paper-with-me

홈 › Papers

On The Topological Expressive Power of Neural Networks

2020-10-10 · NeurIPS Workshop TDA_and_Beyond 2020 12 · Giovanni Petri, António Leitão

We propose a topological description of neural network expressive power. We adopt the topology of the space of decision boundaries realized by a neural architecture as a measure of its intrinsic expressive power. By sampling a large number of neural architectures with different sizes and design, we show how such measure of expressive power depends on the properties of the architectures, like depth, width and other related quantities.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

The Logical Expressiveness of Topological Neural Networks

2026-04-21 · Amirreza Akbari, Amauri H. Souza, Vikas Garg arxiv

Graph neural networks (GNNs) are the standard for learning on graphs, yet they have limited expressive power, often expressed in terms of the Weisfeiler-Leman (WL) hierarchy or within the framework of first-order logic. …

Graph Representation Learning

Topological Blindspots: Understanding and Extending Topological Deep Learning Through the Lens of Expressivity

2024-08-10 · Yam Eitan, Yoav Gelberg, Guy Bar-Shalom, Fabrizio Frasca 외

Topological deep learning (TDL) is a rapidly growing field that seeks to leverage topological structure in data and facilitate learning from data supported on topological objects, ranging from molecules to 3D shapes. Mos…

Weisfeiler Lehman Test on Combinatorial Complexes: Generalized Expressive Power of Topological Neural Networks

2026-05-01 · Jiawen Chen, Qi Shao, Zhiqiang Ge, Duxin Chen 외 arxiv

Topological neural networks have emerged as effective tools for modeling higher-order relational structures beyond pairwise graphs, including hypergraphs, simplicial complexes, and cell complexes. However, existing Weisf…

Heat Kernel Goes Topological

2025-07-16 · Maximilian Krahn, Vikas Garg

Topological neural networks have emerged as powerful successors of graph neural networks. However, they typically involve higher-order message passing, which incurs significant computational expense. We circumvent this i…

Computational EfficiencyProperty Prediction

Nominal Topology for Data Languages

2023-04-26 · Fabian Birkmann, Stefan Milius, Henning Urbat

We propose a novel topological perspective on data languages recognizable by orbit-finite nominal monoids. For this purpose, we introduce pro-orbit-finite nominal topological spaces. Assuming globally bounded support siz…