Neural network spectral robustness under perturbations of the underlying graph
Recent studies have been using graph theoretical approaches to model complex networks (such as social, infrastructural or biological networks), and how their hardwired circuitry relates to their dynamic evolution in time. Understanding how configuration reflects on the coupled behavior in a system of dynamic nodes can be of great importance, for example in the context of how the brain connectome is affecting brain function. However, the connectivity patterns that appear in brain networks, and their individual effects on network dynamics, are far from being fully understood. We study the connections between edge configuration and dynamics in a simple oriented network composed of two interconnected cliques (representative of brain feedback regulatory circuitry). In this paper, our main goal is to study the spectra of the graph adjacency and Laplacian matrices, with a focus on three aspects in particular: (1) the sensitivity/robustness the spectrum in response to varying the intra and inter-modular edge density, (2) the effects on the spectrum of perturbing the edge configuration, while keeping the densities fixed and (3) the effects of increasing the network size. We study some tractable aspects analytically, then simulate more general results numerically. This paper aims to clarify, from analytical and modeling perspectives, the underpinnings of our related work, which further addresses how graph properties affect the network's temporal dynamics and phase transitions. We propose that this type of results may be helpful when studying small networks such as macroscopic brain circuits. We suggest potential applications to understanding synaptic restructuring in learning networks, and the effects of network configuration to function of emotion-regulatory neural circuits.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Robust spectral clustering using LASSO regularization
Cluster structure detection is a fundamental task for the analysis of graphs, in order to understand and to visualize their functional characteristics. Among the different cluster structure detection methods, spectral cl…
ClusteringStochastic Block ModelTransferability of Spectral Graph Convolutional Neural Networks
This paper focuses on spectral graph convolutional neural networks (ConvNets), where filters are defined as elementwise multiplication in the frequency domain of a graph. In machine learning settings where the dataset co…
Spectral Adversarial Training for Robust Graph Neural Network
Recent studies demonstrate that Graph Neural Networks (GNNs) are vulnerable to slight but adversarially designed perturbations, known as adversarial examples. To address this issue, robust training methods against advers…
Graph Neural NetworkLimitless stability for Graph Convolutional Networks
This work establishes rigorous, novel and widely applicable stability guarantees and transferability bounds for graph convolutional networks -- without reference to any underlying limit object or statistical distribution…
ASPECT: Node-Level Adaptive Spectral Fusion for Graph Contrastive Learning
Spectral graph contrastive learning often constructs low- and high-frequency views to capture complementary graph signals, but these views are commonly combined by graph-level or node-agnostic fusion rules. We show that …
Contrastive Learning