DyGCN: Efficient Dynamic Graph Embedding With Graph Convolutional Network

Dynamic Neural Network Structure: A Review for its Theories and Applications

The dynamic neural network (DNN), in contrast to the static counterpart, offers numerous advantages, such as improved accuracy, efficiency, and interpretability. These benefits stem from the network's flexible structures and parameters, making it highly attractive and applicable across various domains. As the broad learning system (BLS) continues to evolve, DNNs have expanded beyond deep learning (DL), orienting a more comprehensive range of domains. Therefore, this comprehensive review article focuses on two prominent areas where DNN structures have rapidly developed: 1) DL and 2) broad learning. This article provides an in-depth exploration of the techniques related to dynamic construction and inference. Furthermore, it discusses the applications of DNNs in diverse domains while also addressing open issues and highlighting promising research directions. By offering a comprehensive understanding of DNNs, this article serves as a valuable resource for researchers, guiding them toward future investigations.

Dynamic Graph Representation Learning via Coupling-Process Model

Representation learning based on dynamic graphs has received a lot of attention in recent years due to its wide range of application scenarios. Although many discrete or continuous dynamic graph representation learning methods have been proposed, many of them ignore the role of edge types. Through the observation of dynamic graphs in the real world, it is found that the types of various edges are very different in nature. They are roughly divided into two categories according to the frequency of occurrence: evolutive edges that appear infrequently and interactive edges that appear frequently. For both types of edges, we propose a coupling-process model (DyCPM) to capture the dynamic mechanisms of them. The model not only generates low-dimensional embedding vectors of nodes, but also aggregates the structural information and temporal information of two kinds of edges. In particular, we design a neural network parameterized discrete process to depict the change law of the topology of evolutive edges and a neural network parameterized temporal point process (TPP) to characterize the temporal dynamic rule of interactive edges. More importantly, we propose a coupling mechanism to transfer the information of the two processes through a shared embedding matrix and finally generate an embedding matrix that aggregates the topology information and temporal information of the two kinds of edges for the dynamic link prediction task. We evaluate our model and several baselines on real datasets. The experimental results show that our model can better aggregate the topology information and temporal information of the two kinds of edges according to their properties and outperforms several state-of-the-art baselines in the performance of dynamic link prediction.

Dynamic network link prediction with node representation learning from graph convolutional networks

Dynamic network link prediction is extensively applicable in various scenarios, and it has progressively emerged as a focal point in data mining research. The comprehensive and accurate extraction of node information, as well as a deeper understanding of the temporal evolution pattern, are particularly crucial in the investigation of link prediction in dynamic networks. To address this issue, this paper introduces a node representation learning framework based on Graph Convolutional Networks (GCN), referred to as GCN_MA. This framework effectively combines GCN, Recurrent Neural Networks (RNN), and multi-head attention to achieve comprehensive and accurate representations of node embedding vectors. It aggregates network structural features and node features through GCN and incorporates an RNN with multi-head attention mechanisms to capture the temporal evolution patterns of dynamic networks from both global and local perspectives. Additionally, a node representation algorithm based on the node aggregation effect (NRNAE) is proposed, which synthesizes information including node aggregation and temporal evolution to comprehensively represent the structural characteristics of the network. The effectiveness of the proposed method for link prediction is validated through experiments conducted on six distinct datasets. The experimental outcomes demonstrate that the proposed approach yields satisfactory results in comparison to state-of-the-art baseline methods.