Graph Adversarial Training: Dynamically Regularizing Based on Graph Structure

计算机科学 对抗制 图形 理论计算机科学 稳健性(进化) 人工智能 卷积神经网络 正规化(语言学) 机器学习 生物化学 化学 基因
作者
Fuli Feng,Xiangnan He,Jie Tang,Tat-Seng Chua
出处
期刊:IEEE Transactions on Knowledge and Data Engineering [IEEE Computer Society]
卷期号:33 (6): 2493-2504 被引量:86
标识
DOI:10.1109/tkde.2019.2957786
摘要

Recent efforts show that neural networks are vulnerable to small but intentional perturbations on input features in visual classification tasks. Due to the additional consideration of connections between examples (e.g., articles with citation link tend to be in the same class), graph neural networks could be more sensitive to the perturbations, since the perturbations from connected examples exacerbate the impact on a target example. Adversarial Training (AT), a dynamic regularization technique, can resist the worst-case perturbations on input features and is a promising choice to improve model robustness and generalization. However, existing AT methods focus on standard classification, being less effective when training models on graph since it does not model the impact from connected examples. In this work, we explore adversarial training on graph, aiming to improve the robustness and generalization of models learned on graph. We propose Graph Adversarial Training (GraphAT), which takes the impact from connected examples into account when learning to construct and resist perturbations. We give a general formulation of GraphAT, which can be seen as a dynamic regularization scheme based on the graph structure. To demonstrate the utility of GraphAT, we employ it on a state-of-the-art graph neural network model - Graph Convolutional Network (GCN). We conduct experiments on two citation graphs (Citeseer and Cora) and a knowledge graph (NELL), verifying the effectiveness of GraphAT which outperforms normal training on GCN by 4.51 percent in node classification accuracy. Codes are available via: https://github.com/fulifeng/GraphAT.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
刚刚
诚心的初露完成签到,获得积分10
刚刚
lyb完成签到 ,获得积分10
2秒前
风中方盒完成签到,获得积分20
2秒前
布丁圆团完成签到,获得积分10
3秒前
yikeshu完成签到,获得积分10
3秒前
Zoe完成签到 ,获得积分10
4秒前
6秒前
星辰大海应助do0采纳,获得10
7秒前
tt完成签到 ,获得积分10
8秒前
浅辰完成签到,获得积分10
9秒前
大气萤完成签到,获得积分20
10秒前
10秒前
我ppp完成签到 ,获得积分10
10秒前
11秒前
易燃物品完成签到,获得积分10
11秒前
Hello应助Ther采纳,获得10
13秒前
CherylZhao完成签到,获得积分10
14秒前
Galato发布了新的文献求助10
15秒前
颜愫完成签到,获得积分10
15秒前
安详向日葵完成签到 ,获得积分10
16秒前
拼搏的白云完成签到,获得积分10
16秒前
852应助hhh采纳,获得10
16秒前
李白白白完成签到,获得积分10
16秒前
王手完成签到,获得积分10
16秒前
17秒前
一人完成签到,获得积分10
18秒前
do0完成签到,获得积分10
19秒前
yar应助xlz110采纳,获得10
19秒前
NexusExplorer应助落寞凌波采纳,获得10
21秒前
量子星尘发布了新的文献求助10
24秒前
123完成签到 ,获得积分10
24秒前
哈哈呵完成签到,获得积分10
24秒前
24秒前
Rylee完成签到,获得积分10
24秒前
Jiro完成签到,获得积分10
26秒前
我ppp发布了新的文献求助60
27秒前
28秒前
纳米酶催化完成签到,获得积分10
29秒前
29秒前
高分求助中
【提示信息,请勿应助】关于scihub 10000
Les Mantodea de Guyane: Insecta, Polyneoptera [The Mantids of French Guiana] 3000
徐淮辽南地区新元古代叠层石及生物地层 3000
The Mother of All Tableaux: Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 3000
Handbook of Industrial Diamonds.Vol2 1100
Global Eyelash Assessment scale (GEA) 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 550
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 4038368
求助须知:如何正确求助?哪些是违规求助? 3576068
关于积分的说明 11374313
捐赠科研通 3305780
什么是DOI,文献DOI怎么找? 1819322
邀请新用户注册赠送积分活动 892672
科研通“疑难数据库(出版商)”最低求助积分说明 815029