Enhancing Burmese News Classification with Kolmogorov-Arnold Network Head Fine-tuning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Aung, Thura, Kyaw, Eaint Kay Khaing, Thu, Ye Kyaw, Oo, Thazin Myint, Supnithi, Thepchai
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912729925681152
author Aung, Thura
Kyaw, Eaint Kay Khaing
Thu, Ye Kyaw
Oo, Thazin Myint
Supnithi, Thepchai
author_facet Aung, Thura
Kyaw, Eaint Kay Khaing
Thu, Ye Kyaw
Oo, Thazin Myint
Supnithi, Thepchai
contents In low-resource languages like Burmese, classification tasks often fine-tune only the final classification layer, keeping pre-trained encoder weights frozen. While Multi-Layer Perceptrons (MLPs) are commonly used, their fixed non-linearity can limit expressiveness and increase computational cost. This work explores Kolmogorov-Arnold Networks (KANs) as alternative classification heads, evaluating Fourier-based FourierKAN, Spline-based EfficientKAN, and Grid-based FasterKAN-across diverse embeddings including TF-IDF, fastText, and multilingual transformers (mBERT, Distil-mBERT). Experimental results show that KAN-based heads are competitive with or superior to MLPs. EfficientKAN with fastText achieved the highest F1-score (0.928), while FasterKAN offered the best trade-off between speed and accuracy. On transformer embeddings, EfficientKAN matched or slightly outperformed MLPs with mBERT (0.917 F1). These findings highlight KANs as expressive, efficient alternatives to MLPs for low-resource language classification.
format Preprint
id arxiv_https___arxiv_org_abs_2511_21081
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Enhancing Burmese News Classification with Kolmogorov-Arnold Network Head Fine-tuning
Aung, Thura
Kyaw, Eaint Kay Khaing
Thu, Ye Kyaw
Oo, Thazin Myint
Supnithi, Thepchai
Computation and Language
Artificial Intelligence
Machine Learning
I.2.7; I.2.6
In low-resource languages like Burmese, classification tasks often fine-tune only the final classification layer, keeping pre-trained encoder weights frozen. While Multi-Layer Perceptrons (MLPs) are commonly used, their fixed non-linearity can limit expressiveness and increase computational cost. This work explores Kolmogorov-Arnold Networks (KANs) as alternative classification heads, evaluating Fourier-based FourierKAN, Spline-based EfficientKAN, and Grid-based FasterKAN-across diverse embeddings including TF-IDF, fastText, and multilingual transformers (mBERT, Distil-mBERT). Experimental results show that KAN-based heads are competitive with or superior to MLPs. EfficientKAN with fastText achieved the highest F1-score (0.928), while FasterKAN offered the best trade-off between speed and accuracy. On transformer embeddings, EfficientKAN matched or slightly outperformed MLPs with mBERT (0.917 F1). These findings highlight KANs as expressive, efficient alternatives to MLPs for low-resource language classification.
title Enhancing Burmese News Classification with Kolmogorov-Arnold Network Head Fine-tuning
topic Computation and Language
Artificial Intelligence
Machine Learning
I.2.7; I.2.6
url https://arxiv.org/abs/2511.21081