Aug 2026· Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2· 1 citation· 53 references
TL;DR
This work proposes PolarFormer, a novel framework for time series generation that addresses limitations through a polar decomposition-based discrete representation, and proposes a structurally decoupled generation strategy that models radial and angular token sequences jointly while leveraging their orthogonality to substantially reduce modeling complexity.
Abstract
Time series generation is essential for data augmentation and privacy-preserving analysis across many real-world domains. Recent progress in discrete token modeling~(DTM) has demonstrated strong potential by transforming continuous sequences into discrete representations and performing generation in the latent space. However, existing DTM-based methods, particularly VQ-VAE based methods, suffer from imprecise manifold modeling, severe codebook collapse, and high generative complexity caused by entangled latent attributes and heuristic sequence decomposition. In this work, we propose PolarFormer, a novel framework for time series generation that addresses these limitations through a polar decomposition-based discrete representation. Specifically, we decompose continuous latent embeddings into radial and angular components, and model them using two independent codebooks, enabling a multi-layer spherical-shell latent topology that more faithfully captures the underlying data manifold. To stabilize representation learning, we reinterpret VQ-VAE quantization as a Mixture-of-Experts routing process and introduce a load-balancing loss to effectively mitigate codebook collapse. In the generative stage, we further propose a structurally decoupled generation strategy that models radial and angular token sequences jointly while leveraging their orthogonality to substantially reduce modeling complexity. Extensive experiments on multiple datasets demonstrate that PolarFormer consistently achieves state-of-the-art performance in time series generation, validating its effectiveness in representation fidelity and generative quality. Our source code has been made publicly available at https://github.com/decisionintelligence/PolarFormer
A spectrally-aligned latent-flow time series generator, where the latent space for flow matching is trained to preserve dynamical properties that are relevant for the suitability of synthetic samples, and incorporating fine-tuning losses based on canonical signal representations helps overcome issues.
Wireless time-series generation is useful for emerging applications that will drive the adoption and integration of machine learning tasks within next-generation networks, such as waveform classification in shared spectrum bands and interpretation of the physical world through integrated sensing and communications. Unl...
Yi-Yang Li, Sai Shankar Narasimhan, Priam Alataris et al.· 0 citations
Extensive experiments show that the proposed Latent-Foresight approach learns more temporally coherent latent representations and consistently outperforms two-stage baselines across multiple future scene understanding tasks and prediction horizons, while eliminating separate training stages, including during high-resol...
Generative modeling has shown strong promise for multivariate time mseries (MTS) forecasting, especially scale to high-dimensional settings. Diffusion-based methods achieve competitive performance but typically require many sampling steps at inference. VAE-based non-iterative forecasting frameworks have therefore emerg...
Shi-Bo Feng, Wan-Jin Feng, Yang Qiu et al.· 0 citations
SphereVAE is proposed, which constrains the VAE latent space to the unit hypersphere and regularizes the latent distribution toward a uniform prior, so that information is encoded mainly by directional variation, providing a bounded geometric target for autoregressive prediction and reducing the risk of norm drift.
Hao-Yu Zhang, Jing-Bin Hu, Han-Ke Xie et al.· 0 citations
This work leverage pretrained score-based models as geometric priors and learn a vector field that evolves data along score-induced interpolation paths that supports generation at arbitrary timestamps and temporal super-resolution beyond the discretization of the training data.
Jan Tauberschmidt, Brian B. Moser, Stanislav Frolov et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.