SuperTML: Two-Dimensional Word Embedding for the Precognition on Structured Tabular Data
[article]
Baohua Sun, Lin Yang, Wenhan Zhang, Michael Lin, Patrick Dong, Charles Young, Jason Dong
2019
arXiv
pre-print
In this paper, we propose the SuperTML method, which borrows the idea of Super Characters method and two-dimensional embeddings to address the problem of classification on tabular data. ...
For each input of tabular data, the features are first projected into two-dimensional embeddings like an image, and then this image is fed into fine-tuned two-dimensional CNN models for classification. ...
For each input, tabular features are first projected onto a two-dimensional embedding and fed into finetuned two-dimensional CNN models for classification. ...
arXiv:1903.06246v3
fatcat:bd35n4p5qfbadcoqbl4pn6llfe