Projekteja vuodessa
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.
Alkuperäiskieli | Englanti |
---|---|
Sivut | 788-803 |
Sivumäärä | 16 |
Julkaisu | IEEE Transactions on Signal and Information Processing over Networks |
Vuosikerta | 10 |
Varhainen verkossa julkaisun päivämäärä | 2024 |
DOI - pysyväislinkit | |
Tila | Julkaistu - 2024 |
OKM-julkaisutyyppi | A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä |
Sormenjälki
Sukella tutkimusaiheisiin 'Graph Convolutional Neural Networks Sensitivity under Probabilistic Error Model'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.Projektit
- 2 Aktiivinen
-
AoF-ISAC: AI-assisted Waveform and Beamforming Design for Integrated Sensing and Communication
Ollila, E. (Vastuullinen tutkija), Kuikka, J. (Projektin jäsen), Wang, X. (Projektin jäsen) & Wang, L. (Projektin jäsen)
01/01/2024 → 31/12/2026
Projekti: Academy of Finland: Other research funding
-
AI Based RAN: Towards Scalable and AI-Based Solutions for Beyond-5G Radio Access Networks
Vorobyov, S. (Vastuullinen tutkija), Esfandiari, M. (Projektin jäsen), Hassas Irani, K. (Projektin jäsen) & Zhang, T. (Projektin jäsen)
01/01/2023 → 31/12/2025
Projekti: Academy of Finland: Other research funding