paper-with-me

홈 › Papers

Feature-aware Modulation for Learning from Temporal Tabular Data

2025-12-03 · Hao-Run Cai, Han-Jia Ye arxiv

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.

📄 PDF Abstract BibTeX arXiv:2512.03678

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

QuAIL: Quality-Aware Inertial Learning for Robust Training under Data Corruption

2026-02-03 · Mattia Sabella, Alberto Archetti, Pietro Pinoli, Matteo Matteucci 외 arxiv

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

2026-07-17 · Kiwan Kwon, Kangmin Kim, Hojin Lee, Yeseong Jung 외 arxiv

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

2023-10-20 · Dongyu Zhang, Liang Wang, Xin Dai, Shubham Jain 외

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 Modeling

Modulation spectral features for speech emotion recognition using deep neural networks

2023-01-14 · Premjeet Singh, Md Sahidullah, Goutam Saha

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 Recognition

Extending Tabular Denoising Diffusion Probabilistic Models for Time-Series Data Generation

2026-04-06 · Umang Dobhal, Christina Garcia, Sozo Inoue arxiv

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…