Results 21 to 30 of about 1,384,853 (279)
Hyperbolic Geometry is Not Necessary: Lightweight Euclidean-Based Models for Low-Dimensional Knowledge Graph Embeddings [PDF]
Conference on Empirical Methods in Natural Language Processing, 2021 Recent knowledge graph embedding (KGE) models based on hyperbolic geometry have shown great potential in a low-dimensional embedding space. However, the necessity of hyperbolic space in KGE is still questionable, because the calculation based on ...
Kai Wang, Yu Liu, Dan Lin, Quan Z. Sheng
semanticscholar +1 more source
Extracting Event Temporal Relations via Hyperbolic Geometry [PDF]
Conference on Empirical Methods in Natural Language Processing, 2021 Detecting events and their evolution through time is a crucial task in natural language understanding. Recent neural approaches to event temporal relation extraction typically map events to embeddings in the Euclidean space and train a classifier to ...
Xingwei Tan, Gabriele Pergola, Yulan He
semanticscholar +1 more source
HyperText: Endowing FastText with Hyperbolic Geometry [PDF]
Findings, 2020 Natural language data exhibit tree-like hierarchical structures such as the hypernym-hyponym hierarchy in WordNet. FastText, as the state-of-the-art text classifier based on shallow neural network in Euclidean space, may not represent such hierarchies ...
Yudong Zhu +5 more
semanticscholar +1 more source
Performance of Hyperbolic Geometry Models on Top-N Recommendation Tasks [PDF]
ACM Conference on Recommender Systems, 2020 We introduce a simple autoencoder based on hyperbolic geometry for solving standard collaborative filtering problem. In contrast to many modern deep learning techniques, we build our solution using only a single hidden layer. Remarkably, even with such a
L. Mirvakhabova +4 more
semanticscholar +1 more source
Beta-star polytopes and hyperbolic stochastic geometry [PDF]
Advances in Mathematics, 2021 Motivated by problems of hyperbolic stochastic geometry we introduce and study the class of beta-star polytopes. A beta-star polytope is defined as the convex hull of an inhomogeneous Poisson processes on the complement of the unit ball in R d with ...
Thomas Godland +2 more
semanticscholar +1 more source
The signature and cusp geometry of hyperbolic knots [PDF]
Geometry & Topology, 2021 We introduce a new real-valued invariant called the natural slope of a hyperbolic knot in the 3-sphere, which is defined in terms of its cusp geometry.
A. Davies +3 more
semanticscholar +1 more source
The Kuramoto model on a sphere: Explaining its low-dimensional dynamics with group theory and hyperbolic geometry. [PDF]
Chaos, 2019 We study a system of N identical interacting particles moving on the unit sphere in d-dimensional space. The particles are self-propelled and coupled all to all, and their motion is heavily overdamped.
Max Lipton, Renato Mirollo, S. Strogatz
semanticscholar +1 more source
KONFLIK KOGNITIF MAHASISWA DALAM MEMAHAMI KONSEP GEOMETRI HIPERBOLIK DAN ELLIPTIK
Jupitek, 2020 Using schemes of Euclid's geometrical concepts in long-term memory to understand hyperbolic geometry and elliptic geometry concepts with assimilation and accommodation allows for cognitive conflict.
Mega Teguh Budiarto, Rini Setyaningsih
doaj +1 more source
Hyperbolic matrix factorization improves prediction of drug-target associations
Scientific Reports, 2023 Past research in computational systems biology has focused more on the development and applications of advanced statistical and numerical optimization techniques and much less on understanding the geometry of the biological space.
Aleksandar Poleksic
doaj +1 more source
Random Motions at Finite Velocity on Non-Euclidean Spaces
Mathematics, 2022 In this paper, random motions at finite velocity on the Poincaré half-plane and on the unit-radius sphere are studied. The moving particle at each Poisson event chooses a uniformly distributed direction independent of the previous evolution. This implies
Francesco Cybo Ottone, Enzo Orsingher
doaj +1 more source