Numerous works prove that existing neighbor-averaging graph neural networks(GNNs)cannot efficiently catch structure features,and many works show that injecting structure,distance,position,or spatial features can signi...Numerous works prove that existing neighbor-averaging graph neural networks(GNNs)cannot efficiently catch structure features,and many works show that injecting structure,distance,position,or spatial features can significantly improve the performance of GNNs,however,injecting high-level structure and distance into GNNs is an intuitive but untouched idea.This work sheds light on this issue and proposes a scheme to enhance graph attention networks(GATs)by encoding distance and hop-wise structure statistics.Firstly,the hop-wise structure and distributional distance information are extracted based on several hop-wise ego-nets of every target node.Secondly,the derived structure information,distance information,and intrinsic features are encoded into the same vector space and then added together to get initial embedding vectors.Thirdly,the derived embedding vectors are fed into GATs,such as GAT and adaptive graph diffusion network(AGDN)to get the soft labels.Fourthly,the soft labels are fed into correct and smooth(C&S)to conduct label propagation and get final predictions.Experiments show that the distance and hop-wise structures encoding enhanced graph attention networks(DHSEGATs)achieve a competitive result.展开更多
台区电力工单记录反映了台区运行工况和用户需求,是制定台区用电安全管理制度和满足台区用户用电需求的重要依据。针对台区电力工单高复杂性和强专业性给台区工单分类带来的难题,提出一种融合标签平滑(LS)与预训练语言模型的台区电力工...台区电力工单记录反映了台区运行工况和用户需求,是制定台区用电安全管理制度和满足台区用户用电需求的重要依据。针对台区电力工单高复杂性和强专业性给台区工单分类带来的难题,提出一种融合标签平滑(LS)与预训练语言模型的台区电力工单分类模型(MiniRBT-LSTM-GAT)。首先,利用预训练模型计算电力工单文本中的字符级特征向量表示;其次,采用双向长短期记忆网络(BiLSTM)捕捉电力文本序列中的依赖关系;再次,通过图注意力网络(GAT)聚焦对文本分类贡献大的特征信息;最后,利用LS改进损失函数以提高模型的分类精度。所提模型与当前主流的文本分类算法在农网台区电力工单数据集(RSPWO)、浙江省95598电力工单数据集(ZJPWO)和THUCNews(TsingHua University Chinese News)数据集上的实验结果表明,与电力审计文本多粒度预训练语言模型(EPAT-BERT)相比,所提模型在RSPWO、ZJPWO上的查准率和F1值分别提升了2.76、2.02个百分点和1.77、1.40个百分点;与胶囊神经网络模型BRsyn-caps(capsule network based on BERT and dependency syntax)相比,所提模型在THUCNews数据集上的查准率和准确率分别提升了0.76和0.71个百分点。可见,所提模型有效提升了台区电力工单分类的性能,并在THUCNews数据集上表现良好,验证了模型的通用性。展开更多
文摘Numerous works prove that existing neighbor-averaging graph neural networks(GNNs)cannot efficiently catch structure features,and many works show that injecting structure,distance,position,or spatial features can significantly improve the performance of GNNs,however,injecting high-level structure and distance into GNNs is an intuitive but untouched idea.This work sheds light on this issue and proposes a scheme to enhance graph attention networks(GATs)by encoding distance and hop-wise structure statistics.Firstly,the hop-wise structure and distributional distance information are extracted based on several hop-wise ego-nets of every target node.Secondly,the derived structure information,distance information,and intrinsic features are encoded into the same vector space and then added together to get initial embedding vectors.Thirdly,the derived embedding vectors are fed into GATs,such as GAT and adaptive graph diffusion network(AGDN)to get the soft labels.Fourthly,the soft labels are fed into correct and smooth(C&S)to conduct label propagation and get final predictions.Experiments show that the distance and hop-wise structures encoding enhanced graph attention networks(DHSEGATs)achieve a competitive result.
文摘台区电力工单记录反映了台区运行工况和用户需求,是制定台区用电安全管理制度和满足台区用户用电需求的重要依据。针对台区电力工单高复杂性和强专业性给台区工单分类带来的难题,提出一种融合标签平滑(LS)与预训练语言模型的台区电力工单分类模型(MiniRBT-LSTM-GAT)。首先,利用预训练模型计算电力工单文本中的字符级特征向量表示;其次,采用双向长短期记忆网络(BiLSTM)捕捉电力文本序列中的依赖关系;再次,通过图注意力网络(GAT)聚焦对文本分类贡献大的特征信息;最后,利用LS改进损失函数以提高模型的分类精度。所提模型与当前主流的文本分类算法在农网台区电力工单数据集(RSPWO)、浙江省95598电力工单数据集(ZJPWO)和THUCNews(TsingHua University Chinese News)数据集上的实验结果表明,与电力审计文本多粒度预训练语言模型(EPAT-BERT)相比,所提模型在RSPWO、ZJPWO上的查准率和F1值分别提升了2.76、2.02个百分点和1.77、1.40个百分点;与胶囊神经网络模型BRsyn-caps(capsule network based on BERT and dependency syntax)相比,所提模型在THUCNews数据集上的查准率和准确率分别提升了0.76和0.71个百分点。可见,所提模型有效提升了台区电力工单分类的性能,并在THUCNews数据集上表现良好,验证了模型的通用性。
