Adversarial Attention-Based Variational Graph Autoencoder

Abstract

Autoencoders have been successfully used for graph embedding, and many variants have been proven to effectively express graph data and conduct graph analysis in low-dimensional space. However, previous methods ignore the structure and properties of the reconstructed graph, or they do not consider the potential data distribution in the graph, which typically leads to unsatisfactory graph embedding performance. In this paper, we propose the adversarial attention variational graph autoencoder (AAVGA), which is a novel framework that incorporates attention networks into the encoder part and uses an adversarial mechanism in embedded training. The encoder involves node neighbors in the representation of nodes by stacking attention layers, which can further improve the graph embedding performance of the encoder. At the same time, due to the adversarial mechanism, the distribution of the potential features that are generated by the encoder are closer to the actual distribution of the original graph data; thus, the decoder generates a graph that is closer to the original graph. Experimental results prove that AAVGA performs competitively with state-of-the-art popular graph encoders on three citation datasets.

Artificial Intelligence for Multimedia Signal Processing

“…As per the results in Table 7, it is evident that the proposed method is superior to the others in terms of SSIM. However, RDN [44] demonstrate higher PSNR values. While DCRN shows a better PSNR-B compared to that of DnCNN, it has comparable performance with DCSC in terms of PSNR-B using the Classic5 dataset.…”

“…All experiments were performed on an Intel Xeon Gold 5120 (14 cores @ 2.20 GHz) with 177 GB RAM and two NVIDIA Tesla V100 GPUs under the experimental environment described in Table 5. In terms of the performance of image restoration, we compared the proposed DCRN with JPEG, ARCNN [30], DnCNN [33], DCSC [42], IDCN [43] and RDN [44]. In terms of the AR performance (i.e., PSNR and SSIM), the number of parameters and total memory size, the performance comparisons between the proposed and existing methods are depicted in Figure 8.…”

“…The implicit dual-domain convolutional network (IDCN) for robust color image compression AR [43] consists of a feature encoder, correction baseline and feature decoder. Zhang et al [44] proposed a residual dense network (RDN), which consists of 16 residual dense blocks, and each dense block contains eight dense layers with local residual learning.…”

“…ARCNN [30] Low PSNR Low network complexity DnCNN [33] Medium PSNR Medium network complexity DCSC [42] Medium PSNR (High PSNR-B) Medium network complexity IDCN [43] High PSNR and PSNR-B High network complexity RDN [44] High PSNR and PSNR-B High network complexity…”

ResVGAE: Going Deeper with Residual Modules for Link Prediction

“…Weng, Z [15] depicts a variational graph auto-encoder that has an attention-based mechanism. To improve the encoder performance, they employ efficient weights for each node of the network and amplify them by analyzing which leads to improvements in the performance of the auto-encoder.…”