{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T00:14:37Z","timestamp":1758672877433,"version":"3.44.0"},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,9]]},"abstract":"<jats:p>Deep neural networks (DNNs) face substantial challenges in Long-Tail Visual Recognition (LTVR) due to the inherent class imbalances in real-world data distributions. \n\nThe Mixture of Experts (MoE) framework has emerged as a promising approach to addressing these issues.\n\nHowever, in MoE systems, experts are typically trained to optimize a collective objective, often neglecting the individual optimality of each expert. This individual optimality usually contributes to the overall performance, as the goals of different experts are not mutually exclusive.\n\nWe propose the Independent and Collaborative Learning (ICL) framework to optimize each expert independently while ensuring global optimality. \n\nFirst, Diverse Optimization Learning (DOL) is introduced to enhance expert diversity and individual performance. \n\nThen, we conceptualize experts as parallel circuit branches and introduce Competition and Collaboration Learning (CoL). Competition Learning amplifies the gradients of better-performing experts to preserve individual optimality, and Collaboration Learning encourages collaboration through mutual distillation to enhance optimal knowledge sharing.\n\nICL achieves state-of-the-art accuracy in experiments on CIFAR-100\/10-LT, ImageNet-LT, and iNaturalist 2018, respectively. Our code is available at https:\/\/github.com\/PolarisLight\/ICL.<\/jats:p>","DOI":"10.24963\/ijcai.2025\/93","type":"proceedings-article","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T08:10:40Z","timestamp":1758269440000},"page":"828-836","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Mixture of Experts with Independent and Collaborative Learning for Long-Tail Visual Recognition"],"prefix":"10.24963","author":[{"given":"Yanhao","family":"Chen","sequence":"first","affiliation":[{"name":"School of Film, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongquan","family":"Jian","sequence":"additional","affiliation":[{"name":"School of Informatics, Xiamen University, Xiamen, China"},{"name":"Institute of Artificial Intelligence, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nianxin","family":"Ke","sequence":"additional","affiliation":[{"name":"School of Film, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuhao","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Film, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junjie","family":"Jiao","sequence":"additional","affiliation":[{"name":"School of Film, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingqi","family":"Hong","sequence":"additional","affiliation":[{"name":"School of Film, Xiamen University, Xiamen, China"},{"name":"Institute of Artificial Intelligence, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingqiang","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Film, Xiamen University, Xiamen, China"},{"name":"School of Informatics, Xiamen University, Xiamen, China"},{"name":"Institute of Artificial Intelligence, Xiamen University, Xiamen, China"},{"name":"Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan, Ministry of Culture and Tourism, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"10584","event":{"number":"34","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"acronym":"IJCAI-2025","name":"Thirty-Fourth International Joint Conference on Artificial Intelligence {IJCAI-25}","start":{"date-parts":[[2025,8,16]]},"theme":"Artificial Intelligence","location":"Montreal, Canada","end":{"date-parts":[[2025,8,22]]}},"container-title":["Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T11:32:57Z","timestamp":1758627177000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2025\/93"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2025\/93","relation":{},"subject":[],"published":{"date-parts":[[2025,9]]}}}