Poster "expressive power" Papers

12 papers found

A Hierarchy of Graphical Models for Counterfactual Inferences

Hongshuo Yang, Elias Bareinboim

NEURIPS 2025

A Little Depth Goes a Long Way: The Expressive Power of Log-Depth Transformers

Will Merrill, Ashish Sabharwal

NEURIPS 2025arXiv:2503.03961
33
citations

The Computational Complexity of Counting Linear Regions in ReLU Neural Networks

Moritz Stargalla, Christoph Hertrich, Daniel Reichman

NEURIPS 2025arXiv:2505.16716
2
citations

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

Yam Eitan, Yoav Gelberg, Guy Bar-Shalom et al.

ICLR 2025arXiv:2408.05486
11
citations

Towards Explaining the Power of Constant-depth Graph Neural Networks for Structured Linear Programming

Qian Li, Minghui Ouyang, Tian Ding et al.

ICLR 2025
1
citations

Aligning Transformers with Weisfeiler-Leman

Luis Müller, Christopher Morris

ICML 2024arXiv:2406.03148
6
citations

Homomorphism Counts for Graph Neural Networks: All About That Basis

Emily Jin, Michael Bronstein, Ismail Ceylan et al.

ICML 2024arXiv:2402.08595
20
citations

On dimensionality of feature vectors in MPNNs

César Bravo, Alexander Kozachinskiy, Cristobal Rojas

ICML 2024arXiv:2402.03966
8
citations

On the Universality of Volume-Preserving and Coupling-Based Normalizing Flows

Felix Draxler, Stefan Wahl, Christoph Schnörr et al.

ICML 2024arXiv:2402.06578
17
citations

Position: Future Directions in the Theory of Graph Machine Learning

Christopher Morris, Fabrizio Frasca, Nadav Dym et al.

ICML 2024

The Expressive Power of Path-Based Graph Neural Networks

Caterina Graziani, Tamara Drucks, Fabian Jogl et al.

ICML 2024

Weisfeiler-Leman at the margin: When more expressivity matters

Billy Franks, Christopher Morris, Ameya Velingker et al.

ICML 2024arXiv:2402.07568
15
citations