×
Jun 26, 2023 · This paper proposes a family of positive definite kernels to embed hyperbolic representations in Hilbert spaces. To define such kernels, we ...
This work introduces valid kernel functions for hyperbolic representations and develops several positive definite kernels in hyperbolic spaces (modeled by a ...
Jun 26, 2023 · We comprehensively study the proposed kernels on a variety of challenging tasks including few-shot learning, zero-shot learning, person re- ...
Jun 6, 2023 · In this paper, we introduce valid kernel functions for hyperbolic representations. This brings in two major advantages, 1. kernelization will ...
People also ask
Oct 16, 2024 · This paper addresses this issue by developing adaptive indefinite kernels, which can better utilize the structures in the Kreĭn space.
In this paper, we address the design challenge of pd kernels for hyperbolic representations using the Poincaré model. Here, we propose several valid pd ...
Jun 26, 2023 · Embedding data in hyperbolic spaces has proven beneficial for many advanced machine learning applications. However, working in hyperbolic ...
TCSVT 2024 [Coming soon!!!] Poincaré Kernels for Hyperbolic Representations. Pengfei Fang, Mehrtash Harandi, Zhenzhong Lan and Lars Petersson IJCV 2023 ...
In this paper, we introduce valid kernel functions for hyperbolic representations. This brings in two major advantages, 1. kernelization will pave the way to ...
Current hyperbolic representation learning methods compare exam- ples with the Poincaré distance. They try to min- imize the distance of each node in a ...