How Should Transformers Encode Numeric Values in Electronic Health Records?

arXiv:2607.01391v1 Announce Type: new Abstract: How do we encode numeric values in transformer-based sequence processing, particularly in electronic health record (EHR) data? We systematically compare discrete, continuous, and hybrid value encoding strategies using synthetic arithmetic tasks embedded within real-world EHR data, as well as real-world clinical prediction tasks. Our study reveals trade-offs between numeric precision, optimisation stability, and architectural flexibility. We find th...

arXiv cs.LG ·Maria Elkj{\ae}r Montgomery, Christian Igel, Mikkel Odgaard, Martin Sillesen, Mads Nielsen ·
compartilhar: