@inproceedings{luo-etal-2025-hdiff,
    title = "{HD}iff: Confidence-Guided Denoising Diffusion for Robust Hyper-relational Link Prediction",
    author = "Luo, Xiangfeng  and
      Zheng, Ruoxin  and
      Huang, Jianqiang  and
      Yu, Hang",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-nlpsi/2025.findings-emnlp.391/",
    doi = "10.18653/v1/2025.findings-emnlp.391",
    pages = "7417--7434",
    ISBN = "979-8-89176-335-7",
    abstract = "Although Hyper-relational Knowledge Graphs (HKGs) can model complex facts better than traditional KGs, the Hyper-relational Knowledge Graph Completion (HKGC) is more sensitive to inherent noise, particularly struggling with two prevalent HKG-specific noise types: Intra-fact Inconsistency and Cross-fact Association Noise.To address these challenges, we propose \textbf{HDiff}, a novel conditional denoising diffusion framework for robust HKGC that learns to reverse structured noise corruption. HDiff integrates a \textbf{Consistency-Enhanced Global Encoder (CGE)} using contrastive learning to enforce intra-fact consistency and a \textbf{Context-Guided Denoiser (CGD)} performing iterative refinement. The CGD features dual conditioning leveraging CGE{'}s global context and local confidence estimates, effectively combatting both noise types. Extensive experiments demonstrate that HDiff substantially outperforms state-of-the-art HKGC methods, highlighting its effectiveness and significant robustness, particularly under noisy conditions."
}