Metraipolis › archive › dc_00a12a6209fd

ProtoFlow: Prototype-Guided Flow Matching for Multivariate Time Series Forecasting — arXiv:2610.01320

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.01320
License (as archived): CC0-1.0
Archived: 2026-10-06T12:04:37.190Z
SHA-256 of the archived text: 8cc8c1f9ab9a0d3f1a5edc9c2610b5f152b727de38f4783dba87335973149e0a
Stable URL of this page: https://metraipolis.com/documento/dc_00a12a6209fd

How to cite

ProtoFlow: Prototype-Guided Flow Matching for Multivariate Time Series Forecasting — arXiv:2610.01320 — arXiv (en), https://arxiv.org/abs/2610.01320 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_00a12a6209fd (Metraipolis archive dc_00a12a6209fd, sha256 8cc8c1f9ab9a0d3f1a5edc9c2610b5f152b727de38f4783dba87335973149e0a)

BibTeX

@misc{dc00a12a6209fd,
  title = {ProtoFlow: Prototype-Guided Flow Matching for Multivariate Time Series Forecasting — arXiv:2610.01320},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.01320},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_00a12a6209fd; sha256 8cc8c1f9ab9a0d3f1a5edc9c2610b5f152b727de38f4783dba87335973149e0a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.01320. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 emerged as an efficient alternative. Within this line of work, vector quantization (VQ) enables controllable latent space modeling by mapping multivariate series into compact discrete representations. Existing VQ-based forecasting methods, however, typically rely on autoregressive (AR) token generation, which suffers from exposure bias and training-inference mismatch. Flow matching provides an efficient non-autoregressive alternative for latent forecasting, but existing formulations usually initialize transport from a generic Gaussian prior. We instead observe that the trained VQ codebook already captures representative latent prototypes and can thus serve as a more informative prior for flow matching. Based on this insight, we propose ProtoFlow, a forecasting framework that combines vector-quantized autoencoding with Prototype-prior Flow matching. Our method first maps multivariate sequences into a discrete latent space, then constructs a structured prior from the learned codebook, and finally learns a DiT-based rectified flow to transport samples from this prior to future latent representations conditioned on historical observations. By replacing generic noise initialization with a learned prototype prior, ProtoFlow avoids the rollout mismatch of AR token prediction and promotes faster training convergence. Extensive experiments on benchmark datasets show that it consistently achieves superior forecasting performance with efficient inference.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.01320 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-06T10:21:27.936Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).