SuperTML: Two-Dimensional Word Embedding for the Precognition on Structured Tabular Data
arXiv:1903.06246
Abstract
Tabular data is the most commonly used form of data in industry. Gradient Boosting Trees, Support Vector Machine, Random Forest, and Logistic Regression are typically used for classification tasks on tabular data. DNN models using categorical embeddings are also applied in this task, but all attempts thus far have used one-dimensional embeddings. The recent work of Super Characters method using two-dimensional word embeddings achieved the state of art result in text classification tasks, showcasing the promise of this new approach. 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. Experimental results have shown that the proposed SuperTML method had achieved state-of-the-art results on both large and small datasets.
9 pages, 5 figures, 3 tables. Accepted by CVPR2019 Precognition Workshop
References in corpus (7)
- Distributed Representations of Words and Phrases and their Compositionality
- DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
- How transferable are features in deep neural networks?
- Entity Embeddings of Categorical Variables
- MRAM Co-designed Processing-in-Memory CNN Accelerator for Mobile and IoT Applications
- Squared English Word: A Method of Generating Glyph to Use Super Characters for Sentiment Analysis
- Neural Feature Learning From Relational Database
Cited by in corpus (3)
- On the impact of selected modern deep-learning techniques to the performance and celerity of classification models in an experimental high-energy physics use case
- SuperCaptioning: Image Captioning Using Two-dimensional Word Embedding
- GnetSeg: Semantic Segmentation Model Optimized on a 224mW CNN Accelerator Chip at the Speed of 318FPS