G
Guanglin Niu
Researcher at Beihang University
Publications - 18
Citations - 259
Guanglin Niu is an academic researcher from Beihang University. The author has contributed to research in topics: Relation (database) & Observer (quantum physics). The author has an hindex of 4, co-authored 18 publications receiving 113 citations. Previous affiliations of Guanglin Niu include Alibaba Group.
Papers
More filters
Journal ArticleDOI
Spacecraft attitude fault-tolerant control based on iterative learning observer and control allocation
TL;DR: An observer-based fault-tolerant control scheme is proposed for the attitude stabilization of rigid spacecraft in the presence of actuator fault, configuration misalignment, input saturation and even external disturbances simultaneously and can be guaranteed theoretically to be stable by the development of Lyapunov methodology.
Proceedings ArticleDOI
Relational Learning with Gated and Attentive Neighbor Aggregator for Few-Shot Knowledge Graph Completion
Guanglin Niu,Yang Li,Chengguang Tang,Ruiying Geng,Jian Dai,Qiao Liu,Hao Wang,Jian Sun,Fei Huang,Luo Si +9 more
TL;DR: Zhang et al. as mentioned in this paper proposed a few-shot relational learning with global-local framework to address the problem of noise neighbor information in knowledge graph completion, where a novel gated and attentive neighbor aggregator is built for accurately integrating the semantics of a fewshot relation's neighborhood.
Journal ArticleDOI
Observer-based fault tolerant control and experimental verification for rigid spacecraft
TL;DR: An iterative learning disturbance observer (ILDO) is developed to estimate and compensate for the synthetic disturbances mentioned above, and the uniformly ultimately bounded stability of the overall closed-loop system with observer-controller architecture could be guaranteed.
Journal ArticleDOI
Rule-Guided Compositional Representation Learning on Knowledge Graphs
TL;DR: Wang et al. as discussed by the authors propose a novel rule and path-based joint embedding (RPJE) scheme, which takes full advantage of the explainability and accuracy of logic rules, the generalization of KG embedding as well as the supplementary semantic structure of paths.
Posted Content
Rule-Guided Compositional Representation Learning on Knowledge Graphs
TL;DR: This paper proposes a novel Rule and Path-based Joint Embedding (RPJE) scheme, which takes full advantage of the explainability and accuracy of logic rules, the generalization of KG embedding as well as the supplementary semantic structure of paths.