Recommender systems based on graph embedding techniques: A comprehensive review

Abstract

As a pivotal tool to alleviate the information overload problem, recommender systems aim to predict user's preferred items from millions of candidates by analyzing observed user-item relations. As for alleviating the sparsity and cold start problems encountered by recommender systems, researchers resort to employing side information or knowledge in recommendation as a strategy for uncovering hidden (indirect) user-item relations, aiming to enrich observed information (or data) for recommendation. However, in the face of the high complexity and large scale of side information and knowledge, this strategy relies for efficient implementation on the scalability of recommendation models. Not until after the prevalence of machine learning did graph embedding techniques be a concentration, which can efficiently utilize complex and large-scale data. In light of that, equipping recommender systems with graph embedding techniques has been widely studied these years, appearing to outperform conventional recommendation implemented directly based on graph topological analysis. As the focus, this article retrospects graph embedding-based recommendation from embedding techniques for bipartite graphs, general graphs and knowledge graphs, and proposes a general design pipeline of that. In addition, after comparing several representative graph embedding-based recommendation models with the most common-used conventional recommendation models on simulations, this article manifests that the conventional models can overall outperform the graph embedding-based ones in predicting implicit user-item interactions, revealing the comparative weakness of graph embedding-based recommendation in these tasks. To foster future research, this article proposes suggestions on making a trade-off between graph embedding-based recommendation and conventional recommendation in different tasks, and puts forward open questions.

References in corpus (96)

• Adam: A Method for Stochastic Optimization
• Efficient Estimation of Word Representations in Vector Space
• Neural Machine Translation by Jointly Learning to Align and Translate
• Sequence to Sequence Learning with Neural Networks
• A Comprehensive Survey on Graph Neural Networks
• DeepWalk: Online Learning of Social Representations
• LINE: Large-scale Information Network Embedding
• Empirical Analysis of Predictive Algorithms for Collaborative Filtering
• BPR: Bayesian Personalized Ranking from Implicit Feedback
• On the difficulty of training Recurrent Neural Networks
• Link Prediction in Complex Networks: A Survey
• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• KGAT: Knowledge Graph Attention Network for Recommendation
• Graph Embedding Techniques, Applications, and Performance: A Survey
• AutoML: A Survey of the State-of-the-Art
• Networks beyond pairwise interactions: structure and dynamics
• A Neural Conversational Model
• Higher-order organization of complex networks
• RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems
• xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems
• struc2vec: Learning Node Representations from Structural Identity
• Knowledge Graph Convolutional Networks for Recommender Systems
• A Survey on Multi-view Learning
• Recommender Systems
• Solving the apparent diversity-accuracy dilemma of recommender systems
• Generalizing from a Few Examples: A Survey on Few-Shot Learning
• Explainable Recommendation: A Survey and New Perspectives
• PTE: Predictive Text Embedding through Large-scale Heterogeneous Text Networks
• Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2vec
• Layer aggregation and reducibility of multilayer interconnected networks
• Dual Learning for Machine Translation
• graph2vec: Learning Distributed Representations of Graphs
• Knowledge Graph Embedding for Link Prediction: A Comparative Analysis
• Representation Learning for Attributed Multiplex Heterogeneous Network
• Attributed Social Network Embedding
• Reinforcement Knowledge Graph Reasoning for Explainable Recommendation
• Translation-based Recommendation
• A Survey on Conversational Recommender Systems
• Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches
• A Survey on Accuracy-oriented Neural Recommendation: From Collaborative Filtering to Information-rich Recommendation
• Multi-Task Learning with Deep Neural Networks: A Survey
• Node Classification in Social Networks
• Attributed Network Embedding for Learning in a Dynamic Environment
• NVAE: A Deep Hierarchical Variational Autoencoder
• An Alternating Direction Algorithm for Matrix Completion with Nonnegative Factors
• Advances and Challenges in Conversational Recommender Systems: A Survey
• Describing Multimedia Content using Attention-based Encoder--Decoder Networks
• SHINE: Signed Heterogeneous Information Network Embedding for Sentiment Link Prediction
• Automated Machine Learning: From Principles to Practices
• Heat Conduction Process on Community Networks as a Recommendation Model
• Estimation-Action-Reflection: Towards Deep Interaction Between Conversational and Recommender Systems
• Analogical Inference for Multi-Relational Embeddings
• Graph Representation Learning: A Survey
• Causal Embeddings for Recommendation
• Research Commentary on Recommendations with Side Information: A Survey and Research Directions
• DKN: Deep Knowledge-Aware Network for News Recommendation
• Reinforced Negative Sampling over Knowledge Graph for Recommendation
• Online Learning: A Comprehensive Survey
• Machine Knowledge: Creation and Curation of Comprehensive Knowledge Bases
• Meta-Path Guided Embedding for Similarity Search in Large-Scale Heterogeneous Information Networks
• NetSMF: Large-Scale Network Embedding as Sparse Matrix Factorization
• Network-based recommendation algorithms: A review
• Deep matrix factorizations
• Recommendation model based on opinion diffusion
• Maximum Inner-Product Search using Tree Data-structures
• TransG : A Generative Mixture Model for Knowledge Graph Embedding
• Deep Learning for Sequential Recommendation: Algorithms, Influential Factors, and Evaluations
• A Survey on Session-based Recommender Systems
• Dual Supervised Learning
• Attention Models in Graphs: A Survey
• mvn2vec: Preservation and Collaboration in Multi-View Network Embedding
• Totally Homogeneous Networks
• Social Media and Information Overload: Survey Results
• A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sources
• Don't Walk, Skip! Online Learning of Multi-scale Network Embeddings
• Learning from Few Samples: A Survey
• DDTCDR: Deep Dual Transfer Cross Domain Recommendation
• Nonparametric Bayesian Factor Analysis for Dynamic Count Matrices
• Deep Learning on Knowledge Graph for Recommender System: A Survey
• Metric Factorization: Recommendation beyond Matrix Factorization
• Causal Collaborative Filtering
• Graph Learning Approaches to Recommender Systems: A Review
• Toward the Next Generation of News Recommender Systems
• Recommending investors for new startups by integrating network diffusion and investors' domain preference
• On the Normalization and Visualization of Author Co-Citation Data Salton's Cosine versus the Jaccard Index
• Hypergraphs: an introduction and review
• To go deep or wide in learning?
• HyperML: A Boosting Metric Learning Approach in Hyperbolic Space for Recommender Systems
• The essential role of time in network-based recommendation
• Comprehend DeepWalk as Matrix Factorization
• Distributed-Representation Based Hybrid Recommender System with Short Item Descriptions
• Ordinal Non-negative Matrix Factorization for Recommendation
• Hyperparameter-free and Explainable Whole Graph Embedding
• A Survey on Cross-domain Recommendation: Taxonomies, Methods, and Future Directions
• Application of Knowledge Graphs to Provide Side Information for Improved Recommendation Accuracy
• Computing Cliques and Cavities in Networks

Cited by in corpus (5)

• A Survey of Graph Neural Networks for Social Recommender Systems
• Tackling Oversmoothing in GNN via Graph Sparsification: A Truss-based Approach
• Determinable and interpretable network representation for link prediction
• Interact2Vec -- An efficient neural network-based model for simultaneously learning users and items embeddings in recommender systems
• Capturing and Anticipating User Intents in Data Analytics via Knowledge Graphs