基于图卷积神经网络的城市交通态势预测算法

闫旭,范晓亮,郑传潘,臧彧,王程,程明,陈龙彪

Urban traffic flow prediction algorithm based on graph convolutional neural networks

Xu YAN,Xiao-liang FAN,Chuan-pan ZHENG,Yu ZANG,Cheng WANG,Ming CHENG,Long-biao CHEN

表 1 FAST-GC、SGC与LSGC的性质比较

Tab.1 Character comparison between FAST-GC，SGC and LSGC

模型 定义公式 参数数量 时间复杂度 FAST-GC ${ {{W} }_{ {g^m } } } \odot { {{F} }^m }$ ${N^2}$ $O({n^2})$ SGC ${{U}}\vartheta ({{\varLambda }}){{{U}}^{\rm{T}} }$ N $O({n^2})$ LSGC $\displaystyle\sum\nolimits_0^{ K - 1} { {\theta _k }{T_k }({{\varLambda } })}$ K $O({n^2})$