Implementation for DUALGCN: A CONVOLUTIONAL NETWORK FOR ANOMALY DETECTION IN DIRECTED GRAPHS BASED ON SYMMETRIZED AND SKEW-SYMMETRIZED LAPLACIANS, published in (MLSP 2024) 2024 IEEE International Workshop on Machine Learning for Signal Processing.
The paper describes a dual spectral graph convolutional network, addressing the anomaly detection problem in directed graphs.
Please cite as follows:
T. Badea and B. Dumitrescu, "DualGCN: A convolutional network for anomaly detection in directed graphs based on symmetrized and skew-symmetrized Laplacian" 2024 IEEE 34rd International Workshop on Machine Learning for Signal Processing (MLSP), London, UK, 2024.
Project: Asymmetric Dictionary Learning AsyDiL: PCE project PN-III-P4-PCE-2021- 0154 https://asydil.upb.ro/