Deepened Graph Auto-Encoders Help Stabilize and Enhance Link Prediction

03/21/2021
by   Xinxing Wu, et al.
0

Graph neural networks have been used for a variety of learning tasks, such as link prediction, node classification, and node clustering. Among them, link prediction is a relatively under-studied graph learning task, with current state-of-the-art models based on one- or two-layer of shallow graph auto-encoder (GAE) architectures. In this paper, we focus on addressing a limitation of current methods for link prediction, which can only use shallow GAEs and variational GAEs, and creating effective methods to deepen (variational) GAE architectures to achieve stable and competitive performance. Our proposed methods innovatively incorporate standard auto-encoders (AEs) into the architectures of GAEs, where standard AEs are leveraged to learn essential, low-dimensional representations via seamlessly integrating the adjacency information and node features, while GAEs further build multi-scaled low-dimensional representations via residual connections to learn a compact overall embedding for link prediction. Empirically, extensive experiments on various benchmarking datasets verify the effectiveness of our methods and demonstrate the competitive performance of our deepened graph models for link prediction. Theoretically, we prove that our deep extensions inclusively express multiple polynomial filters with different orders.

READ FULL TEXT
research
02/24/2021

Benchmarking Graph Neural Networks on Link Prediction

In this paper, we benchmark several existing graph neural network (GNN) ...
research
06/20/2023

Variational Disentangled Graph Auto-Encoders for Link Prediction

With the explosion of graph-structured data, link prediction has emerged...
research
08/18/2021

Variational Graph Normalized Auto-Encoders

Link prediction is one of the key problems for graph-structured data. Wi...
research
02/22/2023

Do We Really Need Complicated Model Architectures For Temporal Networks?

Recurrent neural network (RNN) and self-attention mechanism (SAM) are th...
research
08/28/2019

Effective and Efficient Network Embedding Initialization via Graph Partitioning

Network embedding has been intensively studied in the literature and wid...
research
06/21/2019

Graph Star Net for Generalized Multi-Task Learning

In this work, we present graph star net (GraphStar), a novel and unified...
research
08/27/2020

DVE: Dynamic Variational Embeddings with Applications in Recommender Systems

Embedding is a useful technique to project a high-dimensional feature in...

Please sign up or login with your details

Forgot password? Click here to reset