分享一下收集自己看过的关于Adversarial Training 、Knowledge Distillation、Meta-Learning方向的一些paper. 持续更新~ 欢迎Star https://github.com/xuanzebi/Paper-Knowledge_Distillation-Adversarial_Trainin…
adversarial training (MAT), a novel combination of adversarial training with meta-learning, which overcomes this challenge by meta-learning universal perturbations along with model training. MAT requires little extra computation while continuously adapting a large set of perturbations to the current model...
Adversarial Attacks on Graph Neural Networks via Meta Learning, 📝ICLR, Code Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective, 📝IJCAI, Code Adversarial Examples on Graph Data: Deep Insights into Attack and Defense, 📝IJCAI, Code A Unified Framework for Data ...
Moreover, to fast update the generator with a few observations, the entire adversarial framework is learned in the gradient-based meta-learning manner. The experimental results on AI2THOR and RoboTHOR simulators demonstrate the effectiveness of the proposed method in navigating to unseen object ...
本文介绍图对抗攻击相关的三篇文章:Adversarial Attacks on Neural Networks for Graph Data[1]、 Adversarial Attacks on Graph Neural Networks via Meta Learning[2]和Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective[3]。
展开全部 机器翻译 图表提取 Table_1 Figure_1 Figure_2 Table_2 Intriguing properties of neural networks Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks ...
论文阅读笔记《Meta-learning with Latent Embedding Optimization》 核心思想 本文提出一种基于参数优化的小样本学习算法(LEO),与MAML,Meta-SGD算法相比,本文最重要的改进就是引入了一个低维的隐空间(Latent Space)。为了方便理解本文,我们首先回顾一下MAML算法,其目标是通过元训练得到一个好的初始化模型θ\...
Note that for Adv-makeup these three models will serve as the meta-learning model. The results show that AMT-GAN has a strong attack ability in the black-box set- ting. Evaluations on image quality. Tab. 2 shows the quanti- tative evaluations on...
Implementation of the paper "Adversarial Attacks on Graph Neural Networks via Meta Learning". - GitHub - danielzuegner/gnn-meta-attack: Implementation of the paper "Adversarial Attacks on Graph Neural Networks via Meta Learning".
Adversarial Meta Sampling for Multilingual Low-Resource Speech RecognitionYubei Xiao, Ke Gong, Pan Zhou, Guolin Zheng, Xiaodan Liang, Liang Lin. AAAI 2021.RequirementsPython 3Computing power (high-end GPU) and memory space (both RAM/GPU's RAM) is extremely important if you'd like to train ...