Pre-trained Encoders for Global Child Development: Transfer Learning Enables Deployment in Data-Scarce Settings

Abstract

A large number of children experience preventable developmental delays each year, yet the deployment of machine learning in new countries has been stymied by a data bottleneck: reliable models require thousands of samples, while new programs begin with fewer than 100. We introduce the first pre-trained encoder for global child development, trained on 357,709 children across 44 countries using UNICEF survey data. With only 50 training samples, the pre-trained encoder achieves an average AUC of 0.65 (95% CI: 0.56-0.72), outperforming cold-start gradient boosting at 0.61 by 8-12% across regions. At N=500, the encoder achieves an AUC of 0.73. Zero-shot deployment to unseen countries achieves AUCs up to 0.84. We apply a transfer learning bound to explain why pre-training diversity enables few-shot generalization. These results establish that pre-trained encoders can transform the feasibility of ML for SDG 4.2.1 monitoring in resource-constrained settings.

@article{fahim2026pretrained,
  title   = {Pre-trained Encoders for Global Child Development: Transfer Learning Enables Deployment in Data-Scarce Settings},
  author  = {Md Muhtasim Munif Fahim and Md. Rezaul Karim},
  year    = {2026},
  journal = {arXiv preprint},
  eprint  = {2601.20987},
  archivePrefix = {arXiv},
  url     = {https://arxiv.org/abs/2601.20987},
}