NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphs

计算机科学 变压器 理论计算机科学 安全性令牌 图形 计算 算法 计算机网络 电压 量子力学 物理
作者
Jinsong Chen,Kaiyuan Gao,Gaichao Li,Kun He
出处
期刊:Cornell University - arXiv [Cornell University]
被引量:22
标识
DOI:10.48550/arxiv.2206.04910
摘要

The graph Transformer emerges as a new architecture and has shown superior performance on various graph mining tasks. In this work, we observe that existing graph Transformers treat nodes as independent tokens and construct a single long sequence composed of all node tokens so as to train the Transformer model, causing it hard to scale to large graphs due to the quadratic complexity on the number of nodes for the self-attention computation. To this end, we propose a Neighborhood Aggregation Graph Transformer (NAGphormer) that treats each node as a sequence containing a series of tokens constructed by our proposed Hop2Token module. For each node, Hop2Token aggregates the neighborhood features from different hops into different representations and thereby produces a sequence of token vectors as one input. In this way, NAGphormer could be trained in a mini-batch manner and thus could scale to large graphs. Moreover, we mathematically show that as compared to a category of advanced Graph Neural Networks (GNNs), the decoupled Graph Convolutional Network, NAGphormer could learn more informative node representations from the multi-hop neighborhoods. Extensive experiments on benchmark datasets from small to large are conducted to demonstrate that NAGphormer consistently outperforms existing graph Transformers and mainstream GNNs. Code is available at https://github.com/JHL-HUST/NAGphormer.
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
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
蓝胖子发布了新的文献求助10
1秒前
Encore发布了新的文献求助10
1秒前
1秒前
小菡发布了新的文献求助10
2秒前
清寒完成签到,获得积分10
3秒前
彪壮的隶完成签到,获得积分10
4秒前
七七发布了新的文献求助10
4秒前
沉沉完成签到,获得积分10
4秒前
4秒前
星辰大海应助何秋萍采纳,获得10
5秒前
斯文败类应助dhyrrr采纳,获得10
5秒前
SciGPT应助南北采纳,获得10
5秒前
5秒前
6秒前
达尔文发布了新的文献求助10
7秒前
浅香千雪发布了新的文献求助10
8秒前
Encore完成签到,获得积分10
8秒前
xingxingxing发布了新的文献求助10
8秒前
蓝胖子完成签到,获得积分10
8秒前
能干的cen发布了新的文献求助10
9秒前
9秒前
9秒前
天天快乐应助windli采纳,获得10
10秒前
shenjuan1674完成签到,获得积分10
10秒前
QQ完成签到,获得积分20
10秒前
11秒前
Camellia发布了新的文献求助10
11秒前
11秒前
orixero应助JH采纳,获得10
11秒前
梨白发布了新的文献求助10
12秒前
倩倩完成签到,获得积分10
12秒前
猪猪侠完成签到,获得积分10
12秒前
zoe完成签到,获得积分10
13秒前
好好吃饭完成签到,获得积分20
14秒前
科研通AI6.4应助虚幻的璟采纳,获得10
14秒前
苦学僧发布了新的文献求助10
14秒前
111完成签到,获得积分10
15秒前
Neo发布了新的文献求助20
15秒前
miaowuuuuuuu完成签到,获得积分10
15秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
Autoparametric Resonance in Mechanical Systems 1000
Effects of Two Weeks of Red Light Therapy on Choroidal Thickness and Axial Length in Young Adults 700
Cosmos as Art Object: Studies in Plato's Timaeus and Other Dialogues 600
Management and the Arts 510
Matrix Methods in Data Mining and Pattern Recognition Second Edition 510
Auslegungsgeschichte 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 工程类 有机化学 化学工程 生物化学 计算机科学 内科学 物理 复合材料 催化作用 细胞生物学 无机化学 光电子学 物理化学 电极 基因
热门帖子
关注 科研通微信公众号,转发送积分 7658896
求助须知:如何正确求助?哪些是违规求助? 9229305
关于积分的说明 19840840
捐赠科研通 7226217
什么是DOI,文献DOI怎么找? 3281080
关于科研通互助平台的介绍 2440992
邀请新用户注册赠送积分活动 2281032