Saved in:
Bibliographic Details
Main Author: Khorana, Rahul
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2408.16686
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914938525581312
author Khorana, Rahul
author_facet Khorana, Rahul
contents We present a novel framework for learning on CW-complex structured data points. Recent advances have discussed CW-complexes as ideal learning representations for problems in cheminformatics. However, there is a lack of available machine learning methods suitable for learning on CW-complexes. In this paper we develop notions of convolution and attention that are well defined for CW-complexes. These notions enable us to create the first Hodge informed neural network that can receive a CW-complex as input. We illustrate and interpret this framework in the context of supervised prediction.
format Preprint
id arxiv_https___arxiv_org_abs_2408_16686
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle CW-CNN & CW-AN: Convolutional Networks and Attention Networks for CW-Complexes
Khorana, Rahul
Machine Learning
We present a novel framework for learning on CW-complex structured data points. Recent advances have discussed CW-complexes as ideal learning representations for problems in cheminformatics. However, there is a lack of available machine learning methods suitable for learning on CW-complexes. In this paper we develop notions of convolution and attention that are well defined for CW-complexes. These notions enable us to create the first Hodge informed neural network that can receive a CW-complex as input. We illustrate and interpret this framework in the context of supervised prediction.
title CW-CNN & CW-AN: Convolutional Networks and Attention Networks for CW-Complexes
topic Machine Learning
url https://arxiv.org/abs/2408.16686