GIN is provably as expressive as the Weisfeiler-Lehman graph isomorphism test, while GCN and GraphSAGE have strictly weaker discriminative power on some graphs.
Janossy pooling: Learning deep permutation-invariant functions for variable-size inputs.arXiv:1811.01900
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
abstract
We consider a simple and overarching representation for permutation-invariant functions of sequences (or multiset functions). Our approach, which we call Janossy pooling, expresses a permutation-invariant function as the average of a permutation-sensitive function applied to all reorderings of the input sequence. This allows us to leverage the rich and mature literature on permutation-sensitive functions to construct novel and flexible permutation-invariant functions. If carried out naively, Janossy pooling can be computationally prohibitive. To allow computational tractability, we consider three kinds of approximations: canonical orderings of sequences, functions with $k$-order interactions, and stochastic optimization algorithms with random permutations. Our framework unifies a variety of existing work in the literature, and suggests possible modeling and algorithmic extensions. We explore a few in our experiments, which demonstrate improved performance over current state-of-the-art methods.
fields
cs.LG 3representative citing papers
Graph Kernel Networks learn PDE solution operators that generalize across discretization methods and grid resolutions using graph-based kernel integration.
Geometric deep learning provides a unified mathematical framework based on grids, groups, graphs, geodesics, and gauges to explain and extend neural network architectures by incorporating physical regularities.
citing papers explorer
-
How Powerful are Graph Neural Networks?
GIN is provably as expressive as the Weisfeiler-Lehman graph isomorphism test, while GCN and GraphSAGE have strictly weaker discriminative power on some graphs.
-
Neural Operator: Graph Kernel Network for Partial Differential Equations
Graph Kernel Networks learn PDE solution operators that generalize across discretization methods and grid resolutions using graph-based kernel integration.
-
Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
Geometric deep learning provides a unified mathematical framework based on grids, groups, graphs, geodesics, and gauges to explain and extend neural network architectures by incorporating physical regularities.