A5063625684- Advanced Graph Neural Networks
- Topic Modeling
- Data Quality and Management
- Domain Adaptation and Few-Shot Learning
- Recommender Systems and Techniques
- Data Management and Algorithms
- Tensor decomposition and applications
- Graph Theory and Algorithms
- Advanced Database Systems and Queries
- Web Data Mining and Analysis
University of Science and Technology of China
2020-2022
Knowledge graph embedding, which aims to represent entities and relations as low dimensional vectors (or matrices, tensors, etc.), has been shown be a powerful technique for predicting missing links in knowledge graphs. Existing embedding models mainly focus on modeling relation patterns such symmetry/antisymmetry, inversion, composition. However, many existing approaches fail model semantic hierarchies, are common real-world applications. To address this challenge, we propose novel...
Tensor factorization based models have shown great power in knowledge graph completion (KGC). However, their performance usually suffers from the overfitting problem seriously. This motivates various regularizers -- such as squared Frobenius norm and tensor nuclear while limited applicability significantly limits practical usage. To address this challenge, we propose a novel regularizer namely, DUality-induced RegulArizer (DURA) which is not only effective improving of existing but widely...
Semantic matching models-which assume that entities with similar semantics have embeddings-have shown great power in knowledge graph embeddings (KGE). Many existing semantic models use inner products embedding spaces to measure the plausibility of triples and quadruples static temporal graphs. However, vectors same another vector can still be orthogonal each other, which implies may dissimilar embeddings. This property significantly limits performance models. To address this challenge, we...
Knowledge Graphs (KGs) provide human knowledge with nodes and edges being entities relations among them, respectively.Multihop question answering over KGs-which aims to find answer of given questions through reasoning paths in KGs-has attracted great attention from both academia industry recently.However, this task remains challenging, as it requires accurately identify answers a large candidate entity set, which the size grows exponentially number hops.To tackle problem, we propose novel...
Knowledge graph embedding, which aims to represent entities and relations as low dimensional vectors (or matrices, tensors, etc.), has been shown be a powerful technique for predicting missing links in knowledge graphs. Existing embedding models mainly focus on modeling relation patterns such symmetry/antisymmetry, inversion, composition. However, many existing approaches fail model semantic hierarchies, are common real-world applications. To address this challenge, we propose novel --...
RFID technology holds the promise of real-time identifying, locating and monitoring physical objects. Event detection is key part middleware. In comparison with traditional events, events have following characteristics: large volume, temporal spatial, inaccurate etc. this paper, a high performance hierarchical complex event detecting method proposed to overcome drawback current methods. Based on query plan, uses parallel algorithm at different level improve performance. Traditional language...
Link prediction in large-scale knowledge graphs has gained increasing attention recently. The OGB-LSC team presented OGB Large-Scale Challenge (OGB-LSC), a collection of three real-world datasets for advancing the state-of-the-art graph machine learning. In this paper, we introduce solution our GraphMIRAcles WikiKG90M-LSC track @ KDD Cup 2021. track, goal is to automatically predict missing links WikiKG90M, large scale extracted from Wikidata. To address challenge, propose framework that...