{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T15:11:37Z","timestamp":1786374697751,"version":"build-2736575974"},"reference-count":48,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T00:00:00Z","timestamp":1786320000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100009620","name":"Science and Technology Department of Gansu Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100009620","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>Visual object detection is essential for defect inspection and process monitoring in edge-deployed Industrial Internet of Things (IIoT). Yet, training accurate detectors across distributed factories faces stringent constraints on data privacy, annotation budgets, and uplink communication. Standard federated learning (FL) preserves locality but often wastes labeling resources on redundant frames and overlooks detection-specific gradient alignment when scheduling clients. To bridge this gap, we propose Gradient-Aligned Active Federated Object Detection (GA-AFedOD), a unified framework that jointly optimizes annotation selection, client participation, and model aggregation as a constrained stochastic program. A novel utility metric integrates box-level uncertainty, prototype diversity, gradient alignment, and resource pricing, enabling edge clients to perform locally guided active querying while the server solves a lightweight primal-dual problem for budget-aware client scheduling. We prove a submodular approximation guarantee for the greedy sampling rule and establish a non-convex convergence bound that explicitly captures the impact of label budgets, client drift, and compression noise. This article further clarifies the relationship with recent federated active learning and industrial detection studies, adds parameter and theory-diagnostic analyses, and distinguishes controlled simulation evidence from real-world deployment validation on industrial datasets such as RasPiDets, Electric Power Fitting Dataset (EPFD), and Diverse Insulator Dataset (DINS). Controlled simulation results show that GA-AFedOD achieves considerably higher mean average precision (mAP) while reducing both annotation costs and uplink consumption by over 40% compared with competitive baselines.<\/jats:p>","DOI":"10.3389\/frai.2026.1895239","type":"journal-article","created":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T14:05:18Z","timestamp":1786370718000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["GA-AFedOD: gradient-aligned active federated learning for resource-aware object detection in edge industrial IoT"],"prefix":"10.3389","volume":"9","author":[{"given":"Zepeng","family":"Wang","sequence":"first","affiliation":[{"name":"School of Cyberspace Security, Gansu University of Political Science and Law","place":["Lanzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaogang","family":"Yuan","sequence":"additional","affiliation":[{"name":"School of Cyberspace Security, Gansu University of Political Science and Law","place":["Lanzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Electronic Engineering, National University of Defense Technology","place":["Hefei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,10]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"2720","DOI":"10.3390\/app14072720","article-title":"Communication efficiency and non-independent and identically distributed data challenge in federated learning: a systematic mapping study","volume":"14","author":"Alotaibi","year":"2024","journal-title":"Appl. Sci"},{"key":"B2","doi-asserted-by":"publisher","first-page":"5196","DOI":"10.1109\/TWC.2025.3546448","article-title":"Semi-asynchronous federated split learning for computing-limited devices in wireless networks","volume":"24","author":"Ao","year":"2025","journal-title":"IEEE Trans. Wireless Commun"},{"key":"B3","doi-asserted-by":"publisher","first-page":"1662984","DOI":"10.3389\/frai.2025.1662984","article-title":"Search-optimized quantization in biomedical ontology alignment","volume":"8","author":"Bouaggad","year":"2025","journal-title":"Front. Artif. Intell"},{"key":"B4","doi-asserted-by":"publisher","first-page":"5007","DOI":"10.1109\/TKDE.2024.3382002","article-title":"A survey for federated learning evaluations: goals and measures","volume":"36","author":"Chai","year":"2024","journal-title":"IEEE Trans. Knowl. Data Eng"},{"key":"B5","doi-asserted-by":"publisher","first-page":"913","DOI":"10.1109\/TNET.2024.3511598","article-title":"A distributed symmetric game optimization to 3-path vertex cover of networks","volume":"33","author":"Chen","year":"","journal-title":"IEEE Trans. Netw"},{"key":"B6","doi-asserted-by":"publisher","first-page":"6816","DOI":"10.1109\/TVT.2025.3622655","article-title":"Effective power-efficient task allocation in multi-agent system via GAPPO algorithm","volume":"75","author":"Chen","year":"","journal-title":"IEEE Trans. Vehic. Technol"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2026.3693048","article-title":"A synchronous potential game optimization to the sensor coverage problem of distributed system","author":"Chen","year":"","journal-title":"IEEE Trans. Mobile Comput"},{"key":"B8","doi-asserted-by":"publisher","first-page":"1534","DOI":"10.1109\/TASE.2024.3367722","article-title":"A serial game distributed algorithm to \u03f5-minimum vertex cover of networks in finite time","volume":"22","author":"Chen","year":"","journal-title":"IEEE Trans. Autom. Sci. Eng"},{"key":"B9","doi-asserted-by":"publisher","first-page":"11738","DOI":"10.1109\/TNNLS.2024.3495836","article-title":"Vertex cover of networks and its related optimization problems: an overview","volume":"36","author":"Chen","year":"","journal-title":"IEEE Trans. Neural Netw. Learn. Syst"},{"key":"B10","doi-asserted-by":"publisher","first-page":"1948","DOI":"10.1109\/TCE.2026.3653798","article-title":"A hydro-intelligence body: cognitive architecture for project-oriented autonomous water systems driven by multi-modal sensing and water utility panel","volume":"72","author":"Chen","year":"2026","journal-title":"IEEE Trans. Consumer Electr"},{"key":"B11","doi-asserted-by":"publisher","first-page":"827","DOI":"10.1109\/TKDE.2025.3631144","article-title":"Adaptive weighted double uncertainty incrementally active learning for multi-class imbalanced data","volume":"38","author":"Chen","year":"2026","journal-title":"IEEE Trans. Knowl. Data Eng"},{"key":"B12","doi-asserted-by":"publisher","first-page":"12252","DOI":"10.1109\/TII.2024.3417290","volume":"20","author":"Cui","year":"2024","journal-title":"IEEE Trans. Indus. Inform"},{"key":"B13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2025.3593591","article-title":"Adversarial federated consensus learning for surface defect classification under data heterogeneity in iiot","volume":"74","author":"Cui","year":"2025","journal-title":"IEEE Trans. Instrument. Measur"},{"key":"B14","doi-asserted-by":"publisher","first-page":"1554","DOI":"10.1109\/SMC53654.2022.9945452","article-title":"\u201cFedAL: an federated active learning framework for efficient labeling in skin lesion analysis,\u201d","author":"Deng","year":"2022","journal-title":"Proc. IEEE international conference on systems, man, and cybernetics"},{"key":"B15","doi-asserted-by":"publisher","first-page":"862","DOI":"10.1109\/TPDS.2024.3379905","article-title":"Taking advantage of the mistakes: rethinking clustered federated learning for iot anomaly detection","volume":"35","author":"Fan","year":"2024","journal-title":"IEEE Trans. Parallel Distrib. Syst"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2026.3660945","article-title":"MEDS-Net: meta-evidential dual-stream network for multimodal few-shot driver fatigue detection","author":"Fu","year":"2026","journal-title":"IEEE Trans. Comput. Soc. Syst"},{"key":"B17","doi-asserted-by":"publisher","first-page":"2039","DOI":"10.1109\/TNSE.2022.3169117","article-title":"Federated learning meets multi-objective optimization","volume":"9","author":"Hu","year":"2022","journal-title":"IEEE Trans. Netw. Sci. Eng"},{"key":"B18","doi-asserted-by":"publisher","first-page":"573731","DOI":"10.3389\/frai.2021.573731","article-title":"On consensus-optimality trade-offs in collaborative deep learning","volume":"4","author":"Jiang","year":"2021","journal-title":"Front. Artif. Intell"},{"key":"B19","doi-asserted-by":"publisher","first-page":"638951","DOI":"10.3389\/frai.2021.638951","article-title":"Improving the robustness of object detection through a multi-camera-based fusion algorithm using fuzzy logic","volume":"4","author":"Khan","year":"2021","journal-title":"Front. Artif. Intell"},{"key":"B20","doi-asserted-by":"publisher","first-page":"15196","DOI":"10.1109\/TMC.2024.3455331","article-title":"Joint client-and-sample selection for federated learning via bi-level optimization","volume":"23","author":"Li","year":"2024","journal-title":"IEEE Trans. Mobile Comput"},{"key":"B21","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1007\/978-981-95-1233-1_16","article-title":"\u201cSemi-supervised multi-view learning with graph-based consistent feature fusion,\u201d","author":"Li","year":"2025","journal-title":"Advances in Neural Networks-ISNN 2025 Lecture Notes in Computer Science"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2026.3660170","article-title":"Pseudo-label similarity graph-driven multi-view contrastive clustering","author":"Li","year":"2026","journal-title":"IEEE Trans. Multimedia"},{"key":"B23","doi-asserted-by":"publisher","first-page":"31245","DOI":"10.1109\/JIOT.2025.3572206","article-title":"Fast: Federated active learning with foundation models for communication-efficient sampling and training","volume":"12","author":"Li","year":"2025","journal-title":"IEEE Internet Things J"},{"key":"B24","doi-asserted-by":"publisher","first-page":"5525","DOI":"10.1109\/TII.2025.3556031","article-title":"RasPiDets: a quasi-real-time defect detection method with end-edge-cloud collaboration","volume":"21","author":"Liang","year":"2025","journal-title":"IEEE Trans. Indus. Inform"},{"key":"B25","doi-asserted-by":"publisher","first-page":"1518965","DOI":"10.3389\/frobt.2025.1518965","article-title":"A survey of model compression techniques: past, present, and future","volume":"12","author":"Liu","year":"2025","journal-title":"Front. Robot. AI"},{"key":"B26","doi-asserted-by":"publisher","first-page":"2186","DOI":"10.1109\/TASE.2024.3376427","article-title":"Edge-assisted multi-robot visual-inertial slam with efficient communication","volume":"22","author":"Liu","year":"2025","journal-title":"IEEE Trans. Autom. Sci. Eng"},{"key":"B27","doi-asserted-by":"publisher","first-page":"13172","DOI":"10.1609\/aaai.v34i08.7021","article-title":"\u201cFedVision: an online visual object detection platform powered by federated learning,\u201d","author":"Liu","year":"2020","journal-title":"Proc. AAAI conference on artificial intelligence, vol. 34"},{"key":"B28","doi-asserted-by":"publisher","first-page":"3408","DOI":"10.1109\/TON.2025.3589017","article-title":"Tbcim: two-level blockchain-aided edge resource allocation mechanism for federated learning service market","volume":"33","author":"Ma","year":"2025","journal-title":"IEEE Trans. Netw"},{"key":"B29","doi-asserted-by":"publisher","first-page":"1097","DOI":"10.1109\/TC.2025.3646160","article-title":"Kgnas: prior-knowledge-guided nas for real-time object detection on edge devices","volume":"75","author":"Mo","year":"2026","journal-title":"IEEE Trans. Comput"},{"key":"B30","doi-asserted-by":"publisher","first-page":"3390","DOI":"10.1109\/TMC.2024.3510135","article-title":"Asmafl: adaptive staleness-aware momentum asynchronous federated learning in edge computing","volume":"24","author":"Qiao","year":"2025","journal-title":"IEEE Trans. Mobile Comput"},{"key":"B31","doi-asserted-by":"publisher","first-page":"6452","DOI":"10.3390\/app15126452","article-title":"Edge-FLGuard: a federated learning framework for real-time anomaly detection in 5G-enabled IoT ecosystems","volume":"15","author":"Reis","year":"2025","journal-title":"Appl. Sci"},{"key":"B32","doi-asserted-by":"publisher","first-page":"1825067","DOI":"10.3389\/frai.2026.1825067","article-title":"Structural impact of non-IID heterogeneity on federated behavioral anomaly detection in IoT and IoMT systems","volume":"9","author":"Robalino-D\u00edaz","year":"2026","journal-title":"Front. Artif. Intell"},{"key":"B33","doi-asserted-by":"publisher","first-page":"674","DOI":"10.1109\/TMC.2025.3595117","article-title":"Edt-safl: semi-asynchronous federated learning for edge digital twin in industrial internet-of-things","volume":"25","author":"Tao","year":"2026","journal-title":"IEEE Trans. Mobile Comput"},{"key":"B34","doi-asserted-by":"publisher","first-page":"14114","DOI":"10.1109\/TII.2024.3441638","article-title":"Large-scale visual language model boosted by contrast domain adaptation for intelligent industrial visual monitoring","volume":"20","author":"Wang","year":"2024","journal-title":"IEEE Trans. Indus. Inform"},{"key":"B35","doi-asserted-by":"publisher","first-page":"2607","DOI":"10.1109\/TDSC.2024.3521297","article-title":"Flare: defending federated learning against model poisoning attacks via latent space representations","volume":"22","author":"Wang","year":"2025","journal-title":"IEEE Trans. Depend. Secure Comput"},{"key":"B36","doi-asserted-by":"publisher","first-page":"1968","DOI":"10.1109\/TMC.2023.3246176","article-title":"Industrial vision: rectifying millimeter-level edge deviation in industrial internet of things with camera-based edge device","volume":"23","author":"Xie","year":"2024","journal-title":"IEEE Trans. Mobile Comput"},{"key":"B37","doi-asserted-by":"publisher","first-page":"4603","DOI":"10.1109\/TNSE.2024.3410275","article-title":"Adaptive idle model fusion in hierarchical federated learning for unbalanced edge regions","volume":"11","author":"Xu","year":"2024","journal-title":"IEEE Trans. Netw. Sci. Eng"},{"key":"B38","doi-asserted-by":"publisher","first-page":"9183","DOI":"10.1109\/TII.2025.3598424","article-title":"EPFD: an electric power fitting dataset and benchmark for object detection","volume":"21","author":"Yang","year":"2025","journal-title":"IEEE Trans. Indus. Inform"},{"key":"B39","doi-asserted-by":"publisher","first-page":"13975","DOI":"10.1109\/TII.2024.3438261","article-title":"Few-sample anomaly detection in industrial images with edge enhancement and cascade residual feature refinement","volume":"20","author":"Yao","year":"2024","journal-title":"IEEE Trans. Indus. Inform"},{"key":"B40","doi-asserted-by":"publisher","first-page":"115460","DOI":"10.1016\/j.measurement.2024.115460","article-title":"PSPMoni: a robust wear monitoring method of pantograph slide plate","volume":"239","author":"Yao","year":"2025","journal-title":"Measurement"},{"key":"B41","doi-asserted-by":"publisher","first-page":"867","DOI":"10.1109\/TCYB.2025.3607287","article-title":"Tensor-based semi-supervised multiview subspace clustering with pairwise constraint propagation","volume":"56","author":"Yu","year":"2026","journal-title":"IEEE Trans. Cybernet"},{"key":"B42","doi-asserted-by":"publisher","first-page":"10407","DOI":"10.1109\/TNNLS.2024.3517658","article-title":"Federated learning based on model discrepancy and variance reduction","volume":"36","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Neural Netw. Learn. Syst"},{"key":"B43","doi-asserted-by":"publisher","first-page":"3088","DOI":"10.1109\/TKDE.2025.3547423","article-title":"\u201cchasechase: client heterogeneity-aware data selection for effective federated active learning.\u201d","volume":"37","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Knowl. Data Eng"},{"key":"B44","doi-asserted-by":"publisher","first-page":"20202","DOI":"10.1109\/TITS.2025.3598982","article-title":"YOLOv8DTL: A deep transfer learning model for few-shot rail abrasion detection","volume":"26","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst"},{"key":"B45","doi-asserted-by":"publisher","first-page":"37340","DOI":"10.1109\/JIOT.2024.3443112","article-title":"Toward industrial densely packed object detection: a federated semi-supervised learning approach","volume":"11","author":"Zhao","year":"2024","journal-title":"IEEE Internet Things J"},{"key":"B46","doi-asserted-by":"publisher","first-page":"32272","DOI":"10.1109\/JIOT.2024.3425483","article-title":"PST-transformer: a two-stage model for 3D driving pose estimation","volume":"11","author":"Zhao","year":"2024","journal-title":"IEEE Internet Things J"},{"key":"B47","doi-asserted-by":"publisher","first-page":"1277","DOI":"10.1109\/TMM.2024.3521778","article-title":"Classification committee for active deep object detection","volume":"27","author":"Zhao","year":"2025","journal-title":"IEEE Trans. Multimedia"},{"key":"B48","doi-asserted-by":"publisher","first-page":"7300","DOI":"10.24963\/ijcai.2025\/812","article-title":"\u201cInconsistency-based federated active learning,\u201d","author":"Zong","year":"2025","journal-title":"Proceedings of the thirty-fourth international joint conference on artificial intelligence"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1895239\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T14:05:19Z","timestamp":1786370719000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1895239\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,10]]},"references-count":48,"alternative-id":["10.3389\/frai.2026.1895239"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1895239","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,10]]},"article-number":"1895239"}}