3 papers
cs.LG2025
Comparing Task-Agnostic Embedding Models for Tabular Data
Frederik Hoppe, Lars Kleinemeier, Astrid Franz +1
Recent foundation models for tabular data achieve strong task-specific performance via in-context learning. Nevertheless, they focus on direct prediction by encapsulating both repr…
cs.LG2025
Universal Embeddings of Tabular Data
Astrid Franz, Frederik Hoppe, Marianne Michaelis +1
Tabular data in relational databases represents a significant portion of industrial data. Hence, analyzing and interpreting tabular data is of utmost importance. Application tasks…
cs.LG2025
Generating Synthetic Relational Tabular Data via Structural Causal Models
Frederik Hoppe, Astrid Franz, Lars Kleinemeier +1
Synthetic tabular data generation has received increasing attention in recent years, particularly with the emergence of foundation models for tabular data. The breakthrough success…