ParamReL: Learning Parameter Space Representation via Progressively Encoding Bayesian Flow Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Zhangkai, Fan, Xuhui, Li, Jin, Zhao, Zhilin, Chen, Hui, Cao, Longbing
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916274266701824
author Wu, Zhangkai
Fan, Xuhui
Li, Jin
Zhao, Zhilin
Chen, Hui
Cao, Longbing
author_facet Wu, Zhangkai
Fan, Xuhui
Li, Jin
Zhao, Zhilin
Chen, Hui
Cao, Longbing
contents The recently proposed Bayesian Flow Networks~(BFNs) show great potential in modeling parameter spaces, offering a unified strategy for handling continuous, discretized, and discrete data. However, BFNs cannot learn high-level semantic representation from the parameter space since {common encoders, which encode data into one static representation, cannot capture semantic changes in parameters.} This motivates a new direction: learning semantic representations hidden in the parameter spaces to characterize mixed-typed noisy data. {Accordingly, we propose a representation learning framework named ParamReL, which operates in the parameter space to obtain parameter-wise latent semantics that exhibit progressive structures. Specifically, ParamReL proposes a \emph{self-}encoder to learn latent semantics directly from parameters, rather than from observations. The encoder is then integrated into BFNs, enabling representation learning with various formats of observations. Mutual information terms further promote the disentanglement of latent semantics and capture meaningful semantics simultaneously.} We illustrate {conditional generation and reconstruction} in ParamReL via expanding BFNs, and extensive {quantitative} experimental results demonstrate the {superior effectiveness} of ParamReL in learning parameter representation.
format Preprint
id arxiv_https___arxiv_org_abs_2405_15268
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ParamReL: Learning Parameter Space Representation via Progressively Encoding Bayesian Flow Networks
Wu, Zhangkai
Fan, Xuhui
Li, Jin
Zhao, Zhilin
Chen, Hui
Cao, Longbing
Machine Learning
The recently proposed Bayesian Flow Networks~(BFNs) show great potential in modeling parameter spaces, offering a unified strategy for handling continuous, discretized, and discrete data. However, BFNs cannot learn high-level semantic representation from the parameter space since {common encoders, which encode data into one static representation, cannot capture semantic changes in parameters.} This motivates a new direction: learning semantic representations hidden in the parameter spaces to characterize mixed-typed noisy data. {Accordingly, we propose a representation learning framework named ParamReL, which operates in the parameter space to obtain parameter-wise latent semantics that exhibit progressive structures. Specifically, ParamReL proposes a \emph{self-}encoder to learn latent semantics directly from parameters, rather than from observations. The encoder is then integrated into BFNs, enabling representation learning with various formats of observations. Mutual information terms further promote the disentanglement of latent semantics and capture meaningful semantics simultaneously.} We illustrate {conditional generation and reconstruction} in ParamReL via expanding BFNs, and extensive {quantitative} experimental results demonstrate the {superior effectiveness} of ParamReL in learning parameter representation.
title ParamReL: Learning Parameter Space Representation via Progressively Encoding Bayesian Flow Networks
topic Machine Learning
url https://arxiv.org/abs/2405.15268