paper-with-me

Papers

Discovering Universal Geometry in Embeddings with ICA

2023-05-22 · Hiroaki Yamagiwa, Momose Oyama, Hidetoshi Shimodaira

This study utilizes Independent Component Analysis (ICA) to unveil a consistent semantic structure within embeddings of words or images. Our approach extracts independent semantic components from the embeddings of a pre-trained model by leveraging anisotropic information that remains after the whitening process in Principal Component Analysis (PCA). We demonstrate that each embedding can be expressed as a composition of a few intrinsic interpretable axes and that these semantic axes remain consistent across different languages, algorithms, and modalities. The discovery of a universal semantic structure in the geometric patterns of embeddings enhances our understanding of the representations in embeddings.

📄 PDF Abstract BibTeX arXiv:2305.13175

Code (1)

shimo-lab/universal-geometry-with-ica 공식 구현

Similar Papers 제목 키워드 기반

Harnessing the Universal Geometry of Embeddings

2025-05-18 · Rishi Jha, Collin Zhang, Vitaly Shmatikov, John X. Morris

We introduce the first method for translating text embeddings from one vector space to another without any paired data, encoders, or predefined sets of matches. Our unsupervised approach translates any embedding to and f…

Attribute

PanRep: Universal node embeddings for heterogeneous graphs

2020-09-28 · Vassilis N. Ioannidis, Da Zheng, George Karypis

Learning unsupervised node embeddings facilitates several downstream tasks such as node classification and link prediction. A node embedding is universal if it is designed to be used by and benefit various downstream tas…

Graph Neural NetworkLink PredictionNode Classification

PanRep: Graph neural networks for extracting universal node embeddings in heterogeneous graphs

2020-07-20 · Vassilis N. Ioannidis, Da Zheng, George Karypis

Learning unsupervised node embeddings facilitates several downstream tasks such as node classification and link prediction. A node embedding is universal if it is designed to be used by and benefit various downstream tas…

Graph Neural NetworkLink PredictionNode Classification

Platonic Representations in the Human Brain: Unsupervised Recovery of Universal Geometry

2026-05-19 · Pablo Marcos-Manchón, Rishi Jha, Lluís Fuentemilla arxiv

The Strong Platonic Representation Hypothesis suggests that representational convergence in artificial neural networks can be harnessed constructively: embeddings can be translated across models through a universal laten…

Rediscovering Greenberg's Word Order Universals in UD

2019-08-01 · WS 2019 8 · Kim Gerdes, Sylvain Kahane, Xinying Chen