A systematic approach maps any-dimensional invariant functions to a unique function on an infinite-dimensional limit space admitting a topology with compact sets where universality holds, with examples of non-universal architectures and fixes.
The graph neural network model.IEEE transactions on neural networks, 20(1):61–80
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 7roles
background 1polarities
support 1representative citing papers
k-WL is incomplete on simple spectrum graphs; PRiSM is the first provably complete canonicalization for their eigendecompositions.
Sinks are equivalent to hard attention switches that zero out outputs and are cheaper than diagonal patterns when self-communication is allowed, closing the gap between oversmoothing prevention needs and what sinks provide.
Concept Graph Convolutions perform message passing on node concepts to increase interpretability of graph neural networks without losing task performance.
RelSC is a new graph regression benchmark from program graphs with execution time labels, released in homogeneous (RelSC-H) and multi-relational (RelSC-M) variants to study representation effects.
PIEGraph augments a spring-mass particle model with an equivariant GNN and novel action representation to predict accurate object dynamics for robotic manipulation from few interactions.
Subgraph Concept Network is a new GNN architecture that distills meaningful concepts at node, subgraph, and graph levels via soft clustering to improve explainability while maintaining competitive accuracy.
citing papers explorer
-
Any-Dimensional Invariant Universality
A systematic approach maps any-dimensional invariant functions to a unique function on an infinite-dimensional limit space admitting a topology with compact sets where universality holds, with examples of non-universal architectures and fixes.
-
Weisfeiler-Leman Is Incomplete on Simple Spectrum Graphs, so Canonicalize Them
k-WL is incomplete on simple spectrum graphs; PRiSM is the first provably complete canonicalization for their eigendecompositions.
-
Sink vs. diagonal patterns as mechanisms for attention switch and oversmoothing prevention
Sinks are equivalent to hard attention switches that zero out outputs and are cheaper than diagonal patterns when self-communication is allowed, closing the gap between oversmoothing prevention needs and what sinks provide.
-
Concept Graph Convolutions: Message Passing in the Concept Space
Concept Graph Convolutions perform message passing on node concepts to increase interpretability of graph neural networks without losing task performance.
-
A Benchmark Dataset for Graph Regression with Homogeneous and Multi-Relational Variants
RelSC is a new graph regression benchmark from program graphs with execution time labels, released in homogeneous (RelSC-H) and multi-relational (RelSC-M) variants to study representation effects.
-
Learning Equivariant Neural-Augmented Object Dynamics From Few Interactions
PIEGraph augments a spring-mass particle model with an equivariant GNN and novel action representation to predict accurate object dynamics for robotic manipulation from few interactions.
-
Subgraph Concept Networks: Concept Levels in Graph Classification
Subgraph Concept Network is a new GNN architecture that distills meaningful concepts at node, subgraph, and graph levels via soft clustering to improve explainability while maintaining competitive accuracy.