paper-with-me

홈 › Papers

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

2026-07-02 · Shah Nawaz Haider, Steve Austin, Arnab Barua, Sarowar Morshed Shawon, Hadaate Ullah arxiv

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.

📄 PDF Abstract BibTeX arXiv:2607.02632

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Similar Papers 제목 키워드 기반

MambaQuant: Quantizing the Mamba Family with Variance Aligned Rotation Methods

2025-01-23 · Zukang Xu, Yuxuan Yue, Xing Hu, Zhihang Yuan 외

Mamba is an efficient sequence model that rivals Transformers and demonstrates significant potential as a foundational architecture for various tasks. Quantization is commonly used in neural networks to reduce model size…

MambaQuantization

Is Mamba Capable of In-Context Learning?

2024-02-05 · Riccardo Grazzi, Julien Siems, Simon Schrodi, Thomas Brox 외

State of the art foundation models such as GPT-4 perform surprisingly well at in-context learning (ICL), a variant of meta-learning concerning the learned ability to solve tasks during a neural network forward pass, expl…

AutoMLIn-Context LearningMambaMeta-Learning

Venturing into Uncharted Waters: The Navigation Compass from Transformer to Mamba

2024-06-24 · Yuchen Zou, Yineng Chen, Zuchao Li, Lefei Zhang 외

Transformer, a deep neural network architecture, has long dominated the field of natural language processing and beyond. Nevertheless, the recent introduction of Mamba challenges its supremacy, sparks considerable intere…

MambaState Space Models

Mamba4Cast: Efficient Zero-Shot Time Series Forecasting with State Space Models

2024-10-12 · Sathya Kamesh Bhethanabhotla, Omar Swelam, Julien Siems, David Salinas 외

This paper introduces Mamba4Cast, a zero-shot foundation model for time series forecasting. Based on the Mamba architecture and inspired by Prior-data Fitted Networks (PFNs), Mamba4Cast generalizes robustly across divers…

AutoMLMambaState Space ModelsTime Series+1

Mamba-PTQ: Outlier Channels in Recurrent Large Language Models

2024-07-17 · Alessandro Pierro, Steven Abreu

Modern recurrent layers are emerging as a promising path toward edge deployment of foundation models, especially in the context of large language models (LLMs). Compressing the whole input sequence in a finite-dimensiona…

MambaModel CompressionQuantization