Asymmetric Learning for Graph Neural Network based Link Prediction-Reference-Cited by-同舟云学术

Asymmetric Learning for Graph Neural Network based Link Prediction

Published:2024-01-10 Issue: Volume: Page:
ISSN:1556-4681
Container-title:ACM Transactions on Knowledge Discovery from Data
language:en
Short-container-title:ACM Trans. Knowl. Discov. Data

Author:

Yao Kai-Lang¹,Li Wu-Jun¹

Affiliation:

1. National Key Laboratory for Novel Software Technology, Department of Computer Science and Technology, Nanjing University, China

Abstract

Link prediction is a fundamental problem in many graph-based applications, such as protein-protein interaction prediction. Recently, graph neural network (GNN) has been widely used for link prediction. However, existing GNN-based link prediction (GNN-LP) methods suffer from scalability problem during training for large-scale graphs, which has received little attention from researchers. In this paper, we first analyze the computation complexity of existing GNN-LP methods, revealing that one reason for the scalability problem stems from their symmetric learning strategy in applying the same class of GNN models to learn representation for both head nodes and tail nodes. We then propose a novel method, called a sym m etric l earning (AML), for GNN-LP. More specifically, AML applies a GNN model to learn head node representation while applying a multi-layer perceptron (MLP) model to learn tail node representation. To the best of our knowledge, AML is the first GNN-LP method to adopt an asymmetric learning strategy for node representation learning. Furthermore, we design a novel model architecture and apply a row-wise mini-batch sampling strategy to ensure promising model accuracy and training efficiency for AML. Experiments on three real large-scale datasets show that AML is 1.7 × ∼ 7.3 × faster in training than baselines with a symmetric learning strategy while having almost no accuracy loss.

Publisher

Association for Computing Machinery (ACM)

Subject

General Computer Science

Link

https://dl.acm.org/doi/pdf/10.1145/3640347

Reference64 articles.

1. Friends and neighbors on the Web

2. Joan Bruna , Wojciech Zaremba , Arthur Szlam , and Yann LeCun . 2014 . Spectral networks and locally connected networks on graphs . In International Conference on Learning Representations. Joan Bruna, Wojciech Zaremba, Arthur Szlam, and Yann LeCun. 2014. Spectral networks and locally connected networks on graphs. In International Conference on Learning Representations.

3. Tianle Cai , Shengjie Luo , Keyulu Xu , Di He , Tie-Yan Liu , and Liwei Wang . 2021 . GraphNorm: A principled approach to accelerating graph neural network training . In International Conference on Machine Learning. Tianle Cai, Shengjie Luo, Keyulu Xu, Di He, Tie-Yan Liu, and Liwei Wang. 2021. GraphNorm: A principled approach to accelerating graph neural network training. In International Conference on Machine Learning.

4. Benjamin Paul Chamberlain , Sergey Shirobokov , Emanuele Rossi , Fabrizio Frasca , Thomas Markovich , Nils Hammerla , Michael M. Bronstein , and Max Hansmire . 2023 . Graph neural networks for link prediction with subgraph sketching . In International Conference on Learning Representations. Benjamin Paul Chamberlain, Sergey Shirobokov, Emanuele Rossi, Fabrizio Frasca, Thomas Markovich, Nils Hammerla, Michael M. Bronstein, and Max Hansmire. 2023. Graph neural networks for link prediction with subgraph sketching. In International Conference on Learning Representations.

5. Jie Chen , Tengfei Ma , and Cao Xiao . 2018 a. FastGCN: Fast learning with graph convolutional networks via importance sampling . In International Conference on Learning Representations. Jie Chen, Tengfei Ma, and Cao Xiao. 2018a. FastGCN: Fast learning with graph convolutional networks via importance sampling. In International Conference on Learning Representations.