DeepWeightFlow: Re-Basined Flow Matching for Generating Neural Network Weights

• URL: http://arxiv.org/abs/2601.05052v1
• Date: Thu, 08 Jan 2026 15:56:28 GMT
• Title: DeepWeightFlow: Re-Basined Flow Matching for Generating Neural Network Weights
• Authors: Saumya Gupta, Scott Biggs, Moritz Laber, Zohair Shafi, Robin Walters, Ayan Paul,
• Abstract summary: We present DeepWeightFlow, a Flow Matching model that operates directly in weight space to generate diverse and high-accuracy neural network weights.<n>The neural networks generated by DeepWeightFlow do not require fine-tuning to perform well and can scale to large networks.
• Score: 10.97849774373198
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Building efficient and effective generative models for neural network weights has been a research focus of significant interest that faces challenges posed by the high-dimensional weight spaces of modern neural networks and their symmetries. Several prior generative models are limited to generating partial neural network weights, particularly for larger models, such as ResNet and ViT. Those that do generate complete weights struggle with generation speed or require finetuning of the generated models. In this work, we present DeepWeightFlow, a Flow Matching model that operates directly in weight space to generate diverse and high-accuracy neural network weights for a variety of architectures, neural network sizes, and data modalities. The neural networks generated by DeepWeightFlow do not require fine-tuning to perform well and can scale to large networks. We apply Git Re-Basin and TransFusion for neural network canonicalization in the context of generative weight models to account for the impact of neural network permutation symmetries and to improve generation efficiency for larger model sizes. The generated networks excel at transfer learning, and ensembles of hundreds of neural networks can be generated in minutes, far exceeding the efficiency of diffusion-based methods. DeepWeightFlow models pave the way for more efficient and scalable generation of diverse sets of neural networks.

Related papers

• Geometric Flow Models over Neural Network Weights [0.0]
  A generative model of neural network weights would be useful for a diverse set of applications, such as deep learning, learned optimization, and transfer learning.<n>Existing work on weight-space generative models often ignores the symmetries of neural network weights, or only takes into account a subset of them.<n>We build on recent work on generative modeling with flow matching, and weight-space graph neural networks to design three different weight-space flows.
  arXiv  Detail & Related papers  (2025-03-27T19:29:44Z)
• Growing Neural Networks: Dynamic Evolution through Gradient Descent [0.0]
  We present two approaches for evolving small neural networks into larger ones during training.<n>The first method employs an auxiliary weight that directly controls network size, while the second uses a controller-generated mask to modulate neuron participation.<n>Both approaches optimize network size through the same gradient-descent algorithm that updates the network's weights and biases.
  arXiv  Detail & Related papers  (2025-01-29T21:56:38Z)
• Towards Scalable and Versatile Weight Space Learning [51.78426981947659]
  This paper introduces the SANE approach to weight-space learning. Our method extends the idea of hyper-representations towards sequential processing of subsets of neural network weights.
  arXiv  Detail & Related papers  (2024-06-14T13:12:07Z)
• Message Passing Variational Autoregressive Network for Solving Intractable Ising Models [6.261096199903392]
  Many deep neural networks have been used to solve Ising models, including autoregressive neural networks, convolutional neural networks, recurrent neural networks, and graph neural networks. Here we propose a variational autoregressive architecture with a message passing mechanism, which can effectively utilize the interactions between spin variables. The new network trained under an annealing framework outperforms existing methods in solving several prototypical Ising spin Hamiltonians, especially for larger spin systems at low temperatures.
  arXiv  Detail & Related papers  (2024-04-09T11:27:07Z)
• Graph Neural Networks for Learning Equivariant Representations of Neural Networks [55.04145324152541]
  We propose to represent neural networks as computational graphs of parameters. Our approach enables a single model to encode neural computational graphs with diverse architectures. We showcase the effectiveness of our method on a wide range of tasks, including classification and editing of implicit neural representations.
  arXiv  Detail & Related papers  (2024-03-18T18:01:01Z)
• Diffusion-Based Neural Network Weights Generation [80.89706112736353]
  D2NWG is a diffusion-based neural network weights generation technique that efficiently produces high-performing weights for transfer learning. Our method extends generative hyper-representation learning to recast the latent diffusion paradigm for neural network weights generation. Our approach is scalable to large architectures such as large language models (LLMs), overcoming the limitations of current parameter generation techniques.
  arXiv  Detail & Related papers  (2024-02-28T08:34:23Z)
• Variational Tensor Neural Networks for Deep Learning [0.0]
  We propose an integration of tensor networks (TN) into deep neural networks (NNs) This in turn, results in a scalable tensor neural network (TNN) architecture capable of efficient training over a large parameter space. We validate the accuracy and efficiency of our method by designing TNN models and providing benchmark results for linear and non-linear regressions, data classification and image recognition on MNIST handwritten digits.
  arXiv  Detail & Related papers  (2022-11-26T20:24:36Z)
• A Faster Approach to Spiking Deep Convolutional Neural Networks [0.0]
  Spiking neural networks (SNNs) have closer dynamics to the brain than current deep neural networks. We propose a network structure based on previous work to improve network runtime and accuracy.
  arXiv  Detail & Related papers  (2022-10-31T16:13:15Z)
• Spiking neural network for nonlinear regression [68.8204255655161]
  Spiking neural networks carry the potential for a massive reduction in memory and energy consumption. They introduce temporal and neuronal sparsity, which can be exploited by next-generation neuromorphic hardware. A framework for regression using spiking neural networks is proposed.
  arXiv  Detail & Related papers  (2022-10-06T13:04:45Z)
• A Fully Tensorized Recurrent Neural Network [48.50376453324581]
  We introduce a "fully tensorized" RNN architecture which jointly encodes the separate weight matrices within each recurrent cell. This approach reduces model size by several orders of magnitude, while still maintaining similar or better performance compared to standard RNNs.
  arXiv  Detail & Related papers  (2020-10-08T18:24:12Z)
• Model Fusion via Optimal Transport [64.13185244219353]
  We present a layer-wise model fusion algorithm for neural networks. We show that this can successfully yield "one-shot" knowledge transfer between neural networks trained on heterogeneous non-i.i.d. data.
  arXiv  Detail & Related papers  (2019-10-12T22:07:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.