Modern tabular deep learning methods, including numerical embeddings, retrieval heads, and TabM ensembles, gain most of their advantage on high-data-uncertainty samples, and a triplet-trained embedding built from this insight outperforms standard embeddings.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Unveiling the Role of Data Uncertainty in Tabular Deep Learning
Modern tabular deep learning methods, including numerical embeddings, retrieval heads, and TabM ensembles, gain most of their advantage on high-data-uncertainty samples, and a triplet-trained embedding built from this insight outperforms standard embeddings.