paper-with-me

Papers

Hyperbolic Geometry is Not Necessary: Lightweight Euclidean-Based Models for Low-Dimensional Knowledge Graph Embeddings

2021-03-27 · Findings (EMNLP) 2021 11 · Kai Wang, Yu Liu, Dan Lin, Quan Z. Sheng

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 hyperbolic geometry is much more complicated than Euclidean operations. In this paper, based on the state-of-the-art hyperbolic-based model RotH, we develop two lightweight Euclidean-based models, called RotL and Rot2L. The RotL model simplifies the hyperbolic operations while keeping the flexible normalization effect. Utilizing a novel two-layer stacked transformation and based on RotL, the Rot2L model obtains an improved representation capability, yet costs fewer parameters and calculations than RotH. The experiments on link prediction show that Rot2L achieves the state-of-the-art performance on two widely-used datasets in low-dimensional knowledge graph embeddings. Furthermore, RotL achieves similar performance as RotH but only requires half of the training time.

📄 PDF Abstract BibTeX arXiv:2103.14930

Code (0)

등록된 구현이 없습니다.

Tasks

Graph EmbeddingKnowledge Graph EmbeddingKnowledge Graph EmbeddingsLink Prediction

Similar Papers 제목 키워드 기반

Modelling brain connectomes networks: Solv is a worthy competitor to hyperbolic geometry!

2024-07-22 · Dorota Celińska-Kopczyńska, Eryk Kopczyński

Finding suitable embeddings for connectomes (spatially embedded complex networks that map neural connections in the brain) is crucial for analyzing and understanding cognitive processes. Recent studies have found two-dim…

Hyperbolic Graph Convolutional Neural Networks

2019-10-28 · NeurIPS 2019 12 · Ines Chami, Rex Ying, Christopher Ré, Jure Leskovec

Graph convolutional neural networks (GCNs) embed nodes in a graph into Euclidean space, which has been shown to incur a large distortion when embedding real-world graphs with scale-free or hierarchical structure. Hyperbo…

Link PredictionNode Classification

Two-dimensional Hyperbolic RNN Neural Quantum State

2026-06-24 · H. L. Dao arxiv

In the first part of this work, we construct the first type of two-dimensional (2D) hyperbolic neural quantum state (NQS) in the form of the Lorentz 2DRNN (Recurrent Neural Network) and benchmark its performance against …

Weighted Embeddings for Low-Dimensional Graph Representation

2024-10-08 · Thomas Bläsius, Jean-Pierre von der Heydt, Maximilian Katzmann, Nikolai Maas

Learning low-dimensional numerical representations from symbolic data, e.g., embedding the nodes of a graph into a geometric space, is an important concept in machine learning. While embedding into Euclidean space is com…

Comparing Euclidean and Hyperbolic K-Means for Generalized Category Discovery

2026-02-04 · Mohamad Dalal, Thomas B. Moeslund, Joakim Bruslund Haurum arxiv

Hyperbolic representation learning has been widely used to extract implicit hierarchies within data, and recently it has found its way to the open-world classification task of Generalized Category Discovery (GCD). Howeve…

Representation Learning