ParamReL: Learning Parameter Space Representation via Progressively Encoding Bayesian Flow Networks
This work addresses a bottleneck in representation learning for mixed-typed noisy data, offering an incremental improvement by integrating a self-encoder into BFNs.
The paper tackles the problem that Bayesian Flow Networks (BFNs) cannot learn high-level semantic representations from parameter spaces, proposing ParamReL to learn progressive latent semantics directly from parameters, with experimental results showing superior effectiveness in tasks like conditional generation and reconstruction.
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.