Equivariant Polynomials for Graph Neural Networks

• URL: http://arxiv.org/abs/2302.11556v2
• Date: Sun, 4 Jun 2023 08:14:37 GMT
• Title: Equivariant Polynomials for Graph Neural Networks
• Authors: Omri Puny, Derek Lim, Bobak T. Kiani, Haggai Maron, Yaron Lipman
• Abstract summary: Graph Networks (GNN) are inherently limited in their expressive power. This paper introduces an alternative power hierarchy based on the ability of GNNs to calculate equivariants of certain degree. These enhanced GNNs demonstrate state-of-the-art results in experiments across multiple graph learning benchmarks.
• Score: 38.15983687193912
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Graph Neural Networks (GNN) are inherently limited in their expressive power. Recent seminal works (Xu et al., 2019; Morris et al., 2019b) introduced the Weisfeiler-Lehman (WL) hierarchy as a measure of expressive power. Although this hierarchy has propelled significant advances in GNN analysis and architecture developments, it suffers from several significant limitations. These include a complex definition that lacks direct guidance for model improvement and a WL hierarchy that is too coarse to study current GNNs. This paper introduces an alternative expressive power hierarchy based on the ability of GNNs to calculate equivariant polynomials of a certain degree. As a first step, we provide a full characterization of all equivariant graph polynomials by introducing a concrete basis, significantly generalizing previous results. Each basis element corresponds to a specific multi-graph, and its computation over some graph data input corresponds to a tensor contraction problem. Second, we propose algorithmic tools for evaluating the expressiveness of GNNs using tensor contraction sequences, and calculate the expressive power of popular GNNs. Finally, we enhance the expressivity of common GNN architectures by adding polynomial features or additional operations / aggregations inspired by our theory. These enhanced GNNs demonstrate state-of-the-art results in experiments across multiple graph learning benchmarks.

Related papers

• A Manifold Perspective on the Statistical Generalization of Graph Neural Networks [84.01980526069075]
  We take a manifold perspective to establish the statistical generalization theory of GNNs on graphs sampled from a manifold in the spectral domain. We prove that the generalization bounds of GNNs decrease linearly with the size of the graphs in the logarithmic scale, and increase linearly with the spectral continuity constants of the filter functions.
  arXiv  Detail & Related papers  (2024-06-07T19:25:02Z)
• Uplifting the Expressive Power of Graph Neural Networks through Graph Partitioning [3.236774847052122]
  We study the expressive power of graph neural networks through the lens of graph partitioning. We introduce a novel GNN architecture, namely Graph Partitioning Neural Networks (GPNNs)
  arXiv  Detail & Related papers  (2023-12-14T06:08:35Z)
• A Complete Expressiveness Hierarchy for Subgraph GNNs via Subgraph Weisfeiler-Lehman Tests [30.558563815430418]
  Subgraph neural networks (GNNs) have emerged as an important direction for developing expressive graph neural networks (GNNs) This paper conducts a systematic study of general node-based subgraph GNNs through the lens of Subgraph Weisfeiler-Lehman Tests (SWL) We prove that any node-based subgraph GNN falls into one of the six SWL equivalence classes, among which $mathsfSSWL$ achieves the maximal expressive power.
  arXiv  Detail & Related papers  (2023-02-14T14:42:54Z)
• Towards Better Generalization with Flexible Representation of Multi-Module Graph Neural Networks [0.27195102129094995]
  We use a random graph generator to investigate how the graph size and structural properties affect the predictive performance of GNNs. We present specific evidence that the average node degree is a key feature in determining whether GNNs can generalize to unseen graphs. We propose a multi- module GNN framework that allows the network to adapt flexibly to new graphs by generalizing a single canonical nonlinear transformation over aggregated inputs.
  arXiv  Detail & Related papers  (2022-09-14T12:13:59Z)
• Representation Power of Graph Neural Networks: Improved Expressivity via Algebraic Analysis [124.97061497512804]
  We show that standard Graph Neural Networks (GNNs) produce more discriminative representations than the Weisfeiler-Lehman (WL) algorithm. We also show that simple convolutional architectures with white inputs, produce equivariant features that count the closed paths in the graph.
  arXiv  Detail & Related papers  (2022-05-19T18:40:25Z)
• Expressiveness and Approximation Properties of Graph Neural Networks [6.1323142294300625]
  We provide an elegant way to obtain bounds on the separation power of GNNs in terms of the Weisfeiler-Leman (WL) tests. We use tensor language to define Higher-Order Message-Passing Neural Networks (or k-MPNNs), a natural extension of MPNNs. Our approach provides a toolbox with which GNN architecture designers can analyze the separation power of their GNNs.
  arXiv  Detail & Related papers  (2022-04-10T11:33:04Z)
• The Surprising Power of Graph Neural Networks with Random Node Initialization [54.4101931234922]
  Graph neural networks (GNNs) are effective models for representation learning on relational data. Standard GNNs are limited in their expressive power, as they cannot distinguish beyond the capability of the Weisfeiler-Leman graph isomorphism. In this work, we analyze the expressive power of GNNs with random node (RNI) We prove that these models are universal, a first such result for GNNs not relying on computationally demanding higher-order properties.
  arXiv  Detail & Related papers  (2020-10-02T19:53:05Z)
• Distance Encoding: Design Provably More Powerful Neural Networks for Graph Representation Learning [63.97983530843762]
  Graph Neural Networks (GNNs) have achieved great success in graph representation learning. GNNs generate identical representations for graph substructures that may in fact be very different. More powerful GNNs, proposed recently by mimicking higher-order tests, are inefficient as they cannot sparsity of underlying graph structure. We propose Distance Depiction (DE) as a new class of graph representation learning.
  arXiv  Detail & Related papers  (2020-08-31T23:15:40Z)
• Expressive Power of Invariant and Equivariant Graph Neural Networks [10.419350129060598]
  We show that Folklore Graph Neural Networks (FGNN) are the most expressive architectures proposed so far for a given tensor order. FGNNs are able to learn how to solve the problem, leading to much better average performances than existing algorithms.
  arXiv  Detail & Related papers  (2020-06-28T16:35:45Z)
• Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting [63.04999833264299]
  "Graph Substructure Networks" (GSN) is a topologically-aware message passing scheme based on substructure encoding. We show that it is strictly more expressive than the Weisfeiler-Leman (WL) graph isomorphism test. We perform an extensive evaluation on graph classification and regression tasks and obtain state-of-the-art results in diverse real-world settings.
  arXiv  Detail & Related papers  (2020-06-16T15:30:31Z)
• Eigen-GNN: A Graph Structure Preserving Plug-in for GNNs [95.63153473559865]
  Graph Neural Networks (GNNs) are emerging machine learning models on graphs. Most existing GNN models in practice are shallow and essentially feature-centric. We show empirically and analytically that the existing shallow GNNs cannot preserve graph structures well. We propose Eigen-GNN, a plug-in module to boost GNNs ability in preserving graph structures.
  arXiv  Detail & Related papers  (2020-06-08T02:47:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.