Random Weight Factorization Improves the Training of Continuous Neural Representations

• URL: http://arxiv.org/abs/2210.01274v2
• Date: Wed, 5 Oct 2022 13:12:28 GMT
• Title: Random Weight Factorization Improves the Training of Continuous Neural Representations
• Authors: Sifan Wang, Hanwen Wang, Jacob H. Seidman, Paris Perdikaris
• Abstract summary: Continuous neural representations have emerged as a powerful and flexible alternative to classical discretized representations of signals. We propose random weight factorization as a simple drop-in replacement for parameterizing and initializing conventional linear layers. We show how this factorization alters the underlying loss landscape and effectively enables each neuron in the network to learn using its own self-adaptive learning rate.
• Score: 1.911678487931003
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Continuous neural representations have recently emerged as a powerful and flexible alternative to classical discretized representations of signals. However, training them to capture fine details in multi-scale signals is difficult and computationally expensive. Here we propose random weight factorization as a simple drop-in replacement for parameterizing and initializing conventional linear layers in coordinate-based multi-layer perceptrons (MLPs) that significantly accelerates and improves their training. We show how this factorization alters the underlying loss landscape and effectively enables each neuron in the network to learn using its own self-adaptive learning rate. This not only helps with mitigating spectral bias, but also allows networks to quickly recover from poor initializations and reach better local minima. We demonstrate how random weight factorization can be leveraged to improve the training of neural representations on a variety of tasks, including image regression, shape representation, computed tomography, inverse rendering, solving partial differential equations, and learning operators between function spaces.

Related papers

• 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)
• NeuralFastLAS: Fast Logic-Based Learning from Raw Data [54.938128496934695]
  Symbolic rule learners generate interpretable solutions, however they require the input to be encoded symbolically. Neuro-symbolic approaches overcome this issue by mapping raw data to latent symbolic concepts using a neural network. We introduce NeuralFastLAS, a scalable and fast end-to-end approach that trains a neural network jointly with a symbolic learner.
  arXiv  Detail & Related papers  (2023-10-08T12:33:42Z)
• Generalizable Neural Fields as Partially Observed Neural Processes [16.202109517569145]
  We propose a new paradigm that views the large-scale training of neural representations as a part of a partially-observed neural process framework. We demonstrate that this approach outperforms both state-of-the-art gradient-based meta-learning approaches and hypernetwork approaches.
  arXiv  Detail & Related papers  (2023-09-13T01:22:16Z)
• Permutation Equivariant Neural Functionals [92.0667671999604]
  This work studies the design of neural networks that can process the weights or gradients of other neural networks. We focus on the permutation symmetries that arise in the weights of deep feedforward networks because hidden layer neurons have no inherent order. In our experiments, we find that permutation equivariant neural functionals are effective on a diverse set of tasks.
  arXiv  Detail & Related papers  (2023-02-27T18:52:38Z)
• Data-driven emergence of convolutional structure in neural networks [83.4920717252233]
  We show how fully-connected neural networks solving a discrimination task can learn a convolutional structure directly from their inputs. By carefully designing data models, we show that the emergence of this pattern is triggered by the non-Gaussian, higher-order local structure of the inputs.
  arXiv  Detail & Related papers  (2022-02-01T17:11:13Z)
• Hierarchical Learning to Solve Partial Differential Equations Using Physics-Informed Neural Networks [2.0305676256390934]
  We propose a hierarchical approach to improve the convergence rate and accuracy of the neural network solution to partial differential equations. We validate the efficiency and robustness of the proposed hierarchical approach through a suite of linear and nonlinear partial differential equations.
  arXiv  Detail & Related papers  (2021-12-02T13:53:42Z)
• Meta-Learning Sparse Implicit Neural Representations [69.15490627853629]
  Implicit neural representations are a promising new avenue of representing general signals. Current approach is difficult to scale for a large number of signals or a data set. We show that meta-learned sparse neural representations achieve a much smaller loss than dense meta-learned models.
  arXiv  Detail & Related papers  (2021-10-27T18:02:53Z)
• Dynamic Neural Diversification: Path to Computationally Sustainable Neural Networks [68.8204255655161]
  Small neural networks with a constrained number of trainable parameters, can be suitable resource-efficient candidates for many simple tasks. We explore the diversity of the neurons within the hidden layer during the learning process. We analyze how the diversity of the neurons affects predictions of the model.
  arXiv  Detail & Related papers  (2021-09-20T15:12:16Z)
• Self-Organized Operational Neural Networks for Severe Image Restoration Problems [25.838282412957675]
  Discnative learning based on convolutional neural networks (CNNs) aims to perform image restoration by learning from training examples of noisy-clean image pairs. We claim that this is due to the inherent linear nature of convolution-based transformation, which is inadequate for handling severe restoration problems. We propose a self-organizing variant of ONNs, Self-ONNs, for image restoration, which synthesizes novel nodal transformations onthe-fly.
  arXiv  Detail & Related papers  (2020-08-29T02:19:41Z)

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.