[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83346-en":3,"doc-seo-83346-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},83346,687197207919,"Theodora","https://ap-avatar.wpscdn.com/avatar/a000253d6f5f7c60be?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779446848396160552",8,"Research & Report","RhyMix A Lightweight Adaptive Multi Rhythm Network for Long Term Time Series Forecasting","Real-world multivariate time series contain intertwined dynamics, including short-term fluctuations, seasonal periodic cycles, long-term trends, and abrupt irregular changes. Many existing models either smooth local variations, lack sufficient receptive fields, or miss nonlinear dynamics while remaining computationally expensive. RhyMix (RHYthm MIXture) proposes a lightweight hybrid dual-path network that combines explicit cyclic seasonal priors with a multi-scale temporal convolutional network with channel attention. Adaptive multi-level gating fuses four forecasting heads per sample, preserving linear complexity, achieving state-of-the-art results on 10 of 12 datasets, and enabling low-latency inference.","Graphical Abstract  \nRhyMix: A Lightweight Adaptive Multi-Rhythm Network for Long-Term Time Series Forecasting  \nSumit Satishrao Shevtekar* , Chandresh Kumar Maurya  \narXiv :2607 .08234v 1 [ cs .LG] 9 Jul 2026  \nMultivariate Time Series Data  \nHighlights  \nRhyMix: A Lightweight Adaptive Multi-Rhythm Network for Long-Term Time Series Forecasting  \nSumit Satishrao Shevtekar* , Chandresh Kumar Maurya  \n• Lightweight dual-path forecasting architecture (40K parameters) integrating explicit multi-period cyclic priors  \n• Multi-Scale Temporal Convolution with Channel Attention (MSTCN-CA) for contextual temporal representation learning  \n• Adaptive gating dynamically fuses four forecasting heads on a per-sample basis  \n• Computationally efficient design with linear complexity, compact model size (157 KB), and low inference latency  \n• State-of-the-art forecasting performance on 10 of 12 datasets across diverse long-term forecasting benchmarks  \nRhyMix: A Lightweight Adaptive Multi-Rhythm Network for Long-Term Time Series Forecasting  \nSumit Satishrao Shevtekar*a , Chandresh Kumar Mauryaa  \na Department of Computer Science and Engineering, Indian Institute of Technology Indore, Indore, 453552,  \nMadhya Pradesh, India  \nAbstract  \nReal-world time series exhibit complex dynamics characterized by multiple simultaneous temporal patterns: short-term fluctuations, periodic seasonal cycles, long-term trends, and irregular abrupt changes. However, many existing forecasting architectures rely on single-path temporal modeling–transformers capture long-range dependencies but smooth local variations, convolutions capture local patterns but have limited receptive fields, and linear models are efficient but cannot capture nonlinear dynamics. To address this, we introduce RhyMix (RHYthm MIXture), a hybrid neural architecture designed around a parallel dual-path modeling paradigm with adaptive gating mechanisms. RhyMix integrates two complementary encoding branches: (i) a Cyclic Path that incorporates explicit seasonal inductive bias through learnable cyclic embeddings, capturing predictable rhythmic patterns; and (ii) a lightweight Multi-Scale Temporal Convolutional Network with Channel Attention Path that employs multi-scale depthwise dilated convolutions to capture temporal dependencies across different receptive fields. A key innovation is the use of adaptive gating mechanisms at multiple levels: a path gate dynamically combines four specialized forecasting heads (Direct, Trend-Seasonal Decomposition, Local Convolution, and Periodic Fusion) for each sample and channel, while a hybrid gate adaptively balances the contributions of the Cyclic and MSTCN-CA Paths based on input characteristics. This design ensures that  \n∗ Corresponding author  \nEmail addresses: [sumit.shevtekar@gmail.com](sumit.shevtekar@gmail.com) (Sumit Satishrao Shevtekar* ), [chandresh@iiti.ac.in](chandresh@iiti.ac.in)[ ](chandresh@iiti.ac.in)(Chandresh Kumar Maurya)  \nthe model adapts its behavior to the specific temporal patterns present in each sample while maintaining linear complexity with respect to the sequence length, channels, and prediction horizon. Across extensive benchmarks covering 12 real-world datasets for long-term forecasting, RhyMix achieves state-of-the-art performance on 10 of 12 datasets. The model remains lightweight (∼40K parameters) with linear complexity and low-latency inference (\u003C5 milliseconds), making it suitable for resource-constrained edge devices and real-time deployment.  \nKeywords: Time series forecasting, Deep learning, Temporal convolutional networks, Channel attention, Multi-scale modeling, Adaptive gating  \n1. Introduction  \nMultivariate time series (MTS) analysis underpins a broad spectrum of societally and industrially critical applications, including energy systems, intelligent transportation systems (Kadiyala and Kumar, 2014), weather forecasting (Gruca et al., 2022), industrial prognostics, and behavioral analytics. Across these domains","cbCaivtCQzR8c3bN","https://ap.wps.com/l/cbCaivtCQzR8c3bN","pdf",2786999,2,1,40,"English","en",105,"# Introduction\n## Motivation and challenges in multivariate long-term forecasting\n## Limitations of existing architectures","[{\"question\":\"What problem does RhyMix address in long-term time series forecasting?\",\"answer\":\"RhyMix targets long-term forecasting under multiple concurrent temporal patterns such as fluctuations, seasonal cycles, trends, and abrupt irregular changes, where many existing architectures model these aspects imperfectly or inefficiently.\"},{\"question\":\"How does RhyMix combine cyclic seasonality with temporal convolution?\",\"answer\":\"It uses two complementary branches: a Cyclic Path with learnable cyclic embeddings for explicit seasonal inductive bias, and an MSTCN-CA path that applies multi-scale depthwise dilated convolutions plus channel attention to learn dependencies across receptive fields.\"},{\"question\":\"What is the role of adaptive gating in RhyMix?\",\"answer\":\"Adaptive gating dynamically fuses four specialized forecasting heads on a per-sample basis and also balances contributions between the Cyclic and MSTCN-CA paths according to input characteristics.\"}]",1784186915,101,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"rhymix-a-lightweight-adaptive-multi-rhythm-network-for-long-term-time-series-forecasting","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,47,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":20},"https://docshare.wps.com/document/","Document",{"item":48,"name":12,"@type":43,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/rhymix-a-lightweight-adaptive-multi-rhythm-network-for-long-term-time-series-forecasting/83346/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-23","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does RhyMix address in long-term time series forecasting?","Question",{"text":75,"@type":76},"RhyMix targets long-term forecasting under multiple concurrent temporal patterns such as fluctuations, seasonal cycles, trends, and abrupt irregular changes, where many existing architectures model these aspects imperfectly or inefficiently.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does RhyMix combine cyclic seasonality with temporal convolution?",{"text":80,"@type":76},"It uses two complementary branches: a Cyclic Path with learnable cyclic embeddings for explicit seasonal inductive bias, and an MSTCN-CA path that applies multi-scale depthwise dilated convolutions plus channel attention to learn dependencies across receptive fields.",{"name":82,"@type":73,"acceptedAnswer":83},"What is the role of adaptive gating in RhyMix?",{"text":84,"@type":76},"Adaptive gating dynamically fuses four specialized forecasting heads on a per-sample basis and also balances contributions between the Cyclic and MSTCN-CA paths according to input characteristics.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,119,122,127,130,134],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":22,"slug":118},7,"Healthcare","healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]