Graph Convolutional Neural Networks Sensitivity under Probabilistic Error Model

Xinjue Wang, Esa Ollila*, Sergiy A. Vorobyov

*Tämän työn vastaava kirjoittaja

Tutkimustuotos: LehtiartikkeliArticleScientificvertaisarvioitu

9 Lataukset (Pure)

Abstrakti

Graph Neural Networks (GNNs), particularly Graph Convolutional Neural Networks (GCNNs), have emerged as pivotal instruments in machine learning and signal processing for processing graph-structured data. This paper proposes an analysis framework to investigate the sensitivity of GCNNs to probabilistic graph perturbations, directly impacting the graph shift operator (GSO). Our study establishes tight expected GSO error bounds, which are explicitly linked to the error model parameters, and reveals a linear relationship between GSO perturbations and the resulting output differences at each layer of GCNNs. This linearity demonstrates that a single-layer GCNN maintains stability under graph edge perturbations, provided that the GSO errors remain bounded, regardless of the perturbation scale. For multilayer GCNNs, the dependency of system's output difference on GSO perturbations is shown to be a recursion of linearity. Finally, we exemplify the framework with the Graph Isomorphism Network (GIN) and Simple Graph Convolution Network (SGCN). Experiments validate our theoretical derivations and the effectiveness of our approach.

AlkuperäiskieliEnglanti
Sivut788-803
Sivumäärä16
JulkaisuIEEE Transactions on Signal and Information Processing over Networks
Vuosikerta10
Varhainen verkossa julkaisun päivämäärä2024
DOI - pysyväislinkit
TilaJulkaistu - 2024
OKM-julkaisutyyppiA1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä

Sormenjälki

Sukella tutkimusaiheisiin 'Graph Convolutional Neural Networks Sensitivity under Probabilistic Error Model'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä