that the decoder can reconstruct the original features of unseen instances from the selected ones. The feature selector uses the Concrete random variables to select features via gradient descent. To encode task-specific properties from a few unlabeled instances to the model, the Concrete random variables and decoder are modeled using permutation-invariant neural networks that take a few unlabeled instances as input. Our model is trained by minimizing the expected test reconstruction error given a few unlabeled instances that is calculated with datasets in source tasks. We experimentally demonstrate that the proposed method outperforms existing feature selection methods.