Graph Autoencoder with Preserving Node Attribute Similarity.

The graph autoencoder (GAE) is a powerful graph representation learning tool in an unsupervised learning manner for graph data. However, most existing GAE-based methods typically focus on preserving the graph topological structure by reconstructing the adjacency matrix while ignoring the preservation of the attribute information of nodes. Thus, the node attributes cannot be fully learned and the ability of the GAE to learn higher-quality representations is weakened. To address the issue, this paper proposes a novel GAE model that preserves node attribute similarity. The structural graph and the attribute neighbor graph, which is constructed based on the attribute similarity between nodes, are integrated as the encoder input using an effective fusion strategy. In the encoder, the attributes of the nodes can be aggregated both in their structural neighborhood and by their attribute similarity in their attribute neighborhood. This allows performing the fusion of the structural and node attribute information in the node representation by sharing the same encoder. In the decoder module, the adjacency matrix and the attribute similarity matrix of the nodes are reconstructed using dual decoders. The cross-entropy loss of the reconstructed adjacency matrix and the mean-squared error loss of the reconstructed node attribute similarity matrix are used to update the model parameters and ensure that the node representation preserves the original structural and node attribute similarity information. Extensive experiments on three citation networks show that the proposed method outperforms state-of-the-art algorithms in link prediction and node clustering tasks.

SQEIR: An epidemic virus spread analysis and prediction model.

In 2019, a new strain of coronavirus pneumonia spread quickly worldwide. Viral propagation may be simulated using the Susceptible Infectious Removed (SIR) model. However, the SIR model fails to consider that separation of patients in the COVID-19 incubation stage entails difficulty and that these patients have high transmission potential. The model also ignores the positive effect of quarantine measures on the spread of the epidemic. To address the two flaws in the SIR model, this study proposes a new infectious disease model referred to as the Susceptible Quarantined Exposed Infective Removed (SQEIR) model. The proposed model uses the weighted least squares for the optimal estimation of important parameters in the infectious disease model. Based on these parameters, new differential equations were developed to describe the spread of the epidemic. The experimental results show that this model exhibits an accuracy 6.7% higher than that of traditional infectious disease models.