[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-86332-en":3,"doc-seo-86332-105":29,"detail-sidebar-cat-0-en-105":90},{"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":11,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},86332,7971461741311,"Ophelia","https://ap-avatar.wpscdn.com/avatar/74000253aff267980c6?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779345379180704826",8,"Research & Report","Transformer-Guided Swarm Intelligence for Frugal Neural Architecture Search","Neural Architecture Search (NAS) automates deep model design but is commonly restricted by extremely high compute cost, often requiring thousands of GPU-days. A frugal memetic NAS framework is proposed to enable architecture discovery on consumer-grade hardware. The method combines an autoregressive Transformer controller trained with Reinforcement Learning for global macro-search and an Artificial Bee Colony (ABC) algorithm for local micro-exploitation. A dynamic entropy mechanism combats premature convergence during RL and helps solve the inherent cold-start issue of metaheuristics. On an NVIDIA RTX 3060, it achieves 84.85% accuracy on CIFAR-10 with about 174k parameters in three hours, and reaches F1 0.71 for credit-card fraud detection with a compact ~4.6k-parameter network, suitable for edge deployment.","Transformer-Guided Swarm Intelligence for Frugal  \nNeural Architecture Search  \nRomain Amigon  \nUniversite´ du Que´bec a` Chicoutimi (UQAC)  \nSaguenay, Canada  \nEmail: [amigonromaina@gmail.com / ramigon@etu.uqac.ca](amigonromaina@gmail.com / ramigon@etu.uqac.ca)  \narXiv :2607 . 1 1826v 1 [ cs .LG] 13 Jul 2026  \nAbstract—Neural Architecture Search (NAS) has automated the design of deep learning models but traditionally requires massive computational resources, often measured in thousands of GPU-days. In this paper, we propose a frugal and memetic NAS framework designed to democratize architecture design on consumer-grade hardware. Our approach combines the global macro-search capabilities of an autoregressive Transformer controller, trained via Reinforcement Learning (RL), with the local micro-exploitation of an Artificial Bee Colony (ABC) algorithm. To prevent premature convergence during the RL phase, we introduce a dynamic entropy mechanism that forces topological exploration upon detection of performance stagnation. Evaluated on a standard GPU (NVIDIA RTX 3060), our hybrid method effectively resolves the ”cold-start” problem inherent in metaheuristics. By algorithmically penalizing network depth, our framework actively mitigates model bloat: on the CIFAR- 10 dataset, it discovers an efficient architecture reaching 84.85% accuracy with only ∼174,000 parameters—significantly smaller than standard baselines like ResNet-20—in 3 hours of search time. Furthermore, we demonstrate the framework’s flexibility by applying it to credit card fraud detection, directly optimizing the F1-Score on highly imbalanced tabular data to reach a F1-Score of 0.71 with a compact network of ∼4,600 parameters. These results suggest that our approach can yield tailored, accessible, and highly parameter-efficient deep learning models suitable for edge deployment.  \nIndex Terms—Neural Architecture Search, Transformer, Artificial Bee Colony, Frugal AI, Reinforcement Learning, Memetic Algorithms.  \nI. INTRODUCTION  \nThe design of neural networks has historically been dominated by an empirical approach, where hyperparameters and topology are chosen based on human experience. While Neural Architecture Search (NAS) has formalized this process by automating the discovery of optimal topologies, early Reinforcement Learning (RL) based methods faced prohibitive costs. Foundational works required hundreds of GPUs running for weeks [1] .  \nToday, the field of NAS faces two intertwined challenges. The first is over-parameterization: the literature tends to produce architectures that are computationally redundant relative to the intrinsic complexity of their task. The second is a methodological gap in optimization. Traditional NAS controllers often rely on Recurrent Neural Networks (RNNs or LSTMs), which suffer from an information bottleneck. In a neural network, the choice of a specific layer strongly dictates the necessity of subsequent layers. LSTMs struggle to cap-  \nture these long-range topological dependencies. Furthermore, while RL excels at finding a global macro-architecture, it is notoriously inefficient at fine-tuning continuous, micro-level hyperparameters.  \nThis paper presents nas-torch, a highly modular, ”whitebox” NAS framework specifically designed for applied engineering and resource-constrained environments. This work does not target state-of-the-art accuracy on large benchmarks, but rather serves as a proof of concept to demonstrate that highly efficient, task-specific feature extractors can be generated autonomously on hardware as constrained as a single consumer GPU. Rather than targeting marginal accuracy gains on massive compute clusters, our approach prioritizes democratic accessibility and structural flexibility. To this end, nas-torch provides a suite of plug-and-play frugal optimizers—including Random Search, Simulated Annealing, Artificial Bee Colony (ABC), and an autoregressive Transformer—while allowing researchers to easily integrate","cbCainuqy9cyxib0","https://ap.wps.com/l/cbCainuqy9cyxib0","pdf",424671,4,1,"English","en",105,"# Abstract\n# Introduction\n## Challenges in NAS optimization\n## nas-torch framework and objective\n## Contributions\n# Related Work","[{\"question\":\"What problem does the proposed frugal NAS framework address?\",\"answer\":\"It targets the high computational cost of traditional NAS methods, which often require thousands of GPU-days, by enabling efficient architecture search on consumer-grade hardware.\"},{\"question\":\"How does the framework combine Transformer-based search with swarm optimization?\",\"answer\":\"It uses an autoregressive Transformer controller trained via reinforcement learning for global macro-search, then applies Artificial Bee Colony (ABC) for local micro-exploitation in a memetic pipeline.\"},{\"question\":\"How does the method prevent premature convergence during the RL phase?\",\"answer\":\"It introduces a dynamic entropy mechanism that forces topological exploration when performance stagnation is detected, improving search diversity.\"}]",1784210522,20,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"transformer-guided-swarm-intelligence-for-frugal-neural-architecture-search","",{"@graph":35,"@context":84},[36,52,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":20},"https://docshare.wps.com/document/transformer-guided-swarm-intelligence-for-frugal-neural-architecture-search/86332/",{"url":51,"name":13,"@type":53,"author":54,"headline":13,"publisher":56,"fileFormat":59,"inLanguage":23,"description":14,"dateModified":60,"datePublished":61,"encodingFormat":59,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":55},"Person",{"url":40,"name":57,"@type":58},"DocShare","Organization","application/pdf","2026-07-27","2026-07-16",true,{"@type":64,"interactionType":65,"userInteractionCount":20},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"What problem does the proposed frugal NAS framework address?","Question",{"text":74,"@type":75},"It targets the high computational cost of traditional NAS methods, which often require thousands of GPU-days, by enabling efficient architecture search on consumer-grade hardware.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How does the framework combine Transformer-based search with swarm optimization?",{"text":79,"@type":75},"It uses an autoregressive Transformer controller trained via reinforcement learning for global macro-search, then applies Artificial Bee Colony (ABC) for local micro-exploitation in a memetic pipeline.",{"name":81,"@type":72,"acceptedAnswer":82},"How does the method prevent premature convergence during the RL phase?",{"text":83,"@type":75},"It introduces a dynamic entropy mechanism that forces topological exploration when performance stagnation is detected, improving search diversity.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":57,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,126,129,133],{"id":21,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":20,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":28,"slug":125},9,"Religion & Spirituality","religion-spirituality",{"id":28,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":28,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":45,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":45,"category_name":135,"show_sort_weight":105,"slug":136},19,"General","general"]