Weight Predictor Network with Feature Selection for Small Sample Tabular Biomedical Data

by   Andrei Margeloiu, et al.
University of Cambridge

Tabular biomedical data is often high-dimensional but with a very small number of samples. Although recent work showed that well-regularised simple neural networks could outperform more sophisticated architectures on tabular data, they are still prone to overfitting on tiny datasets with many potentially irrelevant features. To combat these issues, we propose Weight Predictor Network with Feature Selection (WPFS) for learning neural networks from high-dimensional and small sample data by reducing the number of learnable parameters and simultaneously performing feature selection. In addition to the classification network, WPFS uses two small auxiliary networks that together output the weights of the first layer of the classification model. We evaluate on nine real-world biomedical datasets and demonstrate that WPFS outperforms other standard as well as more recent methods typically applied to tabular data. Furthermore, we investigate the proposed feature selection mechanism and show that it improves performance while providing useful insights into the learning task.


FsNet: Feature Selection Network on High-dimensional Biological Data

Biological data are generally high-dimensional and require efficient mac...

Graph Convolutional Network-based Feature Selection for High-dimensional and Low-sample Size Data

Feature selection is a powerful dimension reduction technique which sele...

ProtoGate: Prototype-based Neural Networks with Local Feature Selection for Tabular Biomedical Data

Tabular biomedical data poses challenges in machine learning because it ...

A study of local optima for learning feature interactions using neural networks

In many fields such as bioinformatics, high energy physics, power distri...

Embedded methods for feature selection in neural networks

The representational capacity of modern neural network architectures has...

Online Feature Selection for Efficient Learning in Networked Systems

Current AI/ML methods for data-driven engineering use models that are mo...

Locally Sparse Networks for Interpretable Predictions

Despite the enormous success of neural networks, they are still hard to ...

Please sign up or login with your details

Forgot password? Click here to reset