arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.01083cs.LG
收藏

关于置换等变权重空间网络的表达能力

On the Expressive Power of Permutation-Equivariant Weight-Space Networks

Technion -- Israel Institute of Technology(技术ion-以色列理工学院);NVIDIA Research(NVIDIA研究)

Adir Dayan, Yam Eitan, Haggai Maron

AI总结:

本文系统研究置换等变权重空间网络的表达能力,证明主流网络表达能力等价,并在温和假设下建立权重空间和函数空间的普适性,指导模型改进实现34%性能提升。

摘要:

权重空间学习研究直接对其他神经网络的参数进行操作的神经架构。受预训练模型日益普及的推动,最近的工作展示了权重空间网络在广泛任务中的有效性。SOTA权重空间网络依赖置换等变设计来提高泛化能力。然而,这可能会对表达能力产生负面影响,需要进行理论研究。重要的是,与其他结构化领域不同,权重空间学习的目标是对权重空间和函数空间都进行操作的映射,这使得表达能力分析尤为微妙。虽然一些先前的工作提供了部分表达能力结果,但全面的刻画仍然缺失。在这项工作中,我们通过为权重空间网络的表达能力开发系统理论来填补这一空白。我们首先证明所有主流的置换等变网络在表达能力上是等价的。然后,我们在输入权重的温和自然假设下,建立了权重空间和函数空间设置中的普适性,并刻画了普适性不再成立的边缘情况。在我们的理论结果指导下,我们表明对现有权重空间模型的轻微修改相比先前SOTA实现了34%的提升,展示了我们框架的实际相关性。

英文摘要:

Weight-space learning studies neural architectures that operate directly on the parameters of other neural networks. Motivated by the growing availability of pretrained models, recent work has demonstrated the effectiveness of weight-space networks across a wide range of tasks. SOTA weight-space networks rely on permutation-equivariant designs to improve generalization. However, this may negatively affect expressive power, warranting theoretical investigation. Importantly, unlike other structured domains, weight-space learning targets maps operating on both weight and function spaces, making expressivity analysis particularly subtle. While a few prior works provide partial expressivity results, a comprehensive characterization is still missing. In this work, we address this gap by developing a systematic theory for expressivity of weight-space networks. We first prove that all prominent permutation-equivariant networks are equivalent in expressive power. We then establish universality in both weight- and function-space settings under mild, natural assumptions on the input weights, and characterize the edge-case regimes where universality no longer holds. Guided by our theoretical results, we show that slight modifications to existing weight-space models yield a 34% improvement over prior SOTA, demonstrating the practical relevance of our framework.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑