EUVIMEDEUVIMED entdecken
Crossref

KNNDA: A New Perspective of Alignment Recovery for Partially View-Aligned Clustering

Liang Zhao, Tianqi Yue, Shubin Ma, Ziyue Wang, ZhiYuan Liu, Bo Xu

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (34) · 28706-28714

DOI: 10.1609/aaai.v40i34.40103 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Liang Zhao und 5 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In multi-view clustering (MVC), complementary and consistent information from multiple views is integrated to improve clustering performance. However, inter-view sample correspondences may be partially missing in practice, making it difficult to learn cross-view consistency, which leads to the partially view-aligned problem (PVP). Most existing partially view-aligned clustering (PVC) methods first learn cross-view consistent representations based on known alignments, and then recover missing correspondences by measuring cross-view similarity between samples. However, such an indirect alignment recovery process depends on high-quality consistent representations and lacks effective utilization of known alignments, often resulting in sub-optimal outcomes. To address this, we propose a novel direct alignment recovery perspective, instantiated as K-Nearest Neighbors Direct Alignment (KNNDA). Specifically, we first construct an alignment domain by mapping the aligned neighbors of each unaligned sample into the aligned view. Then, we compute alignment confidence based on the similarity between known aligned pairs of neighbors. In particular, we use a dynamic threshold to filter out unreliable alignments. Finally, new alignments are generated within the high-confidence alignment domain. Contrastive loss is used to learn consistent representations for clustering. Comprehensive experiments on several real-world datasets show the effectiveness and superiority of our module in partially view-aligned clustering.

Zitieren

APA

Zhao, L., Yue, T., Ma, S., Wang, Z., Liu, Z., & Xu, B. (2026). KNNDA: A New Perspective of Alignment Recovery for Partially View-Aligned Clustering. Proceedings of the AAAI Conference on Artificial Intelligence, 40(34), 28706-28714. https://doi.org/10.1609/aaai.v40i34.40103

Vancouver

Zhao L, Yue T, Ma S, Wang Z, Liu Z, Xu B. KNNDA: A New Perspective of Alignment Recovery for Partially View-Aligned Clustering. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(34):28706-28714. doi:10.1609/aaai.v40i34.40103

BibTeX
@article{Zhao2026,
  author = {Zhao, Liang and Yue, Tianqi and Ma, Shubin and Wang, Ziyue and Liu, ZhiYuan and Xu, Bo},
  title = {KNNDA: A New Perspective of Alignment Recovery for Partially View-Aligned Clustering},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {34},
  pages = {28706--28714},
  doi = {10.1609/aaai.v40i34.40103}
}
Kostenlos starten →