Fair Differentiable Neural Network Architecture Search for Long-Tailed Data with Self-Supervised Learning

TL;DR

This paper proposes a fair differentiable neural architecture search method that integrates self-supervised learning to improve model performance on long-tailed datasets, addressing bias issues in traditional NAS.

Contribution

It introduces SSF-NAS, combining self-supervised learning with fair differentiable NAS techniques to enhance architecture search on imbalanced data.

Findings

SSF-NAS outperforms existing NAS methods on CIFAR10-LT

Integration of self-supervised learning improves long-tailed data handling

Experimental results validate the effectiveness of the proposed approach

Abstract

Recent advancements in artificial intelligence (AI) have positioned deep learning (DL) as a pivotal technology in fields like computer vision, data mining, and natural language processing. A critical factor in DL performance is the selection of neural network architecture. Traditional predefined architectures often fail to adapt to different data distributions, making it challenging to achieve optimal performance. Neural architecture search (NAS) offers a solution by automatically designing architectures tailored to specific datasets. However, the effectiveness of NAS diminishes on long-tailed datasets, where a few classes have abundant samples, and many have few, leading to biased models.In this paper, we explore to improve the searching and training performance of NAS on long-tailed datasets. Specifically, we first discuss the related works about NAS and the deep learning method for long-tailed datasets.Then, we focus on an existing work, called SSF-NAS, which integrates the self-supervised learning and fair differentiable NAS to making NAS achieve better performance on long-tailed datasets.An detailed description about the fundamental techniques for SSF-NAS is provided in this paper, including DARTS, FairDARTS, and Barlow Twins. Finally, we conducted a series of experiments on the CIFAR10-LT dataset for performance evaluation, where the results are align with our expectation.