Deep Parameter Interpolation for Scalar Conditioning

2025-11-25

AI Summary

Existing generative models struggle to efficiently fuse heterogeneous conditions—such as high-dimensional image features and scalar-valued time/noise levels—due to architectural coupling or redundant encoding in mainstream approaches. To address this, we propose Deep Parameter Interpolation (DPI), a lightweight, plug-and-play conditioning mechanism that dynamically interpolates between two pretrained parameter sets within the neural network’s layer-wise parameter space, guided by a learnable scalar encoding. DPI is architecture-agnostic: it requires no modification to the backbone network and seamlessly integrates with diverse generative paradigms, including diffusion models and flow matching. Experiments demonstrate that DPI improves denoising accuracy and generation quality while maintaining computational overhead comparable to baseline methods. Its generalizability is validated across multiple generative tasks, confirming robust performance without sacrificing efficiency or flexibility.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Natural Language Processing: Generation

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

We propose deep parameter interpolation (DPI), a general-purpose method for transforming an existing deep neural network architecture into one that accepts an additional scalar input. Recent deep generative models, including diffusion models and flow matching, employ a single neural network to learn a time- or noise level-dependent vector field. Designing a network architecture to accurately represent this vector field is challenging because the network must integrate information from two different sources: a high-dimensional vector (usually an image) and a scalar. Common approaches either encode the scalar as an additional image input or combine scalar and vector information in specific network components, which restricts architecture choices. Instead, we propose to maintain two learnable parameter sets within a single network and to introduce the scalar dependency by dynamically interpolating between the parameter sets based on the scalar value during training and sampling. DPI is a simple, architecture-agnostic method for adding scalar dependence to a neural network. We demonstrate that our method improves denoising performance and enhances sample quality for both diffusion and flow matching models, while achieving computational efficiency comparable to standard scalar conditioning techniques. Code is available at https://github.com/wustl-cig/parameter_interpolation.

Problem

• Enabling neural networks to process scalar inputs alongside high-dimensional data
• Overcoming architecture limitations in scalar-vector information integration
• Improving generative model performance through dynamic parameter interpolation

Innovation

• Interpolates between two learnable parameter sets dynamically
• Adds scalar dependency to neural networks architecture-agnostically
• Maintains computational efficiency while improving sample quality