Understanding and Mitigating Hyperbolic Dimensional Collapse in Graph Contrastive Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Yifei, Zhu, Hao, Yang, Menglin, Liu, Jiahong, Ying, Rex, King, Irwin, Koniusz, Piotr
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910839552868352
author Zhang, Yifei
Zhu, Hao
Yang, Menglin
Liu, Jiahong
Ying, Rex
King, Irwin
Koniusz, Piotr
author_facet Zhang, Yifei
Zhu, Hao
Yang, Menglin
Liu, Jiahong
Ying, Rex
King, Irwin
Koniusz, Piotr
contents Learning generalizable self-supervised graph representations for downstream tasks is challenging. To this end, Contrastive Learning (CL) has emerged as a leading approach. The embeddings of CL are arranged on a hypersphere where similarity is measured by the cosine distance. However, many real-world graphs, especially of hierarchical nature, cannot be embedded well in the Euclidean space. Although the hyperbolic embedding is suitable for hierarchical representation learning, naively applying CL to the hyperbolic space may result in the so-called dimension collapse, i.e., features will concentrate mostly within few density regions, leading to poor utilization of the whole feature space. Thus, we propose a novel contrastive learning framework to learn high-quality graph embeddings in hyperbolic space. Specifically, we design the alignment metric that effectively captures the hierarchical data-invariant information, as well as we propose a substitute of the uniformity metric to prevent the so-called dimensional collapse. We show that in the hyperbolic space one has to address the leaf- and height-level uniformity related to properties of trees. In the ambient space of the hyperbolic manifold these notions translate into imposing an isotropic ring density towards boundaries of Poincaré ball. Our experiments support the efficacy of our method.
format Preprint
id arxiv_https___arxiv_org_abs_2310_18209
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Understanding and Mitigating Hyperbolic Dimensional Collapse in Graph Contrastive Learning
Zhang, Yifei
Zhu, Hao
Yang, Menglin
Liu, Jiahong
Ying, Rex
King, Irwin
Koniusz, Piotr
Machine Learning
Artificial Intelligence
Learning generalizable self-supervised graph representations for downstream tasks is challenging. To this end, Contrastive Learning (CL) has emerged as a leading approach. The embeddings of CL are arranged on a hypersphere where similarity is measured by the cosine distance. However, many real-world graphs, especially of hierarchical nature, cannot be embedded well in the Euclidean space. Although the hyperbolic embedding is suitable for hierarchical representation learning, naively applying CL to the hyperbolic space may result in the so-called dimension collapse, i.e., features will concentrate mostly within few density regions, leading to poor utilization of the whole feature space. Thus, we propose a novel contrastive learning framework to learn high-quality graph embeddings in hyperbolic space. Specifically, we design the alignment metric that effectively captures the hierarchical data-invariant information, as well as we propose a substitute of the uniformity metric to prevent the so-called dimensional collapse. We show that in the hyperbolic space one has to address the leaf- and height-level uniformity related to properties of trees. In the ambient space of the hyperbolic manifold these notions translate into imposing an isotropic ring density towards boundaries of Poincaré ball. Our experiments support the efficacy of our method.
title Understanding and Mitigating Hyperbolic Dimensional Collapse in Graph Contrastive Learning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2310.18209