图网络

来自集智百科 - 复杂系统|人工智能|复杂科学|复杂网络|自组织
跳到导航 跳到搜索

此词条暂由彩云小译翻译，翻译字数共136，未经人工整理和审校，带来阅读不便，请见谅。

A graph neural network (GNN) is a class of neural networks for processing data represented by graph data structures.[1][2] They were popularized by their use in supervised learning on properties of various molecules.[3]

A graph neural network (GNN) is a class of neural networks for processing data represented by graph data structures. They were popularized by their use in supervised learning on properties of various molecules.

图形神经网络(GNN)是一类用图形数据结构表示数据的神经网络。它们因为在监督式学习中使用了各种分子的性质而得到推广。

Since their inception, several variants of the simple message passing neural network (MPNN) framework have been proposed.[4][5][6][7] These models optimize GNNs for use on larger graphs and apply them to domains such as social networks, citation networks, and online communities.[8]

Since their inception, several variants of the simple message passing neural network (MPNN) framework have been proposed. These models optimize GNNs for use on larger graphs and apply them to domains such as social networks, citation networks, and online communities.

从一开始，人们就提出了几种简单消息传递神经网络(MPNN)框架的变体。这些模型优化了 gnn，使之适用于较大的图表，并将其应用于诸如社会网络、引用网络和在线社区等领域。

It has been mathematically proven that GNNs are a weak form of the Weisfeiler–Lehman graph isomorphism test,[9] so any GNN model is at least as powerful as this test.[10] There is now growing interest in uniting GNNs with other so-called "geometric deep learning models"[11] to better understand how and why these models work.

It has been mathematically proven that GNNs are a weak form of the Weisfeiler–Lehman graph isomorphism test, so any GNN model is at least as powerful as this test. There is now growing interest in uniting GNNs with other so-called "geometric deep learning models" to better understand how and why these models work.

从数学上证明了 GNN 是 Weisfeiler-Lehman 图同构检验的弱形式，因此任何 GNN 模型都至少和这个检验一样有效。现在人们越来越有兴趣将 gnn 与其他所谓的“几何深度学习模型”结合起来，以便更好地理解这些模型如何以及为什么会起作用。

References

  1. ↑ Scarselli, Franco; Gori, Marco; Tsoi, Ah Chung; Hagenbuchner, Markus; Monfardini, Gabriele (2009). "The Graph Neural Network Model". IEEE Transactions on Neural Networks. 20 (1): 61–80. doi:10.1109/TNN.2008.2005605. ISSN 1941-0093. PMID 19068426. S2CID 206756462.
  2. ↑ Sanchez-Lengeling, Benjamin; Reif, Emily; Pearce, Adam; Wiltschko, Alex (2021-09-02). "A Gentle Introduction to Graph Neural Networks". Distill (in English). 6 (9): e33. doi:10.23915/distill.00033. ISSN 2476-0757.
  3. ↑ Gilmer, Justin; Schoenholz, Samuel S.; Riley, Patrick F.; Vinyals, Oriol; Dahl, George E. (2017-07-17). "Neural Message Passing for Quantum Chemistry". International Conference on Machine Learning (in English). PMLR: 1263–1272. arXiv:1704.01212.
  4. ↑ Kipf, Thomas N; Welling, Max (2016). "Semi-supervised classification with graph convolutional networks". International Conference on Learning Representations. 5 (1): 61–80. arXiv:1609.02907. doi:10.1109/TNN.2008.2005605. PMID 19068426. S2CID 206756462.
  5. ↑ Defferrard, Michaël; Bresson, Xavier; Vandergheynst, Pierre (2017-02-05). "Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering". Neural Information Processing Systems. 30. arXiv:1606.09375.
  6. ↑ Hamilton, William; Ying, Rex; Leskovec, Jure (2017). "Inductive Representation Learning on Large Graphs" (PDF). Neural Information Processing Systems. 31. arXiv:1706.02216 – via Stanford.
  7. ↑ Veličković, Petar; Cucurull, Guillem; Casanova, Arantxa; Romero, Adriana; Liò, Pietro; Bengio, Yoshua (2018-02-04). "Graph Attention Networks". International Conference on Learning Representations. 6. arXiv:1710.10903.
  8. ↑ "Stanford Large Network Dataset Collection". snap.stanford.edu. Retrieved 2021-07-05.
  9. ↑ Douglas, B. L. (2011-01-27). "The Weisfeiler–Lehman Method and Graph Isomorphism Testing". arXiv:1101.5211 [math.CO].
  10. ↑ Xu, Keyulu; Hu, Weihua; Leskovec, Jure; Jegelka, Stefanie (2019-02-22). "How Powerful are Graph Neural Networks?". International Conference on Learning Representations. 7. arXiv:1810.00826.
  11. ↑ Bronstein, Michael M.; Bruna, Joan; LeCun, Yann; Szlam, Arthur; Vandergheynst, Pierre (2017). "Geometric Deep Learning: Going beyond Euclidean data". IEEE Signal Processing Magazine. 34 (4): 18–42. arXiv:1611.08097. Bibcode:2017ISPM...34...18B. doi:10.1109/MSP.2017.2693418. ISSN 1053-5888. S2CID 15195762.

Category:Machine learning Category:Semisupervised learning Category:Artificial neural networks Category:Graph algorithms

类别: 机器学习类别: 半监督学习类别: 人工神经网络类别: 图形算法


模板:Neuroscience-stub


This page was moved from wikipedia:en:Graph neural network. Its edit history can be viewed at 图网络/edithistory

取自“https://wiki.swarma.org/index.php?title=图网络&oldid=27835”