图的鲁棒性论文推荐

Graph Robustness：研究图的鲁棒性，对噪声/恶意攻击的抗干扰和防御能力。比如去掉或者添加一些图结点或边，对下游任务的性能不应该造成太大的负面影响。这部分研究包括研究图攻击和图防御，挺多思想借鉴自对抗学习，如经典的GAN。
小编整理了近期该领域优质论文，现分享给大家~

1.论文名称：Adversarial Attacks on Neural Networks for Graph Data.
链接：https://www.aminer.cn/pub/5b3d98d617c44a510f8023a8
2.论文名称：Adversarial Attack on Graph Structured Data.
链接：https://www.aminer.cn/pub/5b67b47917c44aac1c863824
3.论文名称：Adversarial Attacks on Graph Neural Networks via Meta Learning.
链接：https://www.aminer.cn/pub/5cede0fcda562983788dbed8
4.论文名称：Robust Graph Convolutional Networks Against Adversarial Attacks
链接：https://www.aminer.cn/pub/5d3ed25a275ded87f97deae1
5.论文名称：Adversarial Attacks on Node Embeddings via Graph Poisoning.
链接：https://www.aminer.cn/pub/5d0b00938607575390fd1081
6.论文名称：Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective.
链接：https://www.aminer.cn/pub/5d06e488da562926acc4bd09
7.论文名称：Adversarial Examples on Graph Data: Deep Insights into Attack and Defense
链接：https://www.aminer.cn/pub/5d0b006f8607575390fc5a3c
8.论文名称：Certifiable Robustness and Robust Training for Graph Convolutional Networks.
链接：https://www.aminer.cn/pub/5d1eb9ecda562961f0b261db
9.论文名称：Graph Adversarial Training: Dynamically Regularizing Based on Graph Structure.
链接：https://www.aminer.cn/pub/5cede0fada562983788d97ed
10.论文名称：Adversarial Attack and Defense on Graph Data: A Survey
链接：https://www.aminer.cn/pub/5e85c27a91e0114016e81c5d
11.论文名称：TDGIA - Effective Injection Attacks on Graph Neural Networks.
链接：https://www.aminer.cn/pub/60c31e856750f853878868f7
12.论文名称：GNNGuard: Defending Graph Neural Networks against Adversarial Attacks
链接：https://www.aminer.cn/pub/5ee8986891e011e66831c556
13.论文名称：Graph Random Neural Networks for Semi-Supervised Learning on Graphs
链接：https://www.aminer.cn/pub/5f7fdd328de39f0828397cc3
14.论文名称：Graph Information Bottleneck
链接：https://www.aminer.cn/pub/5f7fdd328de39f08283980ba
15.论文名称：Information Obfuscation of Graph Neural Networks
链接：https://www.aminer.cn/pub/60bdde338585e32c38af4e9e
16.论文名称：Understanding Structural Vulnerability in Graph Convolutional Networks.
链接：https://www.aminer.cn/pub/60da8fc20abde95dc965f6cd
17.论文名称：Certified Robustness of Graph Neural Networks against Adversarial Structural Perturbation.
链接：https://www.aminer.cn/pub/5f4638f691e011938ffdcf97
18.论文名称：Expressive 1-Lipschitz Neural Networks for Robust Multiple Graph Learning against Adversarial Attacks
链接：https://www.aminer.cn/pub/60bdde338585e32c38af520f
19.论文名称：Reliable Graph Neural Networks via Robust Aggregation
链接：https://www.aminer.cn/pub/5f9beb8291e011dcf482d9dd
更多优质论文，尽在AMiner，主页添加关键词，系统智能推荐最新优质论文~
AMiner平台链接：https://www.aminer.cn/?f=cs