Network of Theseus (like the ship)

• URL: http://arxiv.org/abs/2512.04198v1
• Date: Wed, 03 Dec 2025 19:15:18 GMT
• Title: Network of Theseus (like the ship)
• Authors: Vighnesh Subramaniam, Colin Conwell, Boris Katz, Andrei Barbu, Brian Cheung,
• Abstract summary: Network of Theseus (NoT) is a method for converting a trained, or even untrained, guide network architecture part-by-part into an entirely different target network architecture.<n>At each stage, components in the guide network architecture are incrementally replaced with target architecture modules and aligned via representational similarity metrics.<n>NoT expands the space of viable inference-time architectures, opening opportunities for better accuracy-efficiency tradeoffs and enabling more directed exploration of the architectural design space.
• Score: 17.044332179158392
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: A standard assumption in deep learning is that the inductive bias introduced by a neural network architecture must persist from training through inference. The architecture you train with is the architecture you deploy. This assumption constrains the community from selecting architectures that may have desirable efficiency or design properties due to difficulties with optimization. We challenge this assumption with Network of Theseus (NoT), a method for progressively converting a trained, or even untrained, guide network architecture part-by-part into an entirely different target network architecture while preserving the performance of the guide network. At each stage, components in the guide network architecture are incrementally replaced with target architecture modules and aligned via representational similarity metrics. This procedure largely preserves the functionality of the guide network even under substantial architectural changes-for example, converting a convolutional network into a multilayer perceptron, or GPT-2 into a recurrent neural network. By decoupling optimization from deployment, NoT expands the space of viable inference-time architectures, opening opportunities for better accuracy-efficiency tradeoffs and enabling more directed exploration of the architectural design space.

Related papers

• Training the Untrainable: Introducing Inductive Bias via Representational Alignment [17.222963037741327]
  We show that architectures which traditionally are considered to be ill-suited for a task can be trained using inductive biases from another architecture.<n>We show that guidance prevents FCN overfitting on ImageNet, narrows the vanilla RNN-Transformer gap, boosts plain CNNs toward ResNet accuracy, and aids Transformers on RNN-favored tasks.
  arXiv  Detail & Related papers  (2024-10-26T01:04:03Z)
• EM-DARTS: Hierarchical Differentiable Architecture Search for Eye Movement Recognition [20.209756662832365]
  Differentiable Neural Architecture Search (DARTS) automates the manual process of architecture design with high search efficiency.<n>We propose EM-DARTS, a hierarchical differentiable architecture search algorithm to automatically design the DL architecture for eye movement recognition.<n>We show that EM-DARTS is capable of producing an optimal architecture that leads to state-of-the-art recognition performance.
  arXiv  Detail & Related papers  (2024-09-22T13:11:08Z)
• Principled Architecture-aware Scaling of Hyperparameters [69.98414153320894]
  Training a high-quality deep neural network requires choosing suitable hyperparameters, which is a non-trivial and expensive process. In this work, we precisely characterize the dependence of initializations and maximal learning rates on the network architecture. We demonstrate that network rankings can be easily changed by better training networks in benchmarks.
  arXiv  Detail & Related papers  (2024-02-27T11:52:49Z)
• FlowNAS: Neural Architecture Search for Optical Flow Estimation [65.44079917247369]
  We propose a neural architecture search method named FlowNAS to automatically find the better encoder architecture for flow estimation task. Experimental results show that the discovered architecture with the weights inherited from the super-network achieves 4.67% F1-all error on KITTI.
  arXiv  Detail & Related papers  (2022-07-04T09:05:25Z)
• Hysteretic Behavior Simulation Based on Pyramid Neural Network:Principle, Network Architecture, Case Study and Explanation [0.0]
  A surrogate model based on neural networks shows significant potential in balancing efficiency and accuracy. Its serial information flow and prediction based on single-level features adversely affect the network performance. A weighted stacked pyramid neural network architecture is proposed herein.
  arXiv  Detail & Related papers  (2022-04-29T16:42:00Z)
• SIRe-Networks: Skip Connections over Interlaced Multi-Task Learning and Residual Connections for Structure Preserving Object Classification [28.02302915971059]
  In this paper, we introduce an interlaced multi-task learning strategy, defined SIRe, to reduce the vanishing gradient in relation to the object classification task. The presented methodology directly improves a convolutional neural network (CNN) by enforcing the input image structure preservation through auto-encoders. To validate the presented methodology, a simple CNN and various implementations of famous networks are extended via the SIRe strategy and extensively tested on the CIFAR100 dataset.
  arXiv  Detail & Related papers  (2021-10-06T13:54:49Z)
• Analyze and Design Network Architectures by Recursion Formulas [4.085771561472743]
  This work attempts to find an effective way to design new network architectures. It is discovered that the main difference between network architectures can be reflected in their formulas. A case study is provided to generate an improved architecture based on ResNet. Massive experiments are conducted on CIFAR and ImageNet, which witness the significant performance improvements.
  arXiv  Detail & Related papers  (2021-08-18T06:53:30Z)
• Firefly Neural Architecture Descent: a General Approach for Growing Neural Networks [50.684661759340145]
  Firefly neural architecture descent is a general framework for progressively and dynamically growing neural networks. We show that firefly descent can flexibly grow networks both wider and deeper, and can be applied to learn accurate but resource-efficient neural architectures. In particular, it learns networks that are smaller in size but have higher average accuracy than those learned by the state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-02-17T04:47:18Z)
• Adversarially Robust Neural Architectures [43.74185132684662]
  This paper aims to improve the adversarial robustness of the network from the architecture perspective with NAS framework. We explore the relationship among adversarial robustness, Lipschitz constant, and architecture parameters. Our algorithm empirically achieves the best performance among all the models under various attacks on different datasets.
  arXiv  Detail & Related papers  (2020-09-02T08:52:15Z)
• Structured Convolutions for Efficient Neural Network Design [65.36569572213027]
  We tackle model efficiency by exploiting redundancy in the textitimplicit structure of the building blocks of convolutional neural networks. We show how this decomposition can be applied to 2D and 3D kernels as well as the fully-connected layers.
  arXiv  Detail & Related papers  (2020-08-06T04:38:38Z)
• Neural Architecture Optimization with Graph VAE [21.126140965779534]
  We propose an efficient NAS approach to optimize network architectures in a continuous space. The framework jointly learns four components: the encoder, the performance predictor, the complexity predictor and the decoder.
  arXiv  Detail & Related papers  (2020-06-18T07:05:48Z)
• A Semi-Supervised Assessor of Neural Architectures [157.76189339451565]
  We employ an auto-encoder to discover meaningful representations of neural architectures. A graph convolutional neural network is introduced to predict the performance of architectures.
  arXiv  Detail & Related papers  (2020-05-14T09:02:33Z)
• Stage-Wise Neural Architecture Search [65.03109178056937]
  Modern convolutional networks such as ResNet and NASNet have achieved state-of-the-art results in many computer vision applications. These networks consist of stages, which are sets of layers that operate on representations in the same resolution. It has been demonstrated that increasing the number of layers in each stage improves the prediction ability of the network. However, the resulting architecture becomes computationally expensive in terms of floating point operations, memory requirements and inference time.
  arXiv  Detail & Related papers  (2020-04-23T14:16:39Z)

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.