Deep Graph Learning will stall without Network Science

TL;DR

This paper argues that deep graph learning needs to incorporate network science insights to overcome current limitations and continue advancing effectively.

Contribution

It presents six Calls for Action to integrate network science principles into deep graph learning research.

Findings

Deep graph learning currently lacks fundamental network science insights.

Integrating network science can address key challenges in deep graph learning.

The paper proposes actionable steps to foster this integration.

Abstract

Deep graph learning focuses on flexible and generalizable models that learn patterns in an automated fashion. Network science focuses on models and measures revealing the organizational principles of complex systems with explicit assumptions. Both fields share the same goal: to better model and understand patterns in graph-structured data. However, deep graph learning prioritizes empirical performance but ignores fundamental insights from network science. Our position is that deep graph learning will stall without insights from network science. In this position paper, we formulate six Calls for Action to leverage untapped insights from network science to address current issues in deep graph learning, ensuring the field continues to make progress.