Enregistré dans:
Détails bibliographiques
Auteurs principaux: Ashraf, Tajamul, Bashir, Janibul
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2408.11336
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913894443778048
author Ashraf, Tajamul
Bashir, Janibul
author_facet Ashraf, Tajamul
Bashir, Janibul
contents Climate change stands as one of the most pressing global challenges of the twenty-first century, with far-reaching consequences such as rising sea levels, melting glaciers, and increasingly extreme weather patterns. Accurate forecasting is critical for monitoring these phenomena and supporting mitigation strategies. While recent data-driven models for time-series forecasting, including CNNs, RNNs, and attention-based transformers, have shown promise, they often struggle with sequential dependencies and limited parallelization, especially in long-horizon, multivariate meteorological datasets. In this work, we present Focal Modulated Attention Encoder (FATE), a novel transformer architecture designed for reliable multivariate time-series forecasting. Unlike conventional models, FATE introduces a tensorized focal modulation mechanism that explicitly captures spatiotemporal correlations in time-series data. We further propose two modulation scores that offer interpretability by highlighting critical environmental features influencing predictions. We benchmark FATE across seven diverse real-world datasets including ETTh1, ETTm2, Traffic, Weather5k, USA-Canada, Europe, and LargeST datasets, and show that it consistently outperforms all state-of-the-art methods, including temperature datasets. Our ablation studies also demonstrate that FATE generalizes well to broader multivariate time-series forecasting tasks. For reproducible research, code is released at https://github.com/Tajamul21/FATE.
format Preprint
id arxiv_https___arxiv_org_abs_2408_11336
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle FATE: Focal-modulated Attention Encoder for Multivariate Time-series Forecasting
Ashraf, Tajamul
Bashir, Janibul
Machine Learning
Computer Vision and Pattern Recognition
Climate change stands as one of the most pressing global challenges of the twenty-first century, with far-reaching consequences such as rising sea levels, melting glaciers, and increasingly extreme weather patterns. Accurate forecasting is critical for monitoring these phenomena and supporting mitigation strategies. While recent data-driven models for time-series forecasting, including CNNs, RNNs, and attention-based transformers, have shown promise, they often struggle with sequential dependencies and limited parallelization, especially in long-horizon, multivariate meteorological datasets. In this work, we present Focal Modulated Attention Encoder (FATE), a novel transformer architecture designed for reliable multivariate time-series forecasting. Unlike conventional models, FATE introduces a tensorized focal modulation mechanism that explicitly captures spatiotemporal correlations in time-series data. We further propose two modulation scores that offer interpretability by highlighting critical environmental features influencing predictions. We benchmark FATE across seven diverse real-world datasets including ETTh1, ETTm2, Traffic, Weather5k, USA-Canada, Europe, and LargeST datasets, and show that it consistently outperforms all state-of-the-art methods, including temperature datasets. Our ablation studies also demonstrate that FATE generalizes well to broader multivariate time-series forecasting tasks. For reproducible research, code is released at https://github.com/Tajamul21/FATE.
title FATE: Focal-modulated Attention Encoder for Multivariate Time-series Forecasting
topic Machine Learning
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2408.11336