0%

Information

  • Title: Lipschitz Normalization for Self-Attention Layers with Application to Graph Neural Networks
  • Author: George Dasoulas, Kevin Scaman, Aladin Virmaux
  • Institution: Noah’s Ark Lab, Huawei Technologies France
  • Year: 2021
  • Journal: ICML
  • Source: Arxiv, Github repository
  • Idea: 提出了 LipschitzNorm 来提高 GNN 模型性能,并利用 Lipschitz 连续性在理论上证明了方法的有效性
阅读全文 »

Information

  • Title: Gradient Normalization for Generative Adversarial Networks
  • Author: Yi-Lun Wu, Hong-Han Shuai, Zhi Rui Tam, Hong-Yu Chiu
  • Institution: (台湾)國立交通大學
  • Year: 2021
  • Journal: ICCV2021
  • Source: arxiv, open access, pdf, Official Code
  • Idea: 提出了GN对整个模型进行Lipschitz约束来提高GAN训练的稳定性
  • Cite: Yi-Lun Wu, Hong-Han Shuai, Zhi-Rui Tam, Hong-Yu Chiu; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 6373-6382
阅读全文 »