HierarchyAware KG Embeddings
http://www.semanlink.net/tag/hierarchy_aware_knowledge_graph_embeddings
Documents tagged with HierarchyAware KG Embeddings

[1911.09419] Learning HierarchyAware Knowledge Graph Embeddings for Link Prediction
http://www.semanlink.net/doc/2021/05/1911_09419_learning_hierarchy
Models semantic hierarchies by mapping entities into the polar coordinate system
> Specifically,
the radial coordinate aims to model entities at different levels
of the hierarchy... the angular coordinate aims to distinguish
entities at the same level of the hierarchy, and these entities
are expected to have roughly the same radii but different
angles.
20210517T15:11:47Z

[2010.00402] From Trees to Continuous Embeddings and Back: Hyperbolic Hierarchical Clustering
http://www.semanlink.net/doc/2020/10/2010_00402_from_trees_to_cont
> The key idea of our method, HypHC, is showing a direct correspondence from discrete trees to continuous representations (via the hyperbolic embeddings of their leaf nodes) and back (via a decoding algorithm that maps leaf embeddings to a dendrogram), **allowing us to search the space of discrete binary trees with continuous optimization**.
Cites [Dasgupta: A cost function for similaritybased hierarchical clustering](https://arxiv.org/abs/1510.05043)
20201003T14:46:20Z

[1910.03524] Beyond Vector Spaces: Compact Data Representation as Differentiable Weighted Graphs
http://www.semanlink.net/doc/2019/10/_1910_03524_beyond_vector_spac
> In this paper, we aim to eliminate the inductive bias imposed by the embedding space geometry. Namely, we propose to map data into more general nonvector metric spaces: a weighted graph with a shortest path distance. By design, such graphs can model arbitrary geometry with a proper configuration of edges and weights. Our main contribution is PRODIGE (Probabilistic Differentiable Graph Embeddings): a method that learns a weighted graph representation of data endtoend by gradient descent.
[Github](https://github.com/stanismorozov/prodige)
20191009T23:21:08Z

HyperE: Hyperbolic Embeddings for Entities
https://hazyresearch.github.io/hyperE/
hyperbolic entity embeddings for 100 Wikidata relationships
20180727T12:18:28Z

Tutorial on PoincarĂ© Embeddings (Jupyter Notebook )
https://nbviewer.jupyter.org/github/RaReTechnologies/gensim/blob/develop/docs/notebooks/Poincare%20Tutorial.ipynb
20180520T09:06:58Z

Implementing PoincarĂ© Embeddings  RARE Technologies
https://raretechnologies.com/implementingpoincareembeddings/
20180520T09:01:07Z

[1705.08039] PoincarĂ© Embeddings for Learning Hierarchical Representations
https://arxiv.org/pdf/1705.08039.pdf
> While complex symbolic datasets often exhibit a latent hierarchical structure, stateoftheart methods typically learn embeddings in Euclidean vector spaces, which do not account for this property. For this purpose, we introduce a new approach for learning hierarchical representations of symbolic data by embedding them into hyperbolic space
20171216T14:41:31Z