CrossGMN: Graph Metanetworks for Cross-Architecture Weight-Space Transformations

Excerpt

arXiv:2610.01649v1 Announce Type: new Abstract: Weight-space networks operate directly on parameters of other neural networks, enabling tasks such as predicting model properties, editing trained models, and generating weights. Weight-space symmetries such as neuron permutations make equivariance a key design principle. However, existing equivariant weight-space architectures have primarily been studied for transformations that preserve the network architecture. In contrast, many practical transf