.png){kind=icon}
Return
Lightweight-oriented classification using distillation learning and spatial information from tabular data
.png){kind=icon}
OA
AI
DOI：10.1016/j.asoc.2026.114798.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• We propose a lightweight model that effectively captures spatial information through a distillation learning approach. • Our method outperforms traditional approaches, showing superior results on two agriculture-related datasets for wine quality. • Beyond agriculture, we tested medical clinical datasets, where the model still outperformed traditional methods, proving cross-domain potential. • Our work broadens the applicability of deep learning to tabular data, enhancing model performance and generalization capabilities.
Keywords:
Lightweight-oriented model
Distillation learning
Deep learning
Tabular data processing
Spatial information
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
6.6
Papers:
1.4W
Citations:
4.8W
Organization
Cited Papers
Machine learning-based predictive modelling for the enhancement of wine quality.png)
SCIENTIFIC REPORTSOAAI
SCIENTIFIC REPORTSIF3.9
OAAIShareSaveClassification with 2-D convolutional neural networks for breast cancer diagnosisSCIENTIFIC REPORTSOAAI
SCIENTIFIC REPORTSIF3.9
OAAIShareSave
ShareSaveShareSaveEnhancing FT-Transformer With a Matérn-Driven Kolmogorov-Arnold Feature Tokenizer for Tabular Data-Based In-Bed Posture ClassificationIEEE Access
IEEE AccessIF0
PREAI
ShareSaveShareSaveShareSave
View more