Contrastive and Generative Graph Convolutional Networks for Graph-based Semi-Supervised Learning

计算机科学 图形 判别式 理论计算机科学 标记数据 人工智能 机器学习 半监督学习 卷积神经网络 数据挖掘 模式识别(心理学)
作者
Sheng Wan,Shirui Pan,Jian Yang,Chen Gong
出处
期刊:Proceedings of the ... AAAI Conference on Artificial Intelligence [Association for the Advancement of Artificial Intelligence (AAAI)]
卷期号:35 (11): 10049-10057 被引量:104
标识
DOI:10.1609/aaai.v35i11.17206
摘要

Graph-based Semi-Supervised Learning (SSL) aims to transfer the labels of a handful of labeled data to the remaining massive unlabeled data via a graph. As one of the most popular graph-based SSL approaches, the recently proposed Graph Convolutional Networks (GCNs) have gained remarkable progress by combining the sound expressiveness of neural networks with graph structure. Nevertheless, the existing graph-based methods do not directly address the core problem of SSL, \emph{i.e.}, the shortage of supervision, and thus their performances are still very limited. To accommodate this issue, this paper presents a novel GCN-based SSL algorithm which aims to enrich the supervision signals by utilizing both data similarities and graph structure. Firstly, by designing a semi-supervised contrastive loss, the improved node representations can be generated via maximizing the agreement between different views of the same data or the data from the same class. Therefore, the rich unlabeled data and the scarce yet valuable labeled data can jointly provide abundant supervision information for learning discriminative node representations, which helps improve the subsequent classification result. Secondly, the underlying determinative relationship between the input graph topology and data features is extracted as supplementary supervision signals for SSL via using a graph generative loss related to input features. Intensive experimental results on a variety of real-world datasets firmly verify the effectiveness of our algorithm when compared with other state-of-the-art methods.
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
大幅提高文件上传限制,最高150M (2024-4-1)

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
1秒前
华仔应助lzcnextdoor采纳,获得10
1秒前
无奈的雍发布了新的文献求助10
1秒前
hhh完成签到,获得积分10
1秒前
hauxxiz发布了新的文献求助10
1秒前
扳迪完成签到,获得积分10
2秒前
李健的小迷弟应助夏茉采纳,获得10
3秒前
3秒前
吉祥完成签到 ,获得积分10
3秒前
科研通AI2S应助煎饼采纳,获得10
4秒前
5秒前
丘比特应助扳迪采纳,获得10
5秒前
呼伦贝尔大草原完成签到,获得积分10
5秒前
jin1233完成签到 ,获得积分10
5秒前
红枣泡枸杞完成签到,获得积分10
6秒前
7秒前
7秒前
夏仁培发布了新的文献求助10
7秒前
7秒前
平常的秋天完成签到,获得积分10
8秒前
靓丽念薇完成签到,获得积分10
8秒前
张三坟应助无奈的雍采纳,获得50
9秒前
10秒前
Daria完成签到,获得积分10
10秒前
胖大星完成签到,获得积分10
10秒前
10秒前
快乐蛋挞完成签到,获得积分20
11秒前
11秒前
科研通AI2S应助蝈蝈采纳,获得10
11秒前
12秒前
12秒前
12秒前
科研通AI2S应助9527采纳,获得10
12秒前
12秒前
浮夸风完成签到,获得积分10
12秒前
实验室留守儿童完成签到,获得积分10
13秒前
pluto应助redamancy采纳,获得10
13秒前
风123456发布了新的文献求助10
13秒前
在水一方应助yue采纳,获得10
13秒前
云阿柔完成签到,获得积分10
13秒前
高分求助中
Sustainability in ’Tides Chemistry 2000
Studien zur Ideengeschichte der Gesetzgebung 1000
TM 5-855-1(Fundamentals of protective design for conventional weapons) 1000
Threaded Harmony: A Sustainable Approach to Fashion 810
Handbook of the Mammals of the World – Volume 3: Primates 805
Ethnicities: Media, Health, and Coping 800
Gerard de Lairesse : an artist between stage and studio 500
热门求助领域 (近24小时)
化学 医学 生物 材料科学 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 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3074443
求助须知:如何正确求助?哪些是违规求助? 2727939
关于积分的说明 7501419
捐赠科研通 2376049
什么是DOI,文献DOI怎么找? 1259754
科研通“疑难数据库(出版商)”最低求助积分说明 610754
版权声明 597081