HYPER2: Hyperbolic embedding for hyper-relational link prediction
Abstract Knowledge graphs (KGs) Embedding has been broadly studied in recent years.
However, less light is shed on the ubiquitous hyper-relational KGs. Most existing hyper-…
However, less light is shed on the ubiquitous hyper-relational KGs. Most existing hyper-…
LollipopE: Bi-centered lollipop embedding for complex logic query on knowledge graph
S Yan, C Tian, Z Zhang, G Xu - Neural Networks, 2024 - Elsevier
Answering complex First-Order Logic (FOL) query plays a vital role in multi-hop knowledge
graph (KG) reasoning. Geometric methods have emerged as a promising category of …
graph (KG) reasoning. Geometric methods have emerged as a promising category of …
Polygone: Modeling N-ary relational data as gyro-polygons in hyperbolic space
S Yan, Z Zhang, X Sun, G Xu, S Li, Q Liu… - Proceedings of the …, 2022 - ojs.aaai.org
N-ary relational knowledge base (KBs) embedding aims to map binary and beyond-binary
facts into low-dimensional vector space simultaneously. Existing approaches typically …
facts into low-dimensional vector space simultaneously. Existing approaches typically …
TOT: topology-aware optimal transport for multimodal hate detection
Multimodal hate detection, which aims to identify the harmful content online such as memes,
is crucial for building a wholesome internet environment. Previous work has made …
is crucial for building a wholesome internet environment. Previous work has made …
Ultralight Hierarchical Fe3O4/MoS2/rGO/Ti3C2Tx MXene Composite Aerogels for High-Efficiency Electromagnetic Wave Absorption
S Yan, S Shao, Y Tang, X Zhang, C Guo… - … Applied Materials & …, 2024 - ACS Publications
Aerogel-based composites, renowned for their three-dimensional (3D) network architecture,
are gaining increasing attention as lightweight electromagnetic (EM) wave absorbers. …
are gaining increasing attention as lightweight electromagnetic (EM) wave absorbers. …
SKYPER: Legal case retrieval via skeleton-aware hypergraph embedding in the hyperbolic space
S Yan, Z Zhang - Information Sciences, 2024 - Elsevier
Legal Case Retrieval (LCR) plays a significant role in ensuring judicial justice in various
legal systems and has recently received increasing attention in Information Retrieval (IR) …
legal systems and has recently received increasing attention in Information Retrieval (IR) …
Modeling N-ary relational data as gyro-polygons with learnable gyro-centroid
S Yan, Z Zhang, G Xu, X Sun, S Li, S Wang - Knowledge-Based Systems, 2022 - Elsevier
Binary Knowledge base (KB) embedding has been broadly studied, while n-ary relational
KB embedding which aims to simultaneously map binary and beyond-binary facts into low-…
KB embedding which aims to simultaneously map binary and beyond-binary facts into low-…
Tackling higher-order relations and heterogeneity: Dynamic heterogeneous hypergraph network for spatiotemporal activity prediction
Spatiotemporal activity prediction aims to predict user activities at a particular time and location,
which is applicable in city planning, activity recommendations, and other domains. The …
which is applicable in city planning, activity recommendations, and other domains. The …
Representation learning of knowledge graphs with the interaction between entity types and relations
S Wang, K Fu, X Sun, Z Zhang, S Li, S Yan - Neurocomputing, 2022 - Elsevier
Abstract Representation learning of knowledge graphs is the task of representing entities and
relations of real-world knowledge as low-dimensional vectors. Some previous works have …
relations of real-world knowledge as low-dimensional vectors. Some previous works have …
Gal: Graph-induced adaptive learning for weakly supervised 3d object detection
Weakly Supervised 3D Object Detection (WS3DOD) aims to perform 3D object detection
with little reliance on 3D labels, which greatly reduces the cost of 3D annotations. In recent …
with little reliance on 3D labels, which greatly reduces the cost of 3D annotations. In recent …