翻訳待ち：Systematic Exploration of 4-Expert Heterogeneous Mixture-of-Experts via Automated Pipeline Search
AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要：arXiv:2606.23739v1 Announce Type: new Abstract: We present an automated large-scale search pipeline for heterogeneous 4-Expert Mixture-of-Experts (MoE4) architectures within the LEMUR neural network dataset ecosystem. Building on a hand-crafted heterogeneous MoE reference model, we replace manual design with a deterministic code-assembly generator that systematically combines base architecture families drawn from the LEMUR database into MoE4 ensembles, each governed by a convolutional gating network with temperature scaling, mixup augmentation, and cosine-annealed learning rate scheduling. Over a 28-day campaign on an NVIDIA RTX 4090, the pipeline generated 4,463 candidate models across 197 batches, of which 1,021 were evaluated successfully. A critical finding emerged from the campaign: due to alphabetical enumeration via itertools.combinations, the entire explored search space (4.8% of the theoretical 23,751 possible 4-family combinations) is anchored to a single family, AirNet. We characterise this coverage bias precisely, identify the root cause in the generator, and propose a stratified random sampling fix. Within the AirNet anchored scope, ShuffleNet and MobileNetV3 consistently co-produce the highest-accuracy ensembles (mean accuracy up to 0.632), while FractalNet and MNASNet are identified as low-yield families warranting exclusion in future campaigns. The pipeline, analysis artefacts, and corrected generator are released as part of the open-source NNGPT project at https://github.com/ABrain-One/nn-gpt
AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。
[2606.23739] Systematic Exploration of 4-Expert Heterogeneous Mixture-of-Experts via Automated Pipeline Search [Submitted on 21 Jun 2026] Title:Systematic Exploration of 4-Expert Heterogeneous Mixture-of-Experts via Automated Pipeline Search View a PDF of the paper titled Systematic Exploration of 4-Expert Heterogeneous Mixture-of-Experts via Automated Pipeline Search, by Yashkumar R Lukhi and Harsh Rameshbhai Moradiya and Radu Timofte and Dmitry Ignatov View PDF HTML (experimental) Abstract:We present an automated large-scale search pipeline for heterogeneous 4-Expert Mixture-of-Experts (MoE4) architectures within the LEMUR neural network dataset ecosystem. Building on a hand-crafted heterogeneous MoE reference model, we replace manual design with a deterministic code-assembly generator that systematically combines base architecture families drawn from the LEMUR database into MoE4 ensembles, each governed by a convolutional gating network with temperature scaling, mixup augmentation, and cosine-annealed learning rate scheduling. Over a 28-day campaign on an NVIDIA RTX 4090, the pipeline generated 4,463 candidate models across 197 batches, of which 1,021 were evaluated successfully. A critical finding emerged from the campaign: due to alphabetical enumeration via this http URL, the entire explored search space (4.8% of the theoretical 23,751 possible 4-family combinations) is anchored to a single family, AirNet. We characterise this coverage bias precisely, identify the root cause in the generator, and propose a stratified random sampling fix. Within the AirNet anchored scope, ShuffleNet and MobileNetV3 consistently co-produce the highest-accuracy ensembles (mean accuracy up to 0.632), while FractalNet and MNASNet are identified as low-yield families warranting exclusion in future campaigns. The pipeline, analysis artefacts, and corrected generator are released as part of the open-source NNGPT project at this https URL Comments: 8 pages, 2 figures Subjects: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV); Software Engineering (cs.SE) Cite as: arXiv:2606.23739 [cs.LG] (or arXiv:2606.23739v1 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2606.23739 arXiv-issued DOI via DataCite Submission history From: Yashkumar R Lukhi [view email] [v1] Sun, 21 Jun 2026 13:43:27 UTC (179 KB) Full-text links: Access Paper: View a PDF of the paper titled Systematic Exploration of 4-Expert Heterogeneous Mixture-of-Experts via Automated Pipeline Search, by Yashkumar R Lukhi and Harsh Rameshbhai Moradiya and Radu Timofte and Dmitry Ignatov View PDF HTML (experimental) TeX Source view license Current browse context: cs.LG new | recent | 2026-06 Change to browse by: cs cs.CV cs.SE References & Citations NASA ADS Google Scholar Semantic Scholar Loading... Data provided by: Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) IArxiv recommender toggle IArxiv Recommender (What is IArxiv?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)