# Multi-Level Graph Attention Network Contrastive Learning for Knowledge-Aware Recommendation

arXiv: https://arxiv.org/abs/2605.08499 · HTML: https://mlsanity.com/paper/2605.08499/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 39 references that are in the map.
- First posted on arXiv 8 May 2026.

## Builds on (most cited first, 27 of 27)

- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering](https://mlsanity.com/paper/1606.09375/) (2016)
- [Graph Contrastive Learning with Augmentations](https://mlsanity.com/paper/2010.13902/) (2020)
- [Wide & Deep Learning for Recommender Systems](https://mlsanity.com/paper/1606.07792/) (2016)
- [Graph Contrastive Learning with Adaptive Augmentation](https://mlsanity.com/paper/2010.14945/) (2020)
- [Deep & Cross Network for Ad Click Predictions](https://mlsanity.com/paper/1708.05123/) (2017)
- [KGAT: Knowledge Graph Attention Network for Recommendation](https://mlsanity.com/paper/1905.07854/) (2019)
- [Self-supervised Graph Learning for Recommendation](https://mlsanity.com/paper/2010.10783/) (2020)
- [Adversarial Graph Augmentation to Improve Graph Contrastive Learning](https://mlsanity.com/paper/2106.05819/) (2021)
- [Neural Factorization Machines for Sparse Predictive Analytics](https://mlsanity.com/paper/1708.05027/) (2017)
- [Are Graph Augmentations Necessary? Simple Graph Contrastive Learning for Recommendation](https://mlsanity.com/paper/2112.08679/) (2021)
- [RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems](https://mlsanity.com/paper/1803.03467/) (2018)
- [Heterogeneous Information Network Embedding for Recommendation](https://mlsanity.com/paper/1711.10730/) (2017)
- [Knowledge Graph Convolutional Networks for Recommender Systems](https://mlsanity.com/paper/1904.12575/) (2019)
- [Self-Supervised Learning for Recommender Systems: A Survey](https://mlsanity.com/paper/2203.15876/) (2022)
- [Improving Graph Collaborative Filtering with Neighborhood-enriched Contrastive Learning](https://mlsanity.com/paper/2202.06200/) (2022)
- [Contrastive Learning for Cold-Start Recommendation](https://mlsanity.com/paper/2107.05315/) (2021)
- [Self-Supervised Hypergraph Convolutional Networks for Session-based Recommendation](https://mlsanity.com/paper/2012.06852/) (2020)
- [Multi-Task Feature Learning for Knowledge Graph Enhanced Recommendation](https://mlsanity.com/paper/1901.08907/) (2019)
- [Knowledge Graph Contrastive Learning for Recommendation](https://mlsanity.com/paper/2205.00976/) (2022)
- [Gated Graph Recurrent Neural Networks](https://mlsanity.com/paper/2002.01038/) (2020)
- [Multi-level Cross-view Contrastive Learning for Knowledge-aware Recommender System](https://mlsanity.com/paper/2204.08807/) (2022)
- [Multi-view Multi-behavior Contrastive Learning in Recommendation](https://mlsanity.com/paper/2203.10576/) (2022)
- [Explainable Reasoning over Knowledge Graphs for Recommendation](https://mlsanity.com/paper/1811.04540/) (2018)
- [Contextualized Graph Attention Network for Recommendation with Item Knowledge Graph](https://mlsanity.com/paper/2004.11529/) (2020)
- [Conditional Attention Networks for Distilling Knowledge Graphs in Recommendation](https://mlsanity.com/paper/2111.02100/) (2021)
- [MVIN: Learning Multiview Items for Recommendation](https://mlsanity.com/paper/2005.12516/) (2020)

## Abstract (arXiv)

In recent years, the use of edge information provided by knowledge graphs together with the advantages of higher-order connectivity in graph neural networks for recommendation systems has become an important research direction. However, existing approaches are often limited by sparse labels, insufficient graph structure learning, and noisy entities in the knowledge graph, which reduce recommendation accuracy. To address these limitations, we propose a multi-view graph contrastive learning framework. The proposed method enhances user representations through multi-view knowledge graph distillation, enabling more accurate modeling of user preferences over entities and relations. The network aggregates neighborhood entity information to construct informative item representations. Furthermore, we design a multi-level self-supervised contrastive learning module that performs comparisons across three perspectives: Inter-Level, Intra-Level, and Interaction-Level. This design improves the model's ability to generalize across intra-class samples while increasing discrimination between inter-class samples, thereby enabling more effective multi-dimensional feature modeling. We conduct extensive experiments on three public datasets using both baseline and ablation settings. Experimental results demonstrate that the proposed framework consistently outperforms existing state-of-the-art methods. Ablation studies further verify the effectiveness of each module in the proposed model.