Neural networks that process the parameters of other neural networks find applications in domains as diverse as classifying implicit neural representations, generating neural network weights, and predicting generalization errors. However, existing approaches either overlook the inherent permutation symmetry in the neural network or rely on intricate weight-sharing patterns to achieve equivariance, while ignoring the impact of the network architecture itself. In this work, we propose to represent neural networks as computational graphs of parameters, which allows us to harness powerful graph neural networks and transformers that preserve permutation symmetry. Consequently, 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, predicting generalization performance, and learning to optimize, while consistently outperforming state-of-the-art methods. The source code is open-sourced at https://github.com/mkofinas/neural-graphs.

翻译：处理其他神经网络参数的神经网络在隐式神经表示分类、神经网络权重生成及泛化误差预测等多个领域均有应用。然而，现有方法要么忽视神经网络中固有的置换对称性，要么依赖复杂的权重共享模式来实现等变性，却忽视了网络架构本身的影响。本文提出将神经网络表示为参数的运算图，从而能够利用强大的图神经网络和保持置换对称性的Transformer。由此，我们的方法使单一模型能够编码具有多样架构的神经运算图。我们在包括隐式神经表示分类与编辑、泛化性能预测以及学习优化等广泛任务中展示了该方法的效果，并始终优于现有最佳方法。源代码已在 https://github.com/mkofinas/neural-graphs 开源。