Inductive Graph Pattern Learning for Recommender Systems Based on a Graph Neural Network

04/26/2019
by   Muhan Zhang, et al.
Washington University in St Louis
0

Most modern successful recommender systems are based on matrix factorization techniques, i.e., learning a latent embedding for each user and each item from the given rating matrix and use the embeddings to complete the matrix. However, these learned latent embeddings are inherently transductive and are not designed to generalize to unseen users/items or new tasks. In this paper, we aim to learn an inductive model for recommender systems based on the local graph patterns around user-item pairs. The inductive model can generalize to unseen nodes/items, and potentially also transfer to other tasks. To learn such a model, we extract a local enclosing subgraph for each training (user, item) pair, and feed the subgraphs to a graph neural network (GNN) to train a rating prediction model. We show that our model achieves highly competitive performance with state-of-the-art transductive methods, and is more stable when the rating matrix is sparse. Furthermore, our transfer learning experiment validates that the learned model is transferrable to new tasks.

READ FULL TEXT
08/25/2021

Inductive Matrix Completion Using Graph Autoencoder

Recently, the graph neural network (GNN) has shown great power in matrix...
07/31/2018

Rank and Rate: Multi-task Learning for Recommender Systems

The two main tasks in the Recommender Systems domain are the ranking and...
10/22/2019

From Personalization to Privatization: Meta Matrix Factorization for Private Rating Predictions

Matrix factorization (MF) techniques have been shown to be effective for...
01/18/2023

A Comparative Analysis of Bias Amplification in Graph Neural Network Approaches for Recommender Systems

Recommender Systems (RSs) are used to provide users with personalized it...
06/12/2023

Enhancing Topic Extraction in Recommender Systems with Entropy Regularization

In recent years, many recommender systems have utilized textual data for...
03/05/2020

Semi-supervised Learning Meets Factorization: Learning to Recommend with Chain Graph Model

Recently latent factor model (LFM) has been drawing much attention in re...

Code Repositories

IGPL

Learn graph patterns for recommender systems based on a GNN.


view repo

Please sign up or login with your details

Forgot password? Click here to reset