Learning Network Dismantling Without Handcrafted Inputs

TL;DR

This paper introduces MIND, a message-passing neural network that dismantles networks without handcrafted features, using attention and synthetic training data, achieving superior results on real-world networks.

Contribution

It presents a novel feature-free framework for network dismantling that generalizes well to large, real networks, reducing reliance on handcrafted inputs.

Findings

Outperforms state-of-the-art methods on real networks

Generalizes from synthetic to large real-world networks

Eliminates need for handcrafted structural features

Abstract

The application of message-passing Graph Neural Networks has been a breakthrough for important network science problems. However, the competitive performance often relies on using handcrafted structural features as inputs, which increases computational cost and introduces bias into the otherwise purely data-driven network representations. Here, we eliminate the need for handcrafted features by introducing an attention mechanism and utilizing message-iteration profiles, in addition to an effective algorithmic approach to generate a structurally diverse training set of small synthetic networks. Thereby, we build an expressive message-passing framework and use it to efficiently solve the NP-hard problem of Network Dismantling, virtually equivalent to vital node identification, with significant real-world applications. Trained solely on diversified synthetic networks, our proposed model -- MIND: Message Iteration Network Dismantler -- generalizes to large, unseen real networks with millions of nodes, outperforming state-of-the-art network dismantling methods. Increased efficiency and generalizability of the proposed model can be leveraged beyond dismantling in a range of complex network problems.