Graph Autoencoder with Preserving Node Attribute Similarity

Abstract

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.

KNeXT: a NetworkX-based topologically relevant KEGG parser

“…This may include the future development of tools for integrating KNeXT directly into larger packages such as meta Graphite ( Sales et al, 2019 ), netgsa ( Hellstern et al, 2021 ) or Cytoscape ( Shannon et al, 2003 ). This will also include leveraging these terminally modified pathways in algorithms that require strict neighborhood embeddings such as graph autoencoders (GAE) ( Lin et al, 2023 ). Since we have shown that these pathways exhibit a significant increase in modularity, it has been shown that GAEs may benefit from modularity-based prior communities when calculating embeddings ( Salha-Galvan et al, 2022 ).…”

Robust Overlapping Community Detection in Complex Networks With Graph Convolutional Networks and Fuzzy C-Means

“…Machine learning-based methods that leverage the potent ability of neural networks to identify node relationships within graphs outperform traditional approaches. In recent years, Graph Convolutional Network (GCN) has emerged as a robust tool for handling graph-structured data with deep learning algorithms [21,22]. GCNs has the ability to reveal higherorder structural information through non-linear feature aggregation and information propagation across the network.…”

“…GCNs has the ability to reveal higherorder structural information through non-linear feature aggregation and information propagation across the network. This lead to find wide applications in various network analysis tasks, such as link prediction, node classification, and community detection [21][22][23].…”