Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Feature-aware Modulation for Learning from Temporal Tabular Data

About

While tabular machine learning has achieved remarkable success, temporal distribution shifts pose significant challenges in real-world deployment, as the relationships between features and labels continuously evolve. Static models assume fixed mappings to ensure generalization, whereas adaptive models may overfit to transient patterns, creating a dilemma between robustness and adaptability. In this paper, we analyze key factors essential for constructing an effective dynamic mapping for temporal tabular data. We discover that evolving feature semantics-particularly objective and subjective meanings-introduce concept drift over time. Crucially, we identify that feature transformation strategies are able to mitigate discrepancies in feature representations across temporal stages. Motivated by these insights, we propose a feature-aware temporal modulation mechanism that conditions feature representations on temporal context, modulating statistical properties such as scale and skewness. By aligning feature semantics across time, our approach achieves a lightweight yet powerful adaptation, effectively balancing generalizability and adaptability. Benchmark evaluations validate the effectiveness of our method in handling temporal shifts in tabular data.

Hao-Run Cai, Han-Jia Ye• 2025

Related benchmarks

TaskDatasetResultRank
Tabular LearningTabReD
AUC (HI)96.41
20
Tabular PredictionTabReD (original temporal splits)
HI AUC96.34
17
Tabular Data PredictionTabReD (random split)
HI0.9636
17
Showing 3 of 3 rows

Other info

Follow for update