Feature-aware Modulation for Learning from Temporal Tabular Data
–arXiv.org Artificial Intelligence
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.
arXiv.org Artificial Intelligence
Dec-4-2025
- Country:
- Asia > China
- Jiangsu Province > Nanjing (0.04)
- North America > Montserrat (0.04)
- Asia > China
- Genre:
- Research Report > New Finding (0.46)
- Industry:
- Health & Medicine (0.46)
- Technology: