2021/11/11 by Zhao Zhang, Fuzhen Zhuang, Zhang, Zhao +11 · 1 citation
Computer Science · Engineering · #Advanced Graph Neural Networks #Artificial Intelligence (cs.AI) #Artificial intelligence #Computation and Language (cs.CL) #Computer science #Domain Adaptation and Few-Shot Learning #Embedding #Engineering #Exploit #FOS: Computer and information sciences #Graph #Image (mathematics) #Knowledge graph #Machine learning #Noise (video) #Quality (philosophy) #Reinforcement learning #Task (project management) #Theoretical computer science #Topic Modeling #cs.AI #cs.CL
paper · pdf · doi:10.48550/arxiv.2111.06103
published in arXiv (Cornell University) (Cornell University) · Accepted to TKDE
arxiv created 2021/11/11 · openalex publication_date 2021/11/11 · arxiv updated 2021/11/12 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
Nowadays, Knowledge graphs (KGs) have been playing a pivotal role in AI-related applications. Despite the large sizes, existing KGs are far from complete and comprehensive. In order to continuously enrich KGs, automatic knowledge construction and update mechanisms are usually utilized, which inevitably bring in plenty of noise. However, most existing knowledge graph embedding (KGE) methods assume that all the triple facts in KGs are correct, and project both entities and relations into a low-dimensional space without considering noise and knowledge conflicts. This will lead to low-quality and unreliable representations of KGs. To this end, in this paper, we propose a general multi-task reinforcement learning framework, which can greatly alleviate the noisy data problem. In our framework, we exploit reinforcement learning for choosing high-quality knowledge triples while filtering out the noisy ones. Also, in order to take full advantage of the correlations among semantically similar relations, the triple selection processes of similar relations are trained in a collective way with multi-task learning. Moreover, we extend popular KGE models TransE, DistMult, ConvE and RotatE with the proposed framework. Finally, the experimental validation shows that our approach is able to enhance existing KGE models and can provide more robust representations of KGs in noisy scenarios.