QuantFlow: A Federated Mamba-Based Post-Transformer Foundation Model for Time-Series Forecasting

arXiv cs.LG Papers

Summary

QuantFlow introduces a federated Mamba-based foundation model for time-series forecasting that combines inverted sequence embedding, bidirectional state-space decoders, and quantile regression to achieve strong results on benchmarks while preserving data privacy.

arXiv:2607.02632v1 Announce Type: new Abstract: Time-series forecasting supports decisions in finance, en-ergy, transportation, public health, and industrial monitoring. Recent foundation models improve transfer across forecast-ing tasks, but many depend on centralized data and Trans-former attention, which restricts their use for long, high-di-mensional, and privacy-sensitive signals. This paper presents QuantFlow, a probabilistic forecasting framework that com-bines inverted sequence embedding, bidirectional Mamba state-space decoders, quantile regression, and federated learning. Each variable is embedded over the complete ob-servation window, processed in forward and reverse direc-tions, and projected to five conditional quantiles. TSMixup expands temporal diversity through Dirichlet-weighted inter-polation while preserving sequence structure. Experiments cover cryptocurrency, traffic, electricity, Electricity Trans-former Temperature, influenza, and weather data. QuantFlow obtains mean squared errors of 0.2834 on ETTm1 and 0.2218 on Weather, and a 20-client non-IID deployment retains use-ful accuracy after three communication rounds without cen-tralizing raw records. The results indicate that selective state-space modelling is a promising basis for scalable, uncer-tainty-aware, and privacy-conscious time-series prediction, while also revealing limitations on irregular epidemiological signals and long-horizon generalization.
Original Article
View Cached Full Text

Cached at: 07/07/26, 04:39 AM

# QuantFlow: A Federated Mamba-Based Post-Transformer Foundation Model for Time-Series Forecasting
Source: [https://arxiv.org/abs/2607.02632](https://arxiv.org/abs/2607.02632)
[View PDF](https://arxiv.org/pdf/2607.02632)

> Abstract:Time\-series forecasting supports decisions in finance, en\-ergy, transportation, public health, and industrial monitoring\. Recent foundation models improve transfer across forecast\-ing tasks, but many depend on centralized data and Trans\-former attention, which restricts their use for long, high\-di\-mensional, and privacy\-sensitive signals\. This paper presents QuantFlow, a probabilistic forecasting framework that com\-bines inverted sequence embedding, bidirectional Mamba state\-space decoders, quantile regression, and federated learning\. Each variable is embedded over the complete ob\-servation window, processed in forward and reverse direc\-tions, and projected to five conditional quantiles\. TSMixup expands temporal diversity through Dirichlet\-weighted inter\-polation while preserving sequence structure\. Experiments cover cryptocurrency, traffic, electricity, Electricity Trans\-former Temperature, influenza, and weather data\. QuantFlow obtains mean squared errors of 0\.2834 on ETTm1 and 0\.2218 on Weather, and a 20\-client non\-IID deployment retains use\-ful accuracy after three communication rounds without cen\-tralizing raw records\. The results indicate that selective state\-space modelling is a promising basis for scalable, uncer\-tainty\-aware, and privacy\-conscious time\-series prediction, while also revealing limitations on irregular epidemiological signals and long\-horizon generalization\.

## Submission history

From: Shah Nawaz Haider \[[view email](https://arxiv.org/show-email/da556a1f/2607.02632)\] **\[v1\]**Thu, 2 Jul 2026 14:16:48 UTC \(454 KB\)

Similar Articles

SDFlow: Similarity-Driven Flow Matching for Time Series Generation

arXiv cs.AI

This paper introduces SDFlow, a similarity-driven flow matching framework for time series generation that addresses exposure bias in autoregressive models. It achieves state-of-the-art performance and inference speedups by operating in the frozen VQ latent space with low-rank manifold decomposition.

StateFlow: Dual-State Recurrent Modeling for Long-Horizon Time Series Forecasting

arXiv cs.LG

This paper introduces StateFlow, a recurrent forecasting framework that extends the Variability-Aware Recursive Neural Network (VARNN) to long-horizon multivariate time series forecasting by using a dual-state recurrent backbone and a chunk-based decoder, achieving competitive performance against strong baselines.

A decoder-only foundation model for time-series forecasting

Papers with Code Trending

This article presents a research paper on Time-Series Foundation Model (TimeFM), a decoder-only model that achieves near-optimal zero-shot performance across diverse time-series datasets by adapting large language model techniques.