STCTN:一种基于时域偏倚校正与空域因果传递的时空因果表示学习方法  

STCTN:A Spatio-temporal Causal Representation Learning Method Based on Temporal Bias Adjustment and Spatial Causal Transition

作　　者：邓攀 刘俊廷 王晓[3] 贾晓丰 赵宇 汪慕澜 戴星原 DENG Pan;LIU Jun-Ting;WANG Xiao;JIA Xiao-Feng;ZHAO Yu;WANG Mu-Lan;DAI Xing-Yuan(School of Software,Beihang University,Beijing 100191;School of Computer Science and Engineering,Beihang University,Beijing 100191;School of Artificial Intelligence,Anhui University,Hefei 230601;Data Management Department,Beijing Big Data Centre,Beijing 100191;The State Key Laboratory for Management and Control of Complex Systems,Institute of Automation,Chinese Academy of Sciences,Beijing 100191)

机构地区：[1]北京航空航天大学软件学院,北京100191 [2]北京航空航天大学计算机学院,北京100191 [3]安徽大学人工智能学院,合肥230601 [4]北京市大数据中心数据管理部,北京100101 [5]中国科学院自动化研究所复杂系统管理与控制国家重点实验室,北京100190

出　　处：《计算机学报》2023年第12期2535-2550,共16页Chinese Journal of Computers

摘　　要：从时空数据中有效地提取特征表示是时空数据挖掘的基础.现有时空表示学习方法过于关注时空序列中的统计相关性,易受虚假相关性的影响,难以提取无偏、鲁棒的特征表示.本文基于结构因果模型建模时空数据的生成过程,分析观测数据中虚假相关性的成因,提出了一种基于时域偏倚校正与空域因果传递的时空因果表示学习方法.首先基于后门调整消除时域的虚假相关性,然后构建因果传递网络消除空域的虚假相关性,最后利用下游特征解码器将因果特征表示应用于下游任务中.在两个真实数据集上的实验表明,本文所提时空表示学习方法有效避免了虚假相关性的干扰,增强了模型的稳定性,使其在两个下游预测任务中对数据稀疏节点的预测误差分别降低了3%和10%.Spatio-temporal data,sampled from complex dynamical systems,is ubiquitous in real world,e.g.,traffic flow,meteorological records and energy consumption.Learning effective feature representation from spatiotemporal data is the foundation of spatiotemporal data mining.The existing models overemphasize the statistical correlations in the spatiotemporal data and are susceptible to spurious correlations,which makes it hard to extract unbiased and robust feature representation.We model the generation process of spatiotemporal data based on the structural causal model(SCM),analyze the causes of spurious correlations in observations,and propose a spatiotemporal causal representation learning method based on temporal bias adjustment and spatial causal transition.Here,we focus on two challenges in spatio-temporal representation learning:(1)Eliminating temporal confounding bias.Existing models fail to handle causal relationships and certainly not eliminate the influence of confounders in temporal domain.Hence,the second challenge is to remove confounding bias and extract unbiased temporal representations.(2)Modelling spatial causal relationships.Limited by predefined graph structures,existing models are susceptible to non-causal spatial spurious correlations so it is significant to recover underlying spatial causal structure under causal constraints.First,we eliminate temporal spurious correlation based on backdoor adjustment.Then,we construct causal transition network for eliminating spatial spurious correlation.Finally,the downstream feature decoder applies the causal representation to downstream tasks.We tackle spatio-temporal representation learning tasks from a causal perspective and analyze the causes of spatial and temporal spurious correlation in observation data.To the best of our knowledge,this is the first at-tempt to apply causal theory to spatio-temporal representation learning.Experiments on two real-world datasets show that the proposed spatiotemporal representation learning method effectively avoids the inte

关 键 词：时空表示学习 结构因果模型 虚假相关性 后门调整 因果关系 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]