EUVIMEDEUVIMED entdecken
Crossref

Heterogeneous Graph Masked Autoencoders

Yijun Tian, Kaiwen Dong, Chunhui Zhang, Chuxu Zhang, Nitesh V. Chawla

Proceedings of the AAAI Conference on Artificial Intelligence · 26.06.2023 · 37 (8) · 9997-10005

DOI: 10.1609/aaai.v37i8.26192 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 26.06.2023. Verfasst von Yijun Tian und 4 weiteren Autor:innen. Die Arbeit wurde bisher 104-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Generative self-supervised learning (SSL), especially masked autoencoders, has become one of the most exciting learning paradigms and has shown great potential in handling graph data. However, real-world graphs are always heterogeneous, which poses three critical challenges that existing methods ignore: 1) how to capture complex graph structure? 2) how to incorporate various node attributes? and 3) how to encode different node positions? In light of this, we study the problem of generative SSL on heterogeneous graphs and propose HGMAE, a novel heterogeneous graph masked autoencoder model to address these challenges. HGMAE captures comprehensive graph information via two innovative masking techniques and three unique training strategies. In particular, we first develop metapath masking and adaptive attribute masking with dynamic mask rate to enable effective and stable learning on heterogeneous graphs. We then design several training strategies including metapath-based edge reconstruction to adopt complex structural information, target attribute restoration to incorporate various node attributes, and positional feature prediction to encode node positional information. Extensive experiments demonstrate that HGMAE outperforms both contrastive and generative state-of-the-art baselines on several tasks across multiple datasets. Codes are available at https://github.com/meettyj/HGMAE.

Zitieren

APA

Tian, Y., Dong, K., Zhang, C., Zhang, C., & Chawla, N. V. (2023). Heterogeneous Graph Masked Autoencoders. Proceedings of the AAAI Conference on Artificial Intelligence, 37(8), 9997-10005. https://doi.org/10.1609/aaai.v37i8.26192

Vancouver

Tian Y, Dong K, Zhang C, Zhang C, Chawla NV. Heterogeneous Graph Masked Autoencoders. Proceedings of the AAAI Conference on Artificial Intelligence. 2023;37(8):9997-10005. doi:10.1609/aaai.v37i8.26192

BibTeX
@article{Tian2023,
  author = {Tian, Yijun and Dong, Kaiwen and Zhang, Chunhui and Zhang, Chuxu and Chawla, Nitesh V.},
  title = {Heterogeneous Graph Masked Autoencoders},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2023},
  volume = {37},
  number = {8},
  pages = {9997--10005},
  doi = {10.1609/aaai.v37i8.26192}
}
Kostenlos starten →