Algebraic Positional Encodings

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kogkalidis, Konstantinos, Bernardy, Jean-Philippe, Garg, Vikas
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912097535787008
author Kogkalidis, Konstantinos
Bernardy, Jean-Philippe
Garg, Vikas
author_facet Kogkalidis, Konstantinos
Bernardy, Jean-Philippe
Garg, Vikas
contents We introduce a novel positional encoding strategy for Transformer-style models, addressing the shortcomings of existing, often ad hoc, approaches. Our framework provides a flexible mapping from the algebraic specification of a domain to an interpretation as orthogonal operators. This design preserves the algebraic characteristics of the source domain, ensuring that the model upholds its desired structural properties. Our scheme can accommodate various structures, ncluding sequences, grids and trees, as well as their compositions. We conduct a series of experiments to demonstrate the practical applicability of our approach. Results suggest performance on par with or surpassing the current state-of-the-art, without hyper-parameter optimizations or "task search" of any kind. Code is available at https://github.com/konstantinosKokos/ape.
format Preprint
id arxiv_https___arxiv_org_abs_2312_16045
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Algebraic Positional Encodings
Kogkalidis, Konstantinos
Bernardy, Jean-Philippe
Garg, Vikas
Machine Learning
Artificial Intelligence
We introduce a novel positional encoding strategy for Transformer-style models, addressing the shortcomings of existing, often ad hoc, approaches. Our framework provides a flexible mapping from the algebraic specification of a domain to an interpretation as orthogonal operators. This design preserves the algebraic characteristics of the source domain, ensuring that the model upholds its desired structural properties. Our scheme can accommodate various structures, ncluding sequences, grids and trees, as well as their compositions. We conduct a series of experiments to demonstrate the practical applicability of our approach. Results suggest performance on par with or surpassing the current state-of-the-art, without hyper-parameter optimizations or "task search" of any kind. Code is available at https://github.com/konstantinosKokos/ape.
title Algebraic Positional Encodings
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2312.16045