Variational quantum algorithm for node embedding

Quantum machine learning has made remarkable progress in many important tasks.However,the gate complexity of the initial state preparation is seldom considered in lots of quantum machine learning algorithms,making them non-end-to-end.Herein,we propose a quantum algorithm for the node embedding problem that maps a node graph's topological structure to embedding vectors.The resulting quantum embedding state can be used as an input for other quantum machine learning algorithms.With O(log(N))qubits to store the information of N nodes,our algorithm will not lose quantum advantage for the subsequent quantum information processing.Moreover,owing to the use of a parameterized quantum circuit with O(poly(log(N)))depth,the resulting state can serve as an efficient quantum database.In addition,we explored the measurement complexity of the quantum node embedding algorithm,which is the main issue in training parameters,and extended the algorithm to capture high-order neighborhood information between nodes.Finally,we experimentally demonstrated our algorithm on an nuclear magnetic resonance quantum processor to solve a graph model.

Combat network link prediction based on embedding learning

Link prediction of combat networks is of significant military value for precisely identifying the vital infrastructure of the enemy target and optimizing the operational plan of our side.Due to the profound uncertainty in the battleground circumstances, the acquired topological information of the opponent combat network always presents sparse characteristics. To solve this problem, a novel approach named network embedding based combat network link prediction(NECLP) is put forward to predict missing links of sparse combat networks. First,node embedding techniques are presented to preserve as much information of the combat network as possible using a low-dimensional space. Then, we put forward a solution algorithm to predict links between combat networks based on node embedding similarity. Last, massive experiments are carried out on a real-world combat network case to verify the validity and practicality of the proposed NECLP. This paper compares six baseline methods, and experimental results show that the NECLP has outstanding performance and substantially outperforms the baseline methods.

Node and Edge Joint Embedding for Heterogeneous Information Network

Due to the heterogeneity of nodes and edges,heterogeneous network embedding is a very challenging task to embed highly coupled networks into a set of low-dimensional vectors.Existing models either only learn embedding vectors for nodes or only for edges.These two methods of embedding learning are rarely performed in the same model,and they both overlook the internal correlation between nodes and edges.To solve these problems,a node and edge joint embedding model is proposed for Heterogeneous Information Networks(HINs),called NEJE.The NEJE model can better capture the latent structural and semantic information from an HIN through two joint learning strategies:type-level joint learning and element-level joint learning.Firstly,node-type-aware structure learning and edge-type-aware semantic learning are sequentially performed on the original network and its line graph to get the initial embedding of nodes and the embedding of edges.Then,to optimize performance,type-level joint learning is performed through the alternating training of node embedding on the original network and edge embedding on the line graph.Finally,a new homogeneous network is constructed from the original heterogeneous network,and the graph attention model is further used on the new network to perform element-level joint learning.Experiments on three tasks and five public datasets show that our NEJE model performance improves by about 2.83%over other models,and even improves by 6.42%on average for the node clustering task on Digital Bibliography&Library Project(DBLP)dataset.

Research on Heterogeneous Information Network Link Prediction Based on Representation Learning

A heterogeneous information network,which is composed of various types of nodes and edges,has a complex structure and rich information content,and is widely used in social networks,academic networks,e-commerce,and other fields.Link prediction,as a key task to reveal the unobserved relationships in the network,is of great significance in heterogeneous information networks.This paper reviews the application of presentation-based learning methods in link prediction of heterogeneous information networks.This paper introduces the basic concepts of heterogeneous information networks,and the theoretical basis of representation learning,and discusses the specific application of the deep learning model in node embedding learning and link prediction in detail.The effectiveness and superiority of these methods on multiple real data sets are demonstrated by experimental verification.

IP2vec:an IP node representation model for IP geolocation

IP geolocation is essential for the territorial analysis of sensitive network entities,location-based services(LBS)and network fraud detection.It has important theoretical significance and application value.Measurement-based IP geolocation is a hot research topic.However,the existing IP geolocation algorithms cannot effectively utilize the distance characteristics of the delay,and the nodes’connection relation,resulting in high geolocation error.It is challenging to obtain the mapping between delay,nodes’connection relation,and geographical location.Based on the idea of network representation learning,we propose a representation learning model for IP nodes(IP2vec for short)and apply it to street-level IP geolocation.IP2vec model vectorizes nodes according to the connection relation and delay between nodes so that the IP vectors can reflect the distance and topological proximity between IP nodes.The steps of the street-level IP geolocation algorithm based on IP2vec model are as follows:Firstly,we measure landmarks and target IP to obtain delay and path information to construct the network topology.Secondly,we use the IP2vec model to obtain the IP vectors from the network topology.Thirdly,we train a neural network to fit the mapping relation between vectors and locations of landmarks.Finally,the vector of target IP is fed into the neural network to obtain the geographical location of target IP.The algorithm can accurately infer geographical locations of target IPs based on delay and topological proximity embedded in the IP vectors.The cross-validation experimental results on 10023 target IPs in New York,Beijing,Hong Kong,and Zhengzhou demonstrate that the proposed algorithm can achieve street-level geolocation.Compared with the existing algorithms such as Hop-Hot,IP-geolocater and SLG,the mean geolocation error of the proposed algorithm is reduced by 33%,39%,and 51%,respectively.

Extracting multi-objective multigraph features for the shortest path cost prediction:Statistics-based or learning-based?

Efficient airport airside ground movement(AAGM)is key to successful operations of urban air mobility.Recent studies have introduced the use of multi-objective multigraphs(MOMGs)as the conceptual prototype to formulate AAGM.Swift calculation of the shortest path costs is crucial for the algorithmic heuristic search on MOMGs,however,previous work chiefly focused on single-objective simple graphs(SOSGs),treated cost enquires as search problems,and failed to keep a low level of computational time and storage complexity.This paper concentrates on the conceptual prototype MOMG,and investigates its node feature extraction,which lays the foundation for efficient prediction of shortest path costs.Two extraction methods are implemented and compared:a statistics-based method that summarises 22 node physical patterns from graph theory principles,and a learning-based method that employs node embedding technique to encode graph structures into a discriminative vector space.The former method can effectively evaluate the node physical patterns and reveals their individual importance for distance prediction,while the latter provides novel practices on processing multigraphs for node embedding algorithms that can merely handle SOSGs.Three regression models are applied to predict the shortest path costs to demonstrate the performance of each.Our experiments on randomly generated benchmark MOMGs show that(i)the statistics-based method underperforms on characterising small distance values due to severe overestimation;(ii)A subset of essential physical patterns can achieve comparable or slightly better prediction accuracy than that based on a complete set of patterns;and(iii)the learning-based method consistently outperforms the statistics-based method,while maintaining a competitive level of computational complexity.