conftrace_

expressive power

51 papers

Explore in graph

Co-occurring keywords

graph neural network (3962) message passing (579) weisfeiler-lehman test (32) generative model (2892) graph isomorphism (47) relu network (143) modal logic (55) state space model (390) probabilistic graphical model (226) recurrent neural network (1790)

Papers

Aggregate-Combine-Readout GNNs Can Express Logical Classifiers Beyond the Logic C2 AAAI 2026
Expressive Power of Graph Transformers via Logic AAAI 2026
Logical Characterizations of GNNs with Mean Aggregation AAAI 2026
Circuit Complexity Bounds for RoPE-based Transformer Architecture EMNLP 2025
Expressive Power of Temporal Message Passing AAAI 2025
Orthogonal Bases for Equivariant Graph Learning with Provable k-WL Expressive Power JMLR 2025
The Expressive Capacity of State Space Models: A Formal Language Perspective NIPS 2024
Towards a Theory of Machine Learning on Graphs and its Applications in Combinatorial Optimization IJCAI 2024
Deep Homomorphism Networks NIPS 2024
On the Theoretical Expressive Power and the Design Space of Higher-Order Graph Transformers AISTATS 2024
Understanding the Expressive Power and Mechanisms of Transformer for Sequence Modeling NIPS 2024
Improving Expressive Power of Spectral Graph Neural Networks with Eigenvalue Correction AAAI 2024
Towards Principled Graph Transformers NIPS 2024
On the Expressive Power of Tree-Structured Probabilistic Circuits NIPS 2024
Deep Network Approximation: Beyond ReLU to Diverse Activation Functions JMLR 2024
Theoretical Foundations of Deep Selective State-Space Models NIPS 2024
Logical characterizations of recurrent graph neural networks with reals and floats NIPS 2024
Almost Surely Asymptotically Constant Graph Neural Networks NIPS 2024
What functions can Graph Neural Networks compute on random graphs? The role of Positional Encoding NIPS 2023
Equivariant Polynomials for Graph Neural Networks ICML 2023
Path Neural Networks: Expressive and Accurate Graph Neural Networks ICML 2023
On Enhancing Expressive Power via Compositions of Single Fixed-Size ReLU Network ICML 2023
The Power of Recursion in Graph Neural Networks for Counting Substructures AISTATS 2023
The Expressive Power of Ad-Hoc Constraints for Modelling CSPs AAAI 2023
A Complete Expressiveness Hierarchy for Subgraph GNNs via Subgraph Weisfeiler-Lehman Tests ICML 2023