Feature-aware Modulation for Learning from Temporal Tabular Data

TL;DR

This paper introduces a feature-aware temporal modulation technique that dynamically adjusts feature representations based on temporal context, effectively addressing distribution shifts in temporal tabular data.

Contribution

We propose a novel feature-aware temporal modulation mechanism that aligns feature semantics over time, enhancing model robustness and adaptability to temporal distribution shifts.

Findings

Improves handling of temporal distribution shifts in tabular data

Achieves better generalization and adaptability balance

Validated on benchmark datasets

Abstract

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.