Learning to Boost Resilience of Complex Networks via Neural Edge Rewiring

Shanchao Yang, MA KAILI, Tianshu Yu, Baoxiang Wang, Hongyuan Zha

Keywords: complex networks, network resilience, network robustness, graph neural networks

TL;DR: We develop an inductive network resilience optimization method with the proposed topology-inspired FireGNN for learning inductive neural edge rewiring to boost resilience of complex networks without rich features.

Abstract: The resilience of complex networks, a critical structural characteristic in network science, measures the network's ability to withstand noise corruption and structural changes. Improving resilience typically resorts to minimal modifications of the network structure via degree-preserving edge rewiring-based methods. Despite their effectiveness, existing methods are learning-free, sharing the limitation of transduction: a learned edge rewiring strategy from one graph cannot be generalized to another. Such a limitation cannot be trivially addressed by existing graph neural networks (GNNs)-based approaches since there is no rich initial node features for GNNs to learn meaningful representations. However, neural edge rewiring relies on GNNs for obtaining meaningful representations from pure graph topologies to select edges. We found existing GNNs degenerate remarkably with only pure topologies on the resilience task, leading to the undesired infinite action backtracking. In this work, inspired by persistent homology, we specifically design a variant of GNN called FireGNN for learning inductive edge rewiring strategies. Based on meaningful representations from FireGNN, we develop the first end-to-end inductive method, ResiNet, to discover $\textbf{resi}$lient $\textbf{net}$work topologies while balancing network utility. ResiNet reformulates network resilience optimization as a Markov decision process equipped with edge rewiring action space and learns to select correct edges successively. Extensive experiments demonstrate that ResiNet achieves a near-optimal resilience gain on various graphs while balancing the utility and outperforms existing approaches by a large margin.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning