← Back to all news
arXiv Machine Learning By Yu-Hsiang Wang, Olgica Milenkovic

WaveletDiff: Multilevel Wavelet Diffusion For Time Series Generation

Read the original on arXiv Machine Learning →

WaveletDiff is a diffusion-based framework that generates time series by training directly on wavelet coefficients, leveraging multi-resolution structure through level‑specific transformers and cross‑level attention with adaptive gating. The model incorporates Parseval‑theorem‑based energy constraints to preserve time‑frequency properties during diffusion. Experiments on six real‑world datasets from energy, finance, and neuroscience show that WaveletDiff outperforms several diffusion baselines and competes with the VAE/transformer‑based MSDformer, achieving lower discriminative and Context‑FID scores while using fewer parameters and less training time.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Sep 25

Neuralized Multi-Wavelet Decomposition for Time Series Classification and Forecasting

The paper introduces m-WCN, an end‑to‑end deep learning framework that neuralizes multi‑wavelet decomposition to jointly extract temporal patterns and frequency components from time series. Two task‑specific architectures built on m‑WCN—TFBC for classification and FTB for forecasting—are shown to outperform baseline models on 64 UCR datasets and seven forecasting benchmarks, achieving average improvements of nearly 20% in both tasks. The approach leverages trainable convolutional operators and orthogonality constraints to produce interpretable multi‑resolution representations.

By Xiaohan Jiang, Jingyuan Wang, Jiahao Ji, Yongyao Wang, Chen Yang, Junjie Wu
benchmarks
More like this →
Hugging Face Trending Papers
Sep 24

Neuralized Multi-Wavelet Decomposition for Time Series Classification and Forecasting

The paper introduces m-WCN, an end‑to‑end deep learning framework that neuralizes multi‑wavelet decomposition to jointly extract temporal patterns and frequency components from time series. It enforces orthogonality constraints to produce interpretable multi‑resolution representations, and builds two task‑specific architectures—TFBC for classification and FTB for forecasting—on top of this foundation. Experiments on 64 UCR datasets and seven forecasting benchmarks show that TFBC and FTB outperform baseline models, achieving average improvements of about 20% in both classification and forecasting tasks.

benchmarks
More like this →
arXiv AI
Oct 1

Wavelet Flow Matching for Time Series

The paper introduces Wavelet Flow Matching, a method for generating multivariate time series by applying flow matching to multilevel discrete wavelet coefficients. By working in the wavelet domain, the model captures coarse-to-fine temporal structure implicitly and uses a channel-token transformer to model cross-channel dependencies. Experiments on seven benchmark datasets and four sequence lengths show that the approach matches or surpasses existing methods, especially in Context-FID and discriminative score metrics.

By Lucas Poinsignon, Jorge da Silva Gon\c{c}alves, Samuel Ruip\'erez-Campillo, Julia E. Vogt
llmsdiffusionbenchmarkssafety
More like this →