FSL-LFMG: Few-Shot Learning with Augmented Latent Features and Multitasking Generation for Enhancing Multiclass Classification on Tabular Data

Aviv Nur, Chun-Kit Ngan, Rolf Bardeli

2024

Abstract

In this work, we propose advancing ProtoNet that employs augmented latent features (LF) by an autoencoder and multitasking generation (MG) by STUNT in the few-shot learning (FSL) mechanism. Specifically, the achieved contributions to this work are threefold. First, we propose an FSL-LFMG framework to develop an end-to-end few-shot multiclass classification workflow on tabular data. This framework is composed of three main stages that include (i) data augmentation at the sample level utilizing autoencoders to generate augmented LF, (ii) data augmentation at the task level involving self-generating multitasks using the STUNT approach, and (iii) the learning process taking place on ProtoNet, followed by various model evaluations in our FSL mechanism. Second, due to the outlier and noise sensitivity of K-means clustering and the curse of dimensionality of Euclidean distance, we enhance and customize the STUNT approach by using K-medoids clustering that is less sensitive to noisy outliers and Manhattan distance that is the most preferable for high-dimensional data. Finally, we conduct an extensive experimental study on four diverse domain datasets—Net Promoter Score segmentation, Dry Bean type, Wine type, and Forest Cover type—to prove that our FSL-LFMG approach on the multiclass classification outperforms the Tree Ensemble models and the One-vs-the-rest classifiers by 7.8% in 1-shot and 2.5% in 5-shot learning.

Paper Citation

in Harvard Style

Nur A., Ngan C. and Bardeli R. (2024). FSL-LFMG: Few-Shot Learning with Augmented Latent Features and Multitasking Generation for Enhancing Multiclass Classification on Tabular Data. In Proceedings of the 16th International Joint Conference on Computational Intelligence - Volume 1: NCTA; ISBN 978-989-758-721-4, SciTePress, pages 531-542. DOI: 10.5220/0012934200003837

in Bibtex Style

@conference{ncta24,
author={Aviv Nur and Chun-Kit Ngan and Rolf Bardeli},
title={FSL-LFMG: Few-Shot Learning with Augmented Latent Features and Multitasking Generation for Enhancing Multiclass Classification on Tabular Data},
booktitle={Proceedings of the 16th International Joint Conference on Computational Intelligence - Volume 1: NCTA},
year={2024},
pages={531-542},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012934200003837},
isbn={978-989-758-721-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Computational Intelligence - Volume 1: NCTA
TI - FSL-LFMG: Few-Shot Learning with Augmented Latent Features and Multitasking Generation for Enhancing Multiclass Classification on Tabular Data
SN - 978-989-758-721-4
AU - Nur A.
AU - Ngan C.
AU - Bardeli R.
PY - 2024
SP - 531
EP - 542
DO - 10.5220/0012934200003837
PB - SciTePress