Deep Graphs

TL;DR

Deep Graphs introduce an adaptive, efficient deep learning algorithm for graphs that learns recurrent update functions, achieving high accuracy in labeling and regression tasks.

Contribution

The paper presents a novel deep learning framework for graphs that learns update functions directly, unlike previous methods relying on fixed algorithms.

Findings

Achieves high accuracy on graph labeling tasks

Efficient training and deployment with O(|E| + |V|) complexity

Demonstrates effectiveness on regression tasks

Abstract

We propose an algorithm for deep learning on networks and graphs. It relies on the notion that many graph algorithms, such as PageRank, Weisfeiler-Lehman, or Message Passing can be expressed as iterative vertex updates. Unlike previous methods which rely on the ingenuity of the designer, Deep Graphs are adaptive to the estimation problem. Training and deployment are both efficient, since the cost is $O(|E| + |V|)$, where $E$ and $V$ are the sets of edges and vertices respectively. In short, we learn the recurrent update functions rather than positing their specific functional form. This yields an algorithm that achieves excellent accuracy on both graph labeling and regression tasks.