Stocks that are fundamentally connected with each other tend to move together.Considering such common trends is believed to benefit stock movement forecasting tasks.However,such signals are not trivial to model becaus...
详细信息
Stocks that are fundamentally connected with each other tend to move together.Considering such common trends is believed to benefit stock movement forecasting tasks.However,such signals are not trivial to model because the connections among stocks are not physically presented and need to be estimated from volatile data.Motivated by this observation,we propose a framework that incorporates the inter-connection of firms to forecast stock prices.To effectively utilize a large set of fundamental features,we further design a novel pipeline.First,we use variational autoencoder(VAE)to reduce the dimension of stock fundamental information and then cluster stocks into a graph structure(fundamentally clustering).Second,a hybrid model of graph convolutional network and long-short term memory network(GCN-LSTM)with an adjacency graph matrix(learnt from VAE)is proposed for graph-structured stock market forecasting.Experiments on minute-level U.S.stock market data demonstrate that our model effectively captures both spatial and temporal signals and achieves superior improvement over baseline methods.The proposed model is promising for other applications in which there is a possible but hidden spatial dependency to improve time-series prediction.
Malicious social robots are the disseminators of malicious information on social networks,which seriously affect information security and network environments.Efficient and reliable classification of social robots is ...
详细信息
Malicious social robots are the disseminators of malicious information on social networks,which seriously affect information security and network environments.Efficient and reliable classification of social robots is crucial for detecting information manipulation in social networks.Supervised classification based on manual feature extraction has been widely used in social robot detection.However,these methods not only involve the privacy of users but also ignore hidden feature information,especially the graph feature,and the label utilization rate of semi-supervised algorithms is low.Aiming at the problems of shallow feature extraction and low label utilization rate in existing social network robot detection methods,in this paper a robot detection scheme based on weighted network topology is proposed,which introduces an improved network representation learning algorithm to extract the local structure features of the network,and combined with the graph convolution network(GCN)algorithm based on the graph filter,to obtain the global structure features of the network.An end-to-end semi-supervised combination model(Semi-GSGCN)is established to detect malicious social robots.Experiments on a social network dataset(cresci-rtbust-2019)show that the proposed method has high versatility and effectiveness in detecting social robots.In addition,this method has a stronger insight into robots in social networks than other methods.
Predicting entities in knowledge graphs is a crucial research area,and convolutional neural networks(CNNs)have exhibited significant performance due to their ability to generate expressive feature embeddings.However,se...
详细信息
Predicting entities in knowledge graphs is a crucial research area,and convolutional neural networks(CNNs)have exhibited significant performance due to their ability to generate expressive feature embeddings.However,sev-eral existing methods in thisfield tend to disrupt entities and relational embed-dings,disregarding the original translation characteristics in triples,leading to incomplete feature extraction.To address this issue and preserve the translation characteristics of triples,the present study introduces a novel representation tech-nique,termed MultiGNN.The suggested approach uses a graph convolutional neural network for encoding and implements a parameter sharing technique.It employs a convolutional neural network and a translation model as decoders.The model’s parameter space is expanded to effectively integrate translation charac-teristics into the convolutional neural network,which allows it to capture these characteristics and enhance the model’s performance.The proposed method in this paper has demonstrated significant enhancements in several metrics on the public benchmark dataset when compared to the baseline method.
暂无评论