Directed Graph Auto-Encoders
Keywords:Machine Learning (ML)
AbstractWe introduce a new class of auto-encoders for directed graphs, motivated by a direct extension of the Weisfeiler-Leman algorithm to pairs of node labels. The proposed model learns pairs of interpretable latent representations for the nodes of directed graphs, and uses parameterized graph convolutional network (GCN) layers for its encoder and an asymmetric inner product decoder. Parameters in the encoder control the weighting of representations exchanged between neighboring nodes. We demonstrate the ability of the proposed model to learn meaningful latent embeddings and achieve superior performance on the directed link prediction task on several popular network datasets.
How to Cite
Kollias, G., Kalantzis, V., Ide, T., Lozano, A., & Abe, N. (2022). Directed Graph Auto-Encoders. Proceedings of the AAAI Conference on Artificial Intelligence, 36(7), 7211-7219. https://doi.org/10.1609/aaai.v36i7.20682
AAAI Technical Track on Machine Learning II