Adaptive Graph Encoder for Attributed Graph Embedding

Abstract

Attributed graph embedding, which learns vector representations from graph topology and node features, is a challenging task for graph analysis. Recently, methods based on graph convolutional networks (GCNs) have made great progress on this task. However,existing GCN-based methods have three major drawbacks. Firstly,our experiments indicate that the entanglement of graph convolutional filters and weight matrices will harm both the performance and robustness. Secondly, we show that graph convolutional filters in these methods reveal to be special cases of generalized Laplacian smoothing filters, but they do not preserve optimal low-pass characteristics. Finally, the training objectives of existing algorithms are usually recovering the adjacency matrix or feature matrix, which are not always consistent with real-world applications. To address these issues, we propose Adaptive Graph Encoder (AGE), a novel attributed graph embedding framework. AGE consists of two modules: (1) To better alleviate the high-frequency noises in the node features, AGE first applies a carefully-designed Laplacian smoothing filter. (2) AGE employs an adaptive encoder that iteratively strengthens the filtered features for better node embeddings. We conduct experiments using four public benchmark datasets to validate AGE on node clustering and link prediction tasks. Experimental results show that AGE consistently outperforms state-of-the-art graph embedding methods considerably on these tasks.

To appear in KDD 2020

References in corpus (4)

• DeepWalk: Online Learning of Social Representations
• LINE: Large-scale Information Network Embedding
• Graph Convolutional Neural Networks for Web-Scale Recommender Systems
• Community Detection as an Inference Problem

Cited by in corpus (17)

• A Comprehensive Survey on Community Detection with Deep Learning
• Graph Attention Multi-Layer Perceptron
• Self-supervised Contrastive Attributed Graph Clustering
• Grain: Improving Data Efficiency of Graph Neural Networks via Diversified Influence Maximization
• Personalized Graph Signal Processing for Collaborative Filtering
• ROD: Reception-aware Online Distillation for Sparse Graphs
• Deep Temporal Graph Clustering: A Comprehensive Benchmark and Datasets
• GraphControl: Adding Conditional Control to Universal Graph Pre-trained Models for Graph Domain Transfer Learning
• BIGNet: Pretrained Graph Neural Network for Embedding Semantic, Spatial, and Topological Data in BIM Models
• Grad: Guided Relation Diffusion Generation for Graph Augmentation in Graph Fraud Detection
• A Survey on Self-Supervised Graph Foundation Models: Knowledge-Based Perspective
• Dual-Optimized Adaptive Graph Reconstruction for Multi-View Graph Clustering
• Graph-oriented Instruction Tuning of Large Language Models for Generic Graph Mining
• Co-Membership-based Generic Anomalous Communities Detection
• Attributed Graph Clustering in Collaborative Settings
• Self-Supervised Contrastive Graph Clustering Network via Structural Information Fusion
• Scalable Deep Metric Learning on Attributed Graphs