Feature-aware Modulation for Learning from Temporal Tabular Data
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
QuAIL: Quality-Aware Inertial Learning for Robust Training under Data Corruption
Tabular machine learning systems are frequently trained on data affected by non-uniform corruption, including noisy measurements, missing entries, and feature-specific biases. In practice, these defects are often documen…
Seq2Synth: Benchmarking Temporal Fidelity in Synthetic Sequential Tabular Data
Synthetic sequential tabular data are increasingly used for privacy-preserving data sharing and research, yet conventional tabular metrics often overlook temporal structure. Existing single-table and relational evaluatio…
FATA-Trans: Field And Time-Aware Transformer for Sequential Tabular Data
Sequential tabular data is one of the most commonly used data types in real-world applications. Different from conventional tabular data, where rows in a table are independent, sequential tabular data contains rich conte…
Language ModelingLanguage ModellingMasked Language ModelingModulation spectral features for speech emotion recognition using deep neural networks
This work explores the use of constant-Q transform based modulation spectral features (CQT-MSF) for speech emotion recognition (SER). The human perception and analysis of sound comprise of two important cognitive parts: …
Emotion RecognitionSpeech Emotion RecognitionExtending Tabular Denoising Diffusion Probabilistic Models for Time-Series Data Generation
Diffusion models are increasingly being utilised to create synthetic tabular and time series data for privacy-preserving augmentation. Tabular Denoising Diffusion Probabilistic Models (TabDDPM) generate high-quality synt…