고차원 매핑기법과 딥러닝 네트워크를 통한 정형데이터의 분류
Classification of Tabular Data using High-Dimensional Mapping and Deep Learning Network
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
최근 딥러닝은 다양한 분야에서 전통적인 기계학습에 비해 월등히 높은 성능을 보이고 있으며, 패턴인식을 위한보편적인 방법으로 자리 잡아 가고 있다. 하지만, 이에 비해 정형데이터를 사용하는 분류 문제에서는 여전히 머신러닝기법이 주류를 이루고 있다. 본 논문에서는 정형데이터를 고차원 텐서로 변환하는 네트워크 모듈을 제안하며, 이 모듈을보편적인 딥러닝 네트워크와 함께 구성하여 정형데이터의 분류 문제에 적용하였다. 제안된 방법은 4종의 데이터셋을활용하여 학습 및 검증되었으며, 제안된 방법은 90.22%의 평균 정확도를 달성하여, 최신 딥러닝 모델인 TabNet에 비해 2.55%p 높은 정확도를 보였다. 제안된 방법은 컴퓨터 비전 분야에서 높은 성능을 보이는 다양한 네트워크 구조를정형데이터에 활용할 수 있다는 점에서 의미가 있다.
Abstract
Deep learning has recently demonstrated conspicuous efficacy across diverse domains than traditional machine learning techniques, as the most popular approach for pattern recognition. The classification problems for tabular data, however, are remain for the area of traditional machine learning. This paper introduces a novel network module designed to tabular data into high-dimensional tensors. The module is integrated into conventional deep learning networks and subsequently applied to the classification of structured data. The proposed method undergoes training and validation on four datasets, culminating in an average accuracy of 90.22%. Notably, this performance surpasses that of the contemporary deep learning model, TabNet, by 2.55%p. The proposed approach acquires significance by virtue of its capacity to harness diverse network architectures, renowned for their superior performance in the domain of computer vision, for the analysis of tabular data.
참고문헌 (16)
- A. Krizhevsky, "ImageNet Classification with Deep Convolutional Neural Networks", Advances in Neural Information Processing Systems, 25 (2012)
- C. Szegedy, "Going Deeper with Convolutions", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.1~9 (2015)
- A. Dosovitskiy, "An Image is Worth 16x16 Words : Transformers for Image Recognition at Scale", International Conference on Learning Representations (2021)
- K. He, "Deep Residual Learning for Image Recognition", Computer Vision and Pattern Recognition, pp.770~778 (2016)
- B. Lim, "Temporal Fusion Transformers for Interpretable Multi-Horizon Time Series Forecasting", International Journal of Forecasting, 37(4), pp.1748~1764 (2021)
- J. Devlin, "BERT : Pre-Training of Deep Bidirectional Transformers for Language Understanding", Proceedings of the 2019Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 1, pp.1~ (2019)
- A. Vaswani, "Attention Is All You Need", Advances in Neural Information Processing systems, 30, pp.5998~6008 (2017)
- S. Ö. Arık, "Tabnet : Attentive Interpretable Tabular Learning", Proceedings of the AAAI Conference on Artificial Intelligence, 35(8), pp.6679~6687 (2021)
- R. Shwartz-Ziv, "Tabular Data : Deep Learning is Not All You Need", Information Fusion, 81, pp.84~90 (2022)
- V. Borisov, "Deep Neural Networks and Tabular Data : A Survey", IEEE Transactions on Neural Networks and Learning Systems (2022)
- I. Shavitt, "Regularization Learning Networks : Deep Learning for Tabulat Datasets", International Conference on Neural Information Processing Systems, 31, pp.1379~1389 (2018)
- G. Somepalli, "SAINT : Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training", arXiv : 2106. 01342, ~ (2021)
- L. Buturovic´, "A Novel Method for Classification of Tabular Data Using Convolutional Neural Network", BioRxiv, ~ (2020)
- M. I. Iqbal, "A Dynamic Weighted Tabular Method for Convolutional Neural Networks", IEEE Acces, 10, pp.134183~134198 (2022)
- Y. Zhu, "Converting Tabular Data into Images for Deep Learning With Convolutional Neural Networks", Scientific Reports, 11, pp.1~ (2021)
- T. Chen, "XGBoost : A Scalable Tree Boosting System", The 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp.785~794 (2016)