Scaling Laws of Tabular Foundation Models: Efficiency and Few-Shot Adaptation Trade-offs

Abstract

Abstract: This report synthesises findings from 12 peer-reviewed papers addressing the following research question: How does the computational efficiency (measured in FLOPS or inference latency) of tabular foundation models scale with increasing sample diversity during training, and what trade-offs exist between. 15 claims were extracted from source literature; 4 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 6.2/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research Question

How does the computational efficiency (measured in FLOPS or inference latency) of tabular foundation models scale with increasing sample diversity during training, and what trade-offs exist between efficiency and few-shot adaptation performance on benchmark datasets?

Verification Level

Descriptive public verification status only; aggregate claim counts are public, but individual claim records are not exposed here.

Quality Tier

Descriptive public triage only; this tier does not alter current publication or DOI behavior.

Quality Dimensions

Automated triage signals derived from public fields; not human peer review or independent validation.

Correction Record

Public corrections are additive records. Current status does not claim the synthesis is error-free.

Provenance