Enabling Mixed Effects Neural Networks for Diverse, Clustered Data Using Monte Carlo Methods
This addresses the need for better modeling of clustered data in fields like healthcare or social sciences, though it is an incremental improvement over prior mixed effects neural networks.
The paper tackles the problem of neural networks ignoring correlations in clustered data by proposing MC-GMENN, a Monte Carlo-based method for generalized mixed effects neural networks, which outperforms existing models in generalization, time complexity, and variance quantification, and handles multi-class tasks with multiple features.
Neural networks often assume independence among input data samples, disregarding correlations arising from inherent clustering patterns in real-world datasets (e.g., due to different sites or repeated measurements). Recently, mixed effects neural networks (MENNs) which separate cluster-specific 'random effects' from cluster-invariant 'fixed effects' have been proposed to improve generalization and interpretability for clustered data. However, existing methods only allow for approximate quantification of cluster effects and are limited to regression and binary targets with only one clustering feature. We present MC-GMENN, a novel approach employing Monte Carlo methods to train Generalized Mixed Effects Neural Networks. We empirically demonstrate that MC-GMENN outperforms existing mixed effects deep learning models in terms of generalization performance, time complexity, and quantification of inter-cluster variance. Additionally, MC-GMENN is applicable to a wide range of datasets, including multi-class classification tasks with multiple high-cardinality categorical features. For these datasets, we show that MC-GMENN outperforms conventional encoding and embedding methods, simultaneously offering a principled methodology for interpreting the effects of clustering patterns.