{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:34:10Z","timestamp":1763192050341,"version":"3.45.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11227782","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Mooe: Optimal Expert Deployment Scheme in Low-Rank Adaptation architecture"],"prefix":"10.1109","author":[{"given":"Shuzhen","family":"Sun","sequence":"first","affiliation":[{"name":"Tianjin University,College of Intelligence and Computing,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tianjin University,College of Intelligence and Computing,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xindian","family":"Ma","sequence":"additional","affiliation":[{"name":"Tianjin University,College of Intelligence and Computing,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tianjin University,College of Intelligence and Computing,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.8"},{"article-title":"LoRA: Low-Rank Adaptation of Large Language Models","volume-title":"International Conference on Learning Representations","author":"Hu","key":"ref2"},{"issue":"7","key":"ref3","article-title":"Loramoe: Revolutionizing mixture of experts for maintaining world knowledge in language model alignment","volume":"4","author":"Dou","year":"2023"},{"article-title":"Pushing Mixture of Experts to the Limit: Extremely Parameter Efficient MoE for Instruction Tuning","volume-title":"The Twelfth International Conference on Learning Representations","author":"Zadouri","key":"ref4"},{"key":"ref5","article-title":"MOELoRA: An MOE-based Parameter Efficient Fine-Tuning Method for Multi-task Medical Applications","author":"Liu","year":"2023","journal-title":"CoRR"},{"article-title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","volume-title":"International Conference on Learning Representations","author":"Shazeer","key":"ref6"},{"article-title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","volume-title":"International Conference on Learning Representations","author":"Lepikhin","key":"ref7"},{"issue":"120","key":"ref8","first-page":"1","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"Journal of Machine Learning Research"},{"article-title":"Higher layers need more lora experts","year":"2024","author":"Gao","key":"ref9"},{"article-title":"Mixture of lora experts","year":"2024","author":"Wu","key":"ref10"},{"article-title":"Mixlora: Enhancing large language models fine-tuning with lora-based mixture of experts","year":"2024","author":"Li","key":"ref11"},{"article-title":"Sira: Sparse mixture of low rank adaptation","year":"2023","author":"Zhu","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657722"},{"article-title":"PERFT: Parameter-Efficient Routed Fine-Tuning for Mixture-of-Expert Model","year":"2024","author":"Liu","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/566"},{"article-title":"Towards a Unified View of Parameter-Efficient Transfer Learning","volume-title":"International Conference on Learning Representations","author":"He","key":"ref16"},{"key":"ref17","first-page":"1950","article-title":"Few-shot parameter-efficient fine-tuning is better and cheaper than incontext learning","volume":"35","author":"Liu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.79"},{"article-title":"Learning Factored Representations in a Deep Mixture of Experts","year":"2013","author":"Eigen","key":"ref19"},{"article-title":"Taming Sparsely Activated Transformer with Stochastic Experts","volume-title":"International Conference on Learning Representations","author":"Zuo","key":"ref20"},{"article-title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","volume-title":"R0-FoMo: Robustness of Few-shot and Zero-shot Learning in Large Foundation Models","author":"Huang","key":"ref21"},{"article-title":"Octavius: Mitigating task interference in mllms via moe","year":"2023","author":"Chen","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02318"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3316451"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6239"},{"journal-title":"Try ARC, the AI2 Reasoning Challenge","article-title":"Think you have Solved Question Answering?","author":"Clark","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6399"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1472"},{"article-title":"Pointer Sentinel Mixture Models","volume-title":"International Conference on Learning Representations","author":"Merity","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3115\/1075812.1075835"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11227782.pdf?arnumber=11227782","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:32:09Z","timestamp":1763191929000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11227782\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11227782","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}