Enhancing Recommendations With Knowledge-Guided Interest Contrast

In the digital age, the overwhelming amount of information necessitates advanced recommendation systems to deliver personalized content. However, these systems face significant challenges, such as sparse user-item interactions and long-tail bias. Recent studies construct structural learning or self-supervised learning on the interaction graph achieving a positive impact on alleviating the problems, but the interaction data itself may be far too little to solve the problems. While knowledge graphs (KGs) offer a promising solution by providing semantic depth to recommendations, their integration often introduces noise from redundant knowledge. Addressing these critical gaps, this study proposes a knowledge-guided interest contrast (KGIC) to enhance recommendations, which innovatively harmonizes collaborative filtering with semantic insights from KG. The KGIC model introduces three key innovations: (1) a knowledge filtering mechanism that selectively leverages interest-relevant signals from the knowledge graph to encode interest and avoid redundant knowledge interference; (2) an adaptive graph augmentation strategy that enhances the interaction graph based on semantic-aware interest propagation and interaction intensity estimation; and (3) a self-supervised contrastive learning task that mitigates long-tail bias and sparsity issues by homogenizing the embedding distribution between augmented views. The extensive evaluation reveals the superiority of KGIC with knowledge filtering and graph augmentation for recommendation.

• Publication year

  2026

• Venue

  IEEE Transactions on Big Data

• Publication date

  2026-02-01

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1109/TBDATA.2025.3618449
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Improving Long-Tail Item Recommendation with Graph Augmentation

  2023cited by this paper
• AF-GCN: Attribute-Fusing Graph Convolution Network for Recommendation

  2023cited by this paper
• Swarm Self-supervised Hypergraph Embedding for Recommendation

  2023cited by this paper
• Co-clustering Interactions via Attentive Hypergraph Neural Network

  2022cited by this paper
• Hypergraph Contrastive Collaborative Filtering

  2022cited by this paper
• XSimGCL: Towards Extremely Simple Graph Contrastive Learning for Recommendation

  2022influential reference
• Improving Knowledge-aware Recommendation with Multi-level Interactive Contrastive Learning

  2022cited by this paper
• On the Effectiveness of Sampled Softmax Loss for Item Recommendation

  2022cited by this paper
• Multi-level Cross-view Contrastive Learning for Knowledge-aware Recommender System

  2022influential reference
• UltraGCN: Ultra Simplification of Graph Convolutional Networks for Recommendation

  2021cited by this paper
• Learning Aligned Vertex Convolutional Networks for Graph Classification

  2021cited by this paper
• Are Graph Augmentations Necessary?: Simple Graph Contrastive Learning for Recommendation

  2021cited by this paper
• LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation

  2020influential reference
• Reinforced Negative Sampling over Knowledge Graph for Recommendation

  2020cited by this paper
• Knowledge Graph Convolutional Networks for Recommender Systems

  2019cited by this paper
• KGAT: Knowledge Graph Attention Network for Recommendation

  2019influential reference
• Reinforcement Knowledge Graph Reasoning for Explainable Recommendation

  2019cited by this paper
• Deeply Fusing Reviews and Contents for Cold Start Users in Cross-Domain Recommendation Systems

  2019cited by this paper
• Neural Graph Collaborative Filtering

  2019cited by this paper
• Explainable Reasoning over Knowledge Graphs for Recommendation

  2018cited by this paper
• Learning Graph Convolutional Networks Based on Quantum Vertex Information Propagation

  2018cited by this paper
• Inductive Representation Learning on Large Graphs

  2017cited by this paper
• Controlling Popularity Bias in Learning-to-Rank Recommendation

  2017cited by this paper
• Attentive Collaborative Filtering: Multimedia Recommendation with Item- and Component-Level Attention

  2017cited by this paper
• The MovieLens Datasets: History and Context

  2016cited by this paper
• BPR: Bayesian Personalized Ranking from Implicit Feedback

  2009cited by this paper
• Video suggestion and discovery for youtube: taking random walks through the view graph

  2008cited by this paper
• Item-based collaborative filtering recommendation algorithms

  2001cited by this paper

• No citing papers are available for this paper.