{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T00:14:57Z","timestamp":1758672897489,"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>Few-shot Multi-label Intent Detection (MID) is crucial for dialogue systems, aiming to detect multiple intents of utterances in low-resource dialogue domains. Previous studies focus on a two-stage pipeline. They first learn representations of utterances with multiple labels and then use a threshold-based strategy to identify multi-label results. However, these methods rely on representation classification and ignore instance relations, leading to error propagation. To solve the above issues, we propose a multi-label joint learning method for few-shot MID in an end-to-end manner, which constructs an instance relation learning network with label knowledge propagation to eliminate error propagation. Concretely, we learn the interaction relations between instances with class information to propagate label knowledge between a few labeled (support set) and unlabeled (query set) instances. With label knowledge propagation, the relation strength between instances directly indicates whether two utterances belong to the same intent for multi-label prediction. Besides, a dual relation-enhanced loss is developed to optimize support- and query-level relation strength to improve performance. Experiments show that we outperform strong baselines by an average of  9.54% AUC and 11.19% Macro-F1 in 1-shot scenarios.<\/jats:p>","DOI":"10.24963\/ijcai.2025\/791","type":"proceedings-article","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T08:10:40Z","timestamp":1758269440000},"page":"7110-7118","source":"Crossref","is-referenced-by-count":0,"title":["Instance Relation Learning Network with Label Knowledge Propagation for Few-shot Multi-label Intent Detection"],"prefix":"10.24963","author":[{"given":"Shiman","family":"Zhao","sequence":"first","affiliation":[{"name":"Key Lab of High Confidence Software Technologies (MOE), School of Computer Science, Peking University, Beijing, China."},{"name":"Research Center for Computational Social Science, Peking University, Beijing, China."},{"name":"Institute of Computational Social Science, Peking University, Qingdao, China."}]},{"given":"Shangyuan","family":"Li","sequence":"additional","affiliation":[{"name":"Key Lab of High Confidence Software Technologies (MOE), School of Computer Science, Peking University, Beijing, China."},{"name":"Research Center for Computational Social Science, Peking University, Beijing, China."},{"name":"Institute of Computational Social Science, Peking University, Qingdao, China."}]},{"given":"Wei","family":"Chen","sequence":"additional","affiliation":[{"name":"Key Lab of High Confidence Software Technologies (MOE), School of Computer Science, Peking University, Beijing, China."},{"name":"Research Center for Computational Social Science, Peking University, Beijing, China."},{"name":"Institute of Computational Social Science, Peking University, Qingdao, China."}]},{"given":"Tengjiao","family":"Wang","sequence":"additional","affiliation":[{"name":"Key Lab of High Confidence Software Technologies (MOE), School of Computer Science, Peking University, Beijing, China."},{"name":"Research Center for Computational Social Science, Peking University, Beijing, China."},{"name":"Institute of Computational Social Science, Peking University, Qingdao, China."},{"name":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong, China."}]},{"given":"Jiahui","family":"Yao","sequence":"additional","affiliation":[{"name":"Key Lab of High Confidence Software Technologies (MOE), School of Computer Science, Peking University, Beijing, China."},{"name":"Research Center for Computational Social Science, Peking University, Beijing, China."},{"name":"Institute of Computational Social Science, Peking University, Qingdao, China."}]},{"given":"Jiabin","family":"Zheng","sequence":"additional","affiliation":[{"name":"Key Lab of High Confidence Software Technologies (MOE), School of Computer Science, Peking University, Beijing, China."},{"name":"Research Center for Computational Social Science, Peking University, Beijing, China."},{"name":"Institute of Computational Social Science, Peking University, Qingdao, China."}]},{"given":"Kam-Fai","family":"Wong","sequence":"additional","affiliation":[{"name":"Key Lab of High Confidence Software Technologies (MOE), School of Computer Science, Peking University, Beijing, China."},{"name":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong, China."}]}],"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":"2025-09-23T11:35:09Z","timestamp":1758627309000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2025\/791"}},"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\/791","relation":{},"subject":[],"published":{"date-parts":[[2025,9]]}}}