{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T03:03:24Z","timestamp":1773803004058,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"25","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>Open-set semi-supervised learning (OSSL) leverages unlabeled data containing both in-distribution (ID) and unknown out-of-distribution (OOD) samples, aiming simultaneously to improve closed-set accuracy and detect novel OOD instances. Existing methods either discard valuable information from uncertain samples or force-align every unlabeled sample into one or a few synthetic \u201ccatch-all\u201d representations, resulting in geometric collapse and overconfidence on only seen OODs. To address the limitations, we introduce selective non-alignment, adding a novel \u201cskip\u201d operator into conventional pull and push operations of contrastive learning. Our framework, SkipAlign, selectively skips alignment (pulling) for low-confidence unlabeled samples, retaining only gentle repulsion against ID prototypes. This approach transforms uncertain samples into a pure repulsion signal, resulting in tighter ID clusters and naturally dispersed OOD features. Extensive experiments demonstrate that SkipAlign significantly outperforms state-of-the-art methods in detecting unseen OOD data without sacrificing ID classification accuracy.<\/jats:p>","DOI":"10.1609\/aaai.v40i25.39194","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T01:18:03Z","timestamp":1773796683000},"page":"20579-20587","source":"Crossref","is-referenced-by-count":0,"title":["Let the Void Be Void: Robust Open-Set Semi-Supervised Learning via Selective Non-Alignment"],"prefix":"10.1609","volume":"40","author":[{"given":"You Rim","family":"Choi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Subeom","family":"Park","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seojun","family":"Heo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eunchung","family":"Noh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hyung-Sin","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"9382","published-online":{"date-parts":[[2026,3,14]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/39194\/43155","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/39194\/43155","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T01:18:04Z","timestamp":1773796684000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/39194"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"25","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i25.39194","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3,14]]}}}