Rows of a table are embedded by training a graph auto-encoder on a table-derived weighted graph, giving smaller universal embeddings than EmbDI-style random-walk embeddings on two Kaggle datasets.
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
-
Universal Embeddings of Tabular Data
Rows of a table are embedded by training a graph auto-encoder on a table-derived weighted graph, giving smaller universal embeddings than EmbDI-style random-walk embeddings on two Kaggle datasets.