DeepAI AI Chat
Log In Sign Up

Graph Neural Networks with Precomputed Node Features

by   Beni Egressy, et al.

Most Graph Neural Networks (GNNs) cannot distinguish some graphs or indeed some pairs of nodes within a graph. This makes it impossible to solve certain classification tasks. However, adding additional node features to these models can resolve this problem. We introduce several such augmentations, including (i) positional node embeddings, (ii) canonical node IDs, and (iii) random features. These extensions are motivated by theoretical results and corroborated by extensive testing on synthetic subgraph detection tasks. We find that positional embeddings significantly outperform other extensions in these tasks. Moreover, positional embeddings have better sample efficiency, perform well on different graph distributions and even outperform learning with ground truth node positions. Finally, we show that the different augmentations perform competitively on established GNN benchmarks, and advise on when to use them.


page 7

page 12

page 13


Position-aware Graph Neural Networks

Learning node embeddings that capture a node's position within the broad...

Agent-based Graph Neural Networks

We present a novel graph neural network we call AgentNet, which is desig...

Distributional Signals for Node Classification in Graph Neural Networks

In graph neural networks (GNNs), both node features and labels are examp...

On the Equivalence between Node Embeddings and Structural Graph Representations

This work provides the first unifying theoretical framework for node emb...

Graph-Conditioned MLP for High-Dimensional Tabular Biomedical Data

Genome-wide studies leveraging recent high-throughput sequencing technol...

A Non-Asymptotic Analysis of Oversmoothing in Graph Neural Networks

A central challenge of building more powerful Graph Neural Networks (GNN...

Pretraining Graph Neural Networks for few-shot Analog Circuit Modeling and Design

Being able to predict the performance of circuits without running expens...