cs.LGNov 16, 2026

FH-Sampling: Frequency-aware Hypergraph-driven Oversampling for Imbalanced Time-Series Classification

Authors: Yunrong Hao, Ruohao Dai, Zhen Liu, Guan Wang, Wenbin Pei, Qiang Zhang

Organizations: School of Computer Science and Technology, Dalian University of Technology, Dalian 116024, China · Key Laboratory of Social Computing and Cognitive Intelligence (Dalian University of Technology), Ministry of Education, Dalian 116024, China · School of Engineering and Computer Science, Victoria University of Wellington, PO Box 600, Wellington 6140, New Zealand · College of Computing and Data Science, Nanyang Technological University, Singapore · 

Abstract

Imbalanced time-series data appears commonly in diverse applications, such as medical diagnosis. When trained on imbalanced data, classifiers tend to exhibit a bias toward the majority class, making it difficult to identify minority-class instances accurately, despite their critical importance. Sampling techniques have proven effective in rebalancing imbalanced data. However, existing interpolation-based oversampling methods typically rely on pairwise interpolation, limiting their ability to capture high-order inter-sample relationships, and their inherent smoothing effects tend to suppress high-frequency components, compromising spectral fidelity. Therefore, we propose a Frequency-aware Hypergraph-driven Oversampling method (FH-Sampling) for imbalanced time-series classification. In FH-Sampling, a hypergraph is first constructed in the original time-series space to capture complex high-order inter-sample relationships, and sampling ratios are adaptively assigned to mitigate the impact of noisy samples. The discrete wavelet transform decomposes each sample into frequency components. Guided by the sample hypergraph, FH-Sampling combines high-frequency components from related samples while retaining the target sample's low-frequency component to help preserve important frequency characteristics. Experiments on 24 imbalanced datasets demonstrate the advantages of FH-Sampling for imbalanced time-series classification. We further apply FH-Sampling to aircraft trajectory generation. Experiments on simulated aircraft trajectories show that FH-Sampling produces trajectories that better match the real distribution, highlighting its potential for practical applications.

Figures & tables

Explore similar work

CardsList
  1. Contrastive Representation-Guided Genetic Minority Oversampling for Imbalanced Time-Series Classification

    Aug 24, 2026Wenbin Pei, Yunrong Hao, Zhen Liu +4Class-Imbalanced LearningSynthetic Data Augmentation

  2. HyFAD: Hybrid Time-Frequency Diffusion with Frequency-Aware Embedding for Time Series Imputation

    Jun 3, 2026Hongfan Gao, Wangmeng Shen, Bin Yang +1Frequency-Domain Time Series ModelingTime Series Imputation

  3. MedFlow: Class-Aware Multi-Scale Generation for Medical Time-Series Synthesis

    Sep 4, 2026Yanhao Huang, Shibo Feng, Wanjin Feng +2Flow MatchingSynthetic Data Generation