GCondNet: A Novel Method for Improving Neural Networks on Small High-Dimensional Tabular Data
This addresses a specific bottleneck in machine learning for tabular data analysis, offering a versatile framework for improving neural network performance in data-scarce scenarios.
The paper tackles the problem of neural networks struggling with high-dimensional small sample-size tabular data by proposing GCondNet, a method that leverages implicit structures through graphs and GNNs to condition parameters, resulting in outperformance over 14 standard and state-of-the-art methods on 12 real-world datasets.
Neural networks often struggle with high-dimensional but small sample-size tabular datasets. One reason is that current weight initialisation methods assume independence between weights, which can be problematic when there are insufficient samples to estimate the model's parameters accurately. In such small data scenarios, leveraging additional structures can improve the model's performance and training stability. To address this, we propose GCondNet, a general approach to enhance neural networks by leveraging implicit structures present in tabular data. We create a graph between samples for each data dimension, and utilise Graph Neural Networks (GNNs) to extract this implicit structure, and for conditioning the parameters of the first layer of an underlying predictor network. By creating many small graphs, GCondNet exploits the data's high-dimensionality, and thus improves the performance of an underlying predictor network. We demonstrate GCondNet's effectiveness on 12 real-world datasets, where it outperforms 14 standard and state-of-the-art methods. The results show that GCondNet is a versatile framework for injecting graph-regularisation into various types of neural networks, including MLPs and tabular Transformers. Code is available at https://github.com/andreimargeloiu/GCondNet.