{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T00:14:52Z","timestamp":1758672892508,"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>Traditional Incremental Learning (IL) targets to handle sequential fully-supervised learning problems where novel classes emerge from time to time. However, due to inherent annotation uncertainty and ambiguity, collecting high-quality annotated data in a dynamic learning system can be extremely expensive. To mitigate this problem, we propose a novel weakly-supervised learning paradigm called Incremental Partial Label Learning (IPLL), where the sequentially arrived data relate to a set of candidate labels rather than the ground truth. Technically, we develop the Prototype-Guided Disambiguation and Replay Algorithm (PGDR) which leverages the class prototypes as a proxy to mitigate two intertwined challenges in IPLL, i.e., label ambiguity and catastrophic forgetting. To handle the former, PGDR encapsulates a momentum-based pseudo-labeling algorithm along with prototype-guided initialization, resulting in a balanced perception of classes. To alleviate forgetting, we develop a memory replay technique that collects well-disambiguated samples while maintaining representativeness and diversity. By jointly distilling knowledge from curated memory data, our framework exhibits a great disambiguation ability for samples of new tasks and achieves less forgetting of knowledge. Extensive experiments demonstrate that PGDR achieves superior performance over the baselines in the IPLL task.<\/jats:p>","DOI":"10.24963\/ijcai.2025\/712","type":"proceedings-article","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T08:10:40Z","timestamp":1758269440000},"page":"6397-6405","source":"Crossref","is-referenced-by-count":0,"title":["Towards Robust Incremental Learning Under Ambiguous Supervision"],"prefix":"10.24963","author":[{"given":"Rui","family":"Wang","sequence":"first","affiliation":[{"name":"School of Software Technology, Zhejiang University"},{"name":"Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security"}]},{"given":"Mingxuan","family":"Xia","sequence":"additional","affiliation":[{"name":"School of Software Technology, Zhejiang University"},{"name":"Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security"}]},{"given":"Haobo","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Software Technology, Zhejiang University"},{"name":"Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security"}]},{"given":"Lei","family":"Feng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Southeast University, China"}]},{"given":"Junbo","family":"Zhao","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University"}]},{"given":"Gang","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University"}]},{"given":"Chang","family":"Yao","sequence":"additional","affiliation":[{"name":"School of Software Technology, Zhejiang University"},{"name":"Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security"}]}],"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":"2025-09-23T11:34:56Z","timestamp":1758627296000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2025\/712"}},"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\/712","relation":{},"subject":[],"published":{"date-parts":[[2025,9]]}}}