REVIEW 5 cited by
Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
abstract
In recent years, graph neural networks (GNNs) have emerged as a powerful neural architecture to learn vector representations of nodes and graphs in a supervised, end-to-end fashion. Up to now, GNNs have only been evaluated empirically -- showing promising results. The following work investigates GNNs from a theoretical point of view and relates them to the $1$-dimensional Weisfeiler-Leman graph isomorphism heuristic ($1$-WL). We show that GNNs have the same expressiveness as the $1$-WL in terms of distinguishing non-isomorphic (sub-)graphs. Hence, both algorithms also have the same shortcomings. Based on this, we propose a generalization of GNNs, so-called $k$-dimensional GNNs ($k$-GNNs), which can take higher-order graph structures at multiple scales into account. These higher-order structures play an essential role in the characterization of social networks and molecule graphs. Our experimental evaluation confirms our theoretical findings as well as confirms that higher-order information is useful in the task of graph classification and regression.
Forward citations
Cited by 5 Pith papers
-
The Power of the Weisfeiler-Leman Algorithm to Decompose Graphs
The 2-dimensional Weisfeiler-Leman algorithm detects 2-separators and implicitly computes 3-connected decompositions, yielding a WL dimension upper bound of k for treewidth-k graphs and a factor-2-tight lower bound.
-
Structured Spectral Graph Learning for Anomaly Classification in 3D Chest CT Scans
A graph neural network with spectral convolution over axial slice triplet nodes improves multi-label chest CT anomaly classification on two public datasets.
-
Structured Spectral Graph Representation Learning for Multi-label Abnormality Analysis from 3D CT Scans
A graph-of-slice-triplets encoder with spectral convolution outperforms 3D CNN/Transformer baselines on multi-label chest CT abnormality classification and transfers to report generation and abdominal CT.
-
An AI Approach for Learning the Spectrum of the Laplace-Beltrami Operator
A graph neural network predicts eigenvalues 2-50 of the Laplace-Beltrami operator on mechanical CAD meshes about 5 times faster than FEM and is claimed accurate on 99.3% of held-out parts.
-
Spatio-Temporal Forecasting of PM2.5 via Spatial-Diffusion guided Encoder-Decoder Architecture
AGNN_GRU, a spatio-temporal encoder-decoder with diffusion-aware graph convolution, provides small forecast improvements over ablated baselines on PM2.5 data from India and China.
Discussion (0). Continue with ORCID to comment.