DiffKG: Knowledge Graph Diffusion Model for Recommendation (2312.16890v1)
Abstract: Knowledge Graphs (KGs) have emerged as invaluable resources for enriching recommendation systems by providing a wealth of factual information and capturing semantic relationships among items. Leveraging KGs can significantly enhance recommendation performance. However, not all relations within a KG are equally relevant or beneficial for the target recommendation task. In fact, certain item-entity connections may introduce noise or lack informative value, thus potentially misleading our understanding of user preferences. To bridge this research gap, we propose a novel knowledge graph diffusion model for recommendation, referred to as DiffKG. Our framework integrates a generative diffusion model with a data augmentation paradigm, enabling robust knowledge graph representation learning. This integration facilitates a better alignment between knowledge-aware item semantics and collaborative relation modeling. Moreover, we introduce a collaborative knowledge graph convolution mechanism that incorporates collaborative signals reflecting user-item interaction patterns, guiding the knowledge graph diffusion process. We conduct extensive experiments on three publicly available datasets, consistently demonstrating the superiority of our DiffKG compared to various competitive baselines. We provide the source code repository of our proposed DiffKG model at the following link: https://github.com/HKUDS/DiffKG.
- Graph convolutional matrix completion. arXiv preprint arXiv:1706.02263 (2017).
- Unifying knowledge graph learning and recommendation: Towards a better understanding of user preferences. In WWW. 151–161.
- Heterogeneous graph contrastive learning for recommendation. In WSDM. 544–552.
- DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models. In ICLR.
- Vector quantized diffusion model for text-to-image synthesis. In CVPR. 10696–10706.
- Lightgcn: Simplifying and powering graph convolution network for recommendation. In SIGIR. 639–648.
- Neural collaborative filtering. In WWW. 173–182.
- Denoising diffusion probabilistic models. NeurIPS 33 (2020), 6840–6851.
- Cascaded diffusion models for high fidelity image generation. JLMR 23, 1 (2022), 2249–2281.
- Graphgdp: Generative diffusion processes for permutation invariant graph generation. In ICDM. IEEE, 201–210.
- Advances in collaborative filtering. Recommender systems handbook (2021), 91–142.
- Walid Krichene and Steffen Rendle. 2020. On sampled metrics for item recommendation. In KDD. 1748–1757.
- Multi-Intention Oriented Contrastive Learning for Sequential Recommendation. In WSDM. 411–419.
- Diffusion-lm improves controllable text generation. NeurIPS 35 (2022), 4328–4343.
- Variational autoencoders for collaborative filtering. In WWW. 689–698.
- Repaint: Inpainting using denoising diffusion probabilistic models. In CVPR. 11461–11471.
- Sparsity and noise: Where knowledge graph embeddings fall short. In EMNLP. 1751–1756.
- Representation Learning with Large Language Models for Recommendation. arXiv preprint arXiv:2310.15950 (2023).
- Disentangled Contrastive Collaborative Filtering. arXiv preprint arXiv:2305.02759 (2023).
- Distillation-Enhanced Graph Masked Autoencoders for Bundle Recommendation. In SIGIR. 1660–1669.
- BPR: Bayesian personalized ranking from implicit feedback. arXiv preprint arXiv:1205.2618 (2012).
- Deep unsupervised learning using nonequilibrium thermodynamics. In ICML. PMLR, 2256–2265.
- BERT4Rec: Sequential recommendation with bidirectional encoder representations from transformer. In CIKM. 1441–1450.
- Joint knowledge pruning and recurrent graph convolution for news recommendation. In SIGIR. 51–60.
- Graph attention networks. arXiv preprint arXiv:1710.10903 (2017).
- DiGress: Discrete Denoising diffusion for graph generation. In ICLR.
- Label-free distant supervision for relation extraction via knowledge graph embedding. In EMNLP. 2246–2255.
- DKN: Deep knowledge-aware network for news recommendation. In WWW. 1835–1844.
- Knowledge-aware graph neural networks with label smoothness regularization for recommender systems. In KDD. 968–977.
- Knowledge graph convolutional networks for recommender systems. In WWW. 3307–3313.
- Diffusion Recommender Model. In SIGIR.
- Kgat: Knowledge graph attention network for recommendation. In KDD. 950–958.
- Learning intents behind interactions with knowledge graph for recommendation. In WWW. 878–887.
- Explainable reasoning over knowledge graphs for recommendation. In AAAI, Vol. 33. 5329–5336.
- Multi-Modal Self-Supervised Learning for Recommendation. In WWW. 790–800.
- LLMRec: Large Language Models with Graph Augmentation for Recommendation. arXiv preprint arXiv:2311.00423 (2023).
- Self-supervised graph learning for recommendation. In SIGIR. 726–735.
- Debiased Contrastive Learning for Sequential Recommendation. In WWW. 1063–1073.
- Knowledge graph contrastive learning for recommendation. In SIGIR. 1434–1443.
- Self-supervised learning for large-scale item recommendations. In CIKM. 4321–4330.
- Personalized entity recommendation: A heterogeneous information network approach. In WSDM. 283–292.
- Collaborative knowledge base embedding for recommender systems. In KDD. 353–362.
- Kb4rec: A data set for linking knowledge bases with recommender systems. Data Intelligence 1, 2 (2019), 121–136.
- Multi-level cross-view contrastive learning for knowledge-aware recommender system. In SIGIR. 1358–1368.
- Improving knowledge-aware recommendation with multi-level interactive contrastive learning. In CIKM. 2817–2826.