On the Internal Representations of Graph Metanetworks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yeom, Taesun, Lee, Jaeho
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910871756734464
author Yeom, Taesun
Lee, Jaeho
author_facet Yeom, Taesun
Lee, Jaeho
contents Weight space learning is an emerging paradigm in the deep learning community. The primary goal of weight space learning is to extract informative features from a set of parameters using specially designed neural networks, often referred to as \emph{metanetworks}. However, it remains unclear how these metanetworks learn solely from parameters. To address this, we take the first step toward understanding \emph{representations} of metanetworks, specifically graph metanetworks (GMNs), which achieve state-of-the-art results in this field, using centered kernel alignment (CKA). Through various experiments, we reveal that GMNs and general neural networks (\textit{e.g.,} multi-layer perceptrons (MLPs) and convolutional neural networks (CNNs)) differ in terms of their representation space.
format Preprint
id arxiv_https___arxiv_org_abs_2503_09120
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle On the Internal Representations of Graph Metanetworks
Yeom, Taesun
Lee, Jaeho
Machine Learning
Artificial Intelligence
Weight space learning is an emerging paradigm in the deep learning community. The primary goal of weight space learning is to extract informative features from a set of parameters using specially designed neural networks, often referred to as \emph{metanetworks}. However, it remains unclear how these metanetworks learn solely from parameters. To address this, we take the first step toward understanding \emph{representations} of metanetworks, specifically graph metanetworks (GMNs), which achieve state-of-the-art results in this field, using centered kernel alignment (CKA). Through various experiments, we reveal that GMNs and general neural networks (\textit{e.g.,} multi-layer perceptrons (MLPs) and convolutional neural networks (CNNs)) differ in terms of their representation space.
title On the Internal Representations of Graph Metanetworks
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2503.09120