EUVIMEDEUVIMED entdecken
Crossref

WAGE: Weight-Sharing Attribute-Missing Graph Autoencoder

Wenxuan Tu, Sihang Zhou, Xinwang Liu, Zhiping Cai, Yawei Zhao, Yue Liu, Kunlun He

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-07 · 47 (7) · 5760-5777

DOI: 10.1109/tpami.2025.3554053 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-07. Verfasst von Wenxuan Tu und 6 weiteren Autor:innen. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 73 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Hainan University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Attribute-missing graph learning, a common yet challenging problem, has recently attracted considerable attention. Existing efforts have at least one of the following limitations: 1) lack a noise filtering and information enhancing scheme, resulting in less comprehensive data completion; 2) isolate the node attribute and graph structure encoding processes, introducing more parameters and failing to take full advantage of the two types of information; and 3) impose overly strict distribution assumptions on the latent variables, leading to biased or less discriminative node representations. To tackle the issues, based on the idea of introducing intimate information interaction between the two information sources, we propose Weight-sharing Attribute-missing Graph autoEncoder (WAGE) to boost the expressive capacity of node representations for high-quality missing attribute reconstruction. Specifically, three strategies have been conducted. Firstly, we entangle the attribute embedding and structure embedding by introducing a weight-sharing architecture to share the parameters learned by both processes, which allows the network training to benefit from more abundant and diverse information. Secondly, we introduce a $K$K-nearest neighbor-based dual non-local learning mechanism to improve the quality of data imputation by revealing unobserved high-confidence connections while filtering unreliable ones. Thirdly, we manually mask the connections on multiple adjacency matrices and force the structure-oriented embedding sub-network to recover the actual adjacency matrix, thus enforcing the resulting network to be able to selectively exploit more high-order discriminative features for data completion. Extensive experiments on six benchmark datasets demonstrate the effectiveness and superiority of WAGE against state-of-the-art competitors.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Hainan University

Zitieren

APA

Tu, W., Zhou, S., Liu, X., Cai, Z., Zhao, Y., Liu, Y., & He, K. (2025). WAGE: Weight-Sharing Attribute-Missing Graph Autoencoder. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(7), 5760-5777. https://doi.org/10.1109/tpami.2025.3554053

Vancouver

Tu W, Zhou S, Liu X, Cai Z, Zhao Y, Liu Y, et al. WAGE: Weight-Sharing Attribute-Missing Graph Autoencoder. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(7):5760-5777. doi:10.1109/tpami.2025.3554053

BibTeX
@article{Tu2025,
  author = {Tu, Wenxuan and Zhou, Sihang and Liu, Xinwang and Cai, Zhiping and Zhao, Yawei and Liu, Yue and He, Kunlun},
  title = {WAGE: Weight-Sharing Attribute-Missing Graph Autoencoder},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2025},
  volume = {47},
  number = {7},
  pages = {5760--5777},
  doi = {10.1109/tpami.2025.3554053}
}
Kostenlos starten →