arrow
返回

Adaptive indefinite kernels in hyperbolic spaces

delete2025-01-01
delete0
PRE
AI
P
Pengfei Fang *
DOI:10.1016/j.neunet.2024.106803delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Learning embeddings in hyperbolic space has gained increasing interest in the community, due to its property of negative curvature, as a way of encoding data hierarchy. Recent works investigate the improvement of the representation power of hyperbolic embeddings through kernelization. However, existing developments focus on defining positive definite (pd) kernels, which may affect the intriguing property of hyperbolic spaces. This is due to the structures of hyperbolic spaces being modeled in indefinite spaces (e.g., Krein space). This paper addresses this issue by developing adaptive indefinite kernels, which can better utilize the structures in the Krein space. To this end, we first propose an adaptive embedding function in the Lorentz model and define indefinite Lorentz kernels (iLks) via the embedding function. Due to the isometric relationship between the Lorentz model and the Poincare ball, these iLks are further extended to the Poincare ball, resulting in the development of what are termed indefinite Poincare kernels (iPKs). We evaluate the proposed indefinite kernels on a diversity of learning scenarios, including image classification, few-shot learning, zero-shot learning, person re-identification, knowledge distillation, etc. We show that the proposed indefinite kernels can bring significant performance gains over the baselines and enjoy better representation power from RKKSs than pd kernels.
Keyword:
Hyperbolic space
Data hierarchy
Indefinite Lorentz kernels
Indefinite Poincare kernels

期刊

Neural Networks 封面图
Neural Networks
IF:
6.3
论文数:
8.2K
被引数:
3.0W

机构

S
southeast university - china
学者数:
5.3W
论文数: 4.9W
被引数: 57
引用论文

引用论文

A novel human leukaemic cell line, CTS, has a t(6;11) chromosomal translocation and characteristics of pluripotent stem cells
err2003-10-29
err0
PREAI
errHARUMI KAKUDA; TAKEYUKI SATO; YASUHIDE HAYASHI; YASUHIRO ENOMOTO; JUN TAKAYAMA; MUTSURO OHIRA; MASAO SETO; RYUZO UEDA; AKIRA FUSE; HIROO NIIMI
err分享
err收藏
Comparative analysis of occlusion methods for artificial sphincters人工括约肌闭塞方法的比较分析
err2020-04-07
err0
PREAI
errLeonardo Marziale; Gioia Lucarini; Tommaso Mazzocchi; Leonardo Ricotti; Arianna Menciassi
err分享
err收藏
err分享
err收藏
Poincare Kernels for Hyperbolic Representations
err2023-06-26
err1
PREAI
errFang, Pengfei; Harandi, Mehrtash; Lan, Zhenzhong; Petersson, Lars
err分享
err收藏
err分享
err收藏
学者 查看更多内容