-
Article
Open AccessDeepMCGCN: Multi-channel Deep Graph Neural Networks
Graph neural networks (GNNs) have shown powerful capabilities in modeling and representing graph structural data across various graph learning tasks as an emerging deep learning approach. However, most existin...
-
Article
Open AccessImperceptible graph injection attack on graph neural networks
In recent years, Graph Neural Networks (GNNs) have achieved excellent applications in classification or prediction tasks. Recent studies have demonstrated that GNNs are vulnerable to adversarial attacks. Graph...
-
Chapter and Conference Paper
Construction and Characteristic Analysis of Two-Layer Complex Network Model
To characterize the homogeneity and heterogeneity between nodes or connecting edges, we considered the multi-relationship attributes of nodes and constructed six dual-layer network models. Firstly, based on no...
-
Article
Open AccessA Graph Representation Learning Framework Predicting Potential Multivariate Interactions
Link prediction is a widely adopted method for extracting valuable data insights from graphs, primarily aimed at predicting interactions between two nodes. However, there are not only pairwise interactions but...
-
Article
Open AccessA Novel Link Prediction Framework Based on Gravitational Field
Currently, most researchers only utilize the network information or node characteristics to calculate the connection probability between unconnected node pairs. Therefore, we attempt to project the problem of ...
-
Article
Investigation of Reducing Copper Slag Using Waste Motor Oil to Recover Matte
The traditional fossil reductant used in the copper slag cleaning process cannot fulfill the requirements of sustainable development of the copper industry. Therefore, a new approach of employing waste motor o...
-
Chapter and Conference Paper
Research on Link Prediction Algorithms Based on Multichannel Structure Modelling
Today's link prediction methods are based on the network structure using a single-channel approach for prediction, and there is a lack of link prediction algorithms constructed from a multichannel approach, wh...
-
Chapter and Conference Paper
Qinghai Embroidery Classification System and Intelligent Classification Research
Qinghai embroidery is an artistic treasure of folk embroidery in Qinghai Province. Classifying them to understand the differences between them is an important task. However, currently, there is a lack of a sys...
-
Chapter and Conference Paper
Detecting Social Robots Based on Multi-view Graph Transformer
With the development of social media, social robots are increasingly interfering in political elections and economic issues, and detecting social robots has become a long-standing but unresolved problem. Tradi...
-
Article
Apparent Viscosity Evolution of Copper Converter Slag During a Reduction Process
Decreasing copper content in slag is critical for improving copper recovery, where apparent viscosity is the main factor affecting the separation of matte/copper from the slag. The viscous behavior of copper c...
-
Chapter and Conference Paper
Hypernetwork Model Based on Logistic Regression
The evolution of hypernetworks is mostly based on growth and preferential connection. During the construction process, the number of new nodes and hyperedges is increasing infinitely. However, in the network, ...
-
Article
Text-enhanced network representation learning
Network representation learning called NRL for short aims at embedding various networks into low-dimensional continuous distributed vector spaces. Most existing representation learning methods focus on learnin...
-
Chapter and Conference Paper
Improved DeepWalk Algorithm Based on Preference Random Walk
Network representation learning based on neural network originates from language modeling based on neural network. These two types of tasks are then studied and applied along different paths. DeepWalk is the m...
-
Chapter and Conference Paper
Network Representation Learning Based on Community and Text Features
Network representation learning (NRL) aims at building a low-dimensional vector for each vertex in a network, which is also increasingly recognized as an important aspect for network analysis. Some current NRL...
-
Chapter and Conference Paper
Text-Associated Max-Margin DeepWalk
Most existing network representation algorithms learn the network representations based on network structure, however, they neglect the rich external information associated with nodes (i.e. text contents, comm...
-
Chapter and Conference Paper
Research on Open Domain Question Answering System
Aiming at open domain question answering system evaluation task in the fourth CCF Natural Language Processing and Chinese Computing Conference (NLPCC2015), a solution of automatic question answering which can ...
