Multi-branch of Attention Yields Accurate Results for Tabular Data

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Li, Xuechen, Li, Yupeng, Liu, Jian, Jin, Xiaolin, Hu, Xin
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916959504826368
author Li, Xuechen
Li, Yupeng
Liu, Jian
Jin, Xiaolin
Hu, Xin
author_facet Li, Xuechen
Li, Yupeng
Liu, Jian
Jin, Xiaolin
Hu, Xin
contents Tabular data inherently exhibits significant feature heterogeneity, but existing transformer-based methods lack specialized mechanisms to handle this property. To bridge the gap, we propose MAYA, an encoder-decoder transformer-based framework. In the encoder, we design a Multi-Branch of Attention (MBA) that constructs multiple parallel attention branches and averages the features at each branch, effectively fusing heterogeneous features while limiting parameter growth. Additionally, we employ collaborative learning with a dynamic consistency weight constraint to produce more robust representations. In the decoder stage, cross-attention is utilized to seamlessly integrate tabular data with corresponding label features. This dual-attention mechanism effectively captures both intra-instance and inter-instance interactions. We evaluate the proposed method on a wide range of datasets and compare it with other state-of-the-art transformer-based methods. Extensive experiments demonstrate that our model achieves superior performance among transformer-based methods in both tabular classification and regression tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2502_12507
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Multi-branch of Attention Yields Accurate Results for Tabular Data
Li, Xuechen
Li, Yupeng
Liu, Jian
Jin, Xiaolin
Hu, Xin
Machine Learning
Artificial Intelligence
Tabular data inherently exhibits significant feature heterogeneity, but existing transformer-based methods lack specialized mechanisms to handle this property. To bridge the gap, we propose MAYA, an encoder-decoder transformer-based framework. In the encoder, we design a Multi-Branch of Attention (MBA) that constructs multiple parallel attention branches and averages the features at each branch, effectively fusing heterogeneous features while limiting parameter growth. Additionally, we employ collaborative learning with a dynamic consistency weight constraint to produce more robust representations. In the decoder stage, cross-attention is utilized to seamlessly integrate tabular data with corresponding label features. This dual-attention mechanism effectively captures both intra-instance and inter-instance interactions. We evaluate the proposed method on a wide range of datasets and compare it with other state-of-the-art transformer-based methods. Extensive experiments demonstrate that our model achieves superior performance among transformer-based methods in both tabular classification and regression tasks.
title Multi-branch of Attention Yields Accurate Results for Tabular Data
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2502.12507