Integrating Random Effects in Deep Neural Networks

1 code implementation • 7 Jun 2022 • Giora Simchoni, Saharon Rosset

We propose to use the mixed models framework to handle correlated data in DNNs.

Using Random Effects to Account for High-Cardinality Categorical Features and Repeated Measures in Deep Neural Networks

1 code implementation • NeurIPS 2021 • Giora Simchoni, Saharon Rosset

Our results show that treating high-cardinality categorical features as random effects leads to a significant improvement in prediction performance compared to state of the art alternatives.

Entity Embeddings