Convolutional Geometric Matrix Completion

2018/03/02 by Kai-Lang Yao, Yao, Kai-Lang, Wu-Jun Li +5
Computer Science · #Advanced Graph Neural Networks #Data Management and Algorithms #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Machine Learning (cs.LG) #Recommender Systems and Techniques #cs.IR #cs.LG

paper · pdf · doi:10.48550/arxiv.1803.00754

openalex publication_date 2018/03/02 · arxiv created 2019/05/27 · arxiv updated 2019/05/28 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Geometric matrix completion (GMC) has been proposed for recommendation by integrating the relationship (link) graphs among users/items into matrix completion (MC). Traditional GMC methods typically adopt graph regularization to impose smoothness priors for MC. Recently, geometric deep learning on graphs (GDLG) is proposed to solve the GMC problem, showing better performance than existing GMC methods including traditional graph regularization based methods. To the best of our knowledge, there exists only one GDLG method for GMC, which is called RMGCNN. RMGCNN combines graph convolutional network (GCN) and recurrent neural network (RNN) together for GMC. In the original work of RMGCNN, RMGCNN demonstrates better performance than pure GCN-based method. In this paper, we propose a new GMC method, called convolutional geometric matrix completion (CGMC), for recommendation with graphs among users/items. CGMC is a pure GCN-based method with a newly designed graph convolutional network. Experimental results on real datasets show that CGMC can outperform other state-of-the-art methods including RMGCNN in terms of both accuracy and speed.

Citations

• ADADELTA: An Adaptive Learning Rate Method
• Deep Convolutional Networks on Graph-Structured Data
• Matrix Factorization Techniques for Recommender Systems
• Long Short-Term Memory
• Laplacian Eigenmaps for Dimensionality Reduction and Data Representation
• The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
• Empirical Analysis of Predictive Algorithms for Collaborative Filtering
• A Simpler Approach to Matrix Completion
• Wavelets on graphs via spectral graph theory
• Geometric deep learning: going beyond Euclidean data
• Neural Message Passing for Quantum Chemistry
• Graph Convolutional Matrix Completion
• Inductive Representation Learning on Large Graphs
• Adaptive Sampling Towards Fast Graph Representation Learning
• Detecting Functionality-Specific Vulnerabilities via Retrieving Individual Functionality-Equivalent APIs in Open-Source Repositories
• Nonconvex Optimization Meets Low-Rank Matrix Factorization: An Overview

Related

• Geometric Matrix Completion with Recurrent Multi-Graph Neural Networks
• Graph Convolutional Matrix Completion
• Inductive Matrix Completion Using Graph Autoencoder
• SVD-GCN: A Simplified Graph Convolution Paradigm for Recommendation
• RGCF: Refined Graph Convolution Collaborative Filtering with concise and expressive embedding