Neural Trees for Learning on Graphs

by   Rajat Talak, et al.

Graph Neural Networks (GNNs) have emerged as a flexible and powerful approach for learning over graphs. Despite this success, existing GNNs are constrained by their local message-passing architecture and are provably limited in their expressive power. In this work, we propose a new GNN architecture – the Neural Tree. The neural tree architecture does not perform message passing on the input graph but on a tree-structured graph, called the H-tree, that is constructed from the input graph. Nodes in the H-tree correspond to subgraphs in the input graph, and they are reorganized in a hierarchical manner such that a parent-node of a node in the H-tree always corresponds to a larger subgraph in the input graph. We show that the neural tree architecture can approximate any smooth probability distribution function over an undirected graph, as well as emulate the junction tree algorithm. We also prove that the number of parameters needed to achieve an ϵ-approximation of the distribution function is exponential in the treewidth of the input graph, but linear in its size. We apply the neural tree to semi-supervised node classification in 3D scene graphs, and show that these theoretical properties translate into significant gains in prediction accuracy, over the more traditional GNN architectures.


Ego-GNNs: Exploiting Ego Structures in Graph Neural Networks

Graph neural networks (GNNs) have achieved remarkable success as a frame...

Understanding and Extending Subgraph GNNs by Rethinking Their Symmetries

Subgraph GNNs are a recent class of expressive Graph Neural Networks (GN...

GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddings

We present GNNAutoScale (GAS), a framework for scaling arbitrary message...

A Simple yet Effective Method for Graph Classification

In deep neural networks, better results can often be obtained by increas...

Graph Tree Neural Networks

Graph neural networks (GNNs) have recently shown good performance in var...

Graph Neural Networks are Inherently Good Generalizers: Insights by Bridging GNNs and MLPs

Graph neural networks (GNNs), as the de-facto model class for representa...

GRAFENNE: Learning on Graphs with Heterogeneous and Dynamic Feature Sets

Graph neural networks (GNNs), in general, are built on the assumption of...

Please sign up or login with your details

Forgot password? Click here to reset