Unifying Knowledge Graph Learning and Recommendation: Towards a Better Understanding of User Preferences

Abstract

Incorporating knowledge graph (KG) into recommender system is promising in improving the recommendation accuracy and explainability. However, existing methods largely assume that a KG is complete and simply transfer the "knowledge" in KG at the shallow level of entity raw data or embeddings. This may lead to suboptimal performance, since a practical KG can hardly be complete, and it is common that a KG has missing facts, relations, and entities. Thus, we argue that it is crucial to consider the incomplete nature of KG when incorporating it into recommender system. In this paper, we jointly learn the model of recommendation and knowledge graph completion. Distinct from previous KG-based recommendation methods, we transfer the relation information in KG, so as to understand the reasons that a user likes an item. As an example, if a user has watched several movies directed by (relation) the same person (entity), we can infer that the director relation plays a critical role when the user makes the decision, thus help to understand the user's preference at a finer granularity. Technically, we contribute a new translation-based recommendation model, which specially accounts for various preferences in translating a user to an item, and then jointly train it with a KG completion model by combining several transfer schemes. Extensive experiments on two benchmark datasets show that our method outperforms state-of-the-art KG-based recommendation methods. Further analysis verifies the positive effect of joint training on both tasks of recommendation and KG completion, and the advantage of our model in understanding user preference. We publish our project at https://github.com/TaoMiner/joint-kg-recommender.

11 pages, 6 figures

References in corpus (18)

• BPR: Bayesian Personalized Ranking from Implicit Feedback
• Categorical Reparameterization with Gumbel-Softmax
• Complex Embeddings for Simple Link Prediction
• Learning over Knowledge-Base Embeddings for Recommendation
• Temporal Relational Ranking for Stock Prediction
• Learning Heterogeneous Knowledge Base Embeddings for Explainable Recommendation
• Translation-based Recommendation
• Adversarial Personalized Ranking for Recommendation
• Aspect-Aware Latent Factor Model: Rating Prediction with Ratings and Reviews
• Latent Relational Metric Learning via Memory-based Attention for Collaborative Ranking
• Neural Factorization Machines for Sparse Predictive Analytics
• Modeling Relation Paths for Representation Learning of Knowledge Bases
• Neural Collective Entity Linking
• Probabilistic Reasoning via Deep Learning: Neural Association Models
• Explicit State Tracking with Semi-Supervision for Neural Dialogue Generation
• Visually Explainable Recommendation
• Do Social Explanations Work? Studying and Modeling the Effects of Social Explanations in Recommender Systems
• Factorization Machines Leveraging Lightweight Linked Open Data-enabled Features for Top-N Recommendations

Cited by in corpus (77)

• Neural Graph Collaborative Filtering
• KGAT: Knowledge Graph Attention Network for Recommendation
• Self-supervised Graph Learning for Recommendation
• Learning Intents behind Interactions with Knowledge Graph for Recommendation
• Knowledge Graph Contrastive Learning for Recommendation
• A Survey on Accuracy-oriented Neural Recommendation: From Collaborative Filtering to Information-rich Recommendation
• Multi-level Cross-view Contrastive Learning for Knowledge-aware Recommender System
• Research Commentary on Recommendations with Side Information: A Survey and Research Directions
• Knowledge Graph Self-Supervised Rationalization for Recommendation
• DisenHAN: Disentangled Heterogeneous Graph Attention Network for Recommendation
• Reinforced Negative Sampling over Knowledge Graph for Recommendation
• Knowledge Graph Reasoning with Relational Digraph
• BERT Based Clinical Knowledge Extraction for Biomedical Knowledge Graph Construction and Analysis
• KRED: Knowledge-Aware Document Representation for News Recommendations
• Temporal Knowledge Graph Completion: A Survey
• Improving Knowledge-aware Recommendation with Multi-level Interactive Contrastive Learning
• CAFE: Coarse-to-Fine Neural Symbolic Reasoning for Explainable Recommendation
• Graph Convolution Machine for Context-aware Recommender System
• Multi-Behavior Sequential Recommendation with Temporal Graph Transformer
• ATBRG: Adaptive Target-Behavior Relational Graph Network for Effective Recommendation
• MVIN: Learning Multiview Items for Recommendation
• FairSR: Fairness-aware Sequential Recommendation through Multi-Task Learning with Preference Graph Embeddings
• Post Processing Recommender Systems with Knowledge Graphs for Recency, Popularity, and Diversity of Explanations
• Learning to Ask Appropriate Questions in Conversational Recommendation
• Variational Reasoning over Incomplete Knowledge Graphs for Conversational Recommendation
• Knowledge-guided Deep Reinforcement Learning for Interactive Recommendation
• VRKG4Rec: Virtual Relational Knowledge Graphs for Recommendation
• RecBole: Towards a Unified, Comprehensive and Efficient Framework for Recommendation Algorithms
• Knowledge-refined Denoising Network for Robust Recommendation
• Ultrahyperbolic Knowledge Graph Embeddings
• Heterogeneous Network Representation Learning: A Unified Framework with Survey and Benchmark
• Recent Advances in Heterogeneous Relation Learning for Recommendation
• A Survey on Knowledge Graph-Based Recommender Systems
• DaisyRec 2.0: Benchmarking Recommendation for Rigorous Evaluation
• Knowledge Enhanced Multi-intent Transformer Network for Recommendation
• Improving Neural Relation Extraction with Implicit Mutual Relations
• Toward Degree Bias in Embedding-Based Knowledge Graph Completion
• Schema-aware Reference as Prompt Improves Data-Efficient Knowledge Graph Construction
• Relational Collaborative Filtering:Modeling Multiple Item Relations for Recommendation
• Rethinking Collaborative Metric Learning: Toward an Efficient Alternative without Negative Sampling
• MindReader: Recommendation over Knowledge Graph Entities with Explicit User Ratings
• Comprehending Knowledge Graphs with Large Language Models for Recommender Systems
• Multi-Channel Graph Neural Network for Entity Alignment
• Recommending on graphs: a comprehensive review from a data perspective
• MTBRN: Multiplex Target-Behavior Relation Enhanced Network for Click-Through Rate Prediction
• Graph Neural News Recommendation with Long-term and Short-term Interest Modeling
• Exploring and Evaluating Attributes, Values, and Structures for Entity Alignment
• Learning to Deceive Knowledge Graph Augmented Models via Targeted Perturbation
• FeedLens: Polymorphic Lenses for Personalizing Exploratory Search over Knowledge Graphs
• LogicRec: Recommendation with Users' Logical Requirements
• Progressive Distillation Based on Masked Generation Feature Method for Knowledge Graph Completion
• TinyKG: Memory-Efficient Training Framework for Knowledge Graph Neural Recommender Systems
• Sequential Recommendation in Online Games with Multiple Sequences, Tasks and User Levels
• KG4RecEval: Does Knowledge Graph Really Matter for Recommender Systems?
• Learning Relation Prototype from Unlabeled Texts for Long-tail Relation Extraction
• Improving Location Recommendation with Urban Knowledge Graph
• Heterogeneous Graph Collaborative Filtering
• Are Negative Samples Necessary in Entity Alignment? An Approach with High Performance, Scalability and Robustness
• Contextualized Graph Attention Network for Recommendation with Item Knowledge Graph
• Low-Resource Name Tagging Learned with Weakly Labeled Data
• Searching to Sparsify Tensor Decomposition for N-ary Relational Data
• GraphSW: a training protocol based on stage-wise training for GNN-based Recommender Model
• Reinforcement Learning based Collective Entity Alignment with Adaptive Features
• Knowledge Transfer via Pre-training for Recommendation: A Review and Prospect
• Can Offline Metrics Measure Explanation Goals? A Comparative Survey Analysis of Offline Explanation Metrics in Recommender Systems
• printf: Preference Modeling Based on User Reviews with Item Images and Textual Information via Graph Learning
• Augmenting the User-Item Graph with Textual Similarity Models
• SPARK: Adaptive Low-Rank Knowledge Graph Modeling in Hybrid Geometric Spaces for Recommendation
• Personalized Hashtag Recommendation for Micro-videos
• Dual Graph Embedding for Object-Tag LinkPrediction on the Knowledge Graph
• A Concept Knowledge-Driven Keywords Retrieval Framework for Sponsored Search
• From Alignment to Assignment: Frustratingly Simple Unsupervised Entity Alignment
• Mining Implicit Entity Preference from User-Item Interaction Data for Knowledge Graph Completion via Adversarial Learning
• Conditional Attention Networks for Distilling Knowledge Graphs in Recommendation
• Are Missing Links Predictable? An Inferential Benchmark for Knowledge Graph Completion
• Inter-domain Multi-relational Link Prediction
• UGRec: Modeling Directed and Undirected Relations for Recommendation