TY - GEN
T1 - INFERENCE OF TIME-VARYING GRAPH TOPOLOGIES VIA GAUSSIAN PROCESSES
AU - Cui, Chen
AU - Djurić, Petar M.
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - In this paper, we explore the estimation of directed time-varying graph topologies, which represent evolving relationships among nodes in high-dimensional, interdependent data. We introduce a novel fully Bayesian method based on Gaussian processes, employing random walks to model the time-varying edge weights with time. This approach accommodates nonlinear and time-varying lagged relationships among time series. We implement the proposed method using the Hamiltonian Monte Carlo method. Numerical tests reveal that our method performs very well and is comparable to state-of-the-art methods, making it a promising tool for unveiling dynamic graph structures and causality.
AB - In this paper, we explore the estimation of directed time-varying graph topologies, which represent evolving relationships among nodes in high-dimensional, interdependent data. We introduce a novel fully Bayesian method based on Gaussian processes, employing random walks to model the time-varying edge weights with time. This approach accommodates nonlinear and time-varying lagged relationships among time series. We implement the proposed method using the Hamiltonian Monte Carlo method. Numerical tests reveal that our method performs very well and is comparable to state-of-the-art methods, making it a promising tool for unveiling dynamic graph structures and causality.
KW - Gaussian processes
KW - Hamiltonian Monte Carlo
KW - automatic relevance determination
KW - time-varying graphs
UR - https://www.scopus.com/pages/publications/85195417631
U2 - 10.1109/ICASSP48485.2024.10447631
DO - 10.1109/ICASSP48485.2024.10447631
M3 - Conference contribution
AN - SCOPUS:85195417631
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 13276
EP - 13280
BT - 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024
Y2 - 14 April 2024 through 19 April 2024
ER -