TY - GEN
T1 - Gravity-inspired graph autoencoders for directed link prediction
AU - Salha, Guillaume
AU - Limnios, Stratis
AU - Hennequin, Romain
AU - Tran, Viet Anh
AU - Vazirgiannis, Michalis
N1 - Publisher Copyright:
© 2019 Copyright held by the owner/author(s). Publication rights licensed to ACM.
PY - 2019/11/3
Y1 - 2019/11/3
N2 - Graph autoencoders (AE) and variational autoencoders (VAE) recently emerged as powerful node embedding methods. In particular, graph AE and VAE were successfully leveraged to tackle the challenging link prediction problem, aiming at figuring out whether some pairs of nodes from a graph are connected by unobserved edges. However, these models focus on undirected graphs and therefore ignore the potential direction of the link, which is limiting for numerous real-life applications. In this paper, we extend the graph AE and VAE frameworks to address link prediction in directed graphs. We present a new gravity-inspired decoder scheme that can effectively reconstruct directed graphs from a node embedding. We empirically evaluate our method on three different directed link prediction tasks, for which standard graph AE and VAE perform poorly. We achieve competitive results on three real-world graphs, outperforming several popular baselines.
AB - Graph autoencoders (AE) and variational autoencoders (VAE) recently emerged as powerful node embedding methods. In particular, graph AE and VAE were successfully leveraged to tackle the challenging link prediction problem, aiming at figuring out whether some pairs of nodes from a graph are connected by unobserved edges. However, these models focus on undirected graphs and therefore ignore the potential direction of the link, which is limiting for numerous real-life applications. In this paper, we extend the graph AE and VAE frameworks to address link prediction in directed graphs. We present a new gravity-inspired decoder scheme that can effectively reconstruct directed graphs from a node embedding. We empirically evaluate our method on three different directed link prediction tasks, for which standard graph AE and VAE perform poorly. We achieve competitive results on three real-world graphs, outperforming several popular baselines.
KW - Autoencoders
KW - Directed Graphs
KW - Graph Representation Learning
KW - Link Prediction
KW - Node Embedding
KW - Variational Autoencoders
UR - https://www.scopus.com/pages/publications/85075422410
U2 - 10.1145/3357384.3358023
DO - 10.1145/3357384.3358023
M3 - Conference contribution
AN - SCOPUS:85075422410
T3 - International Conference on Information and Knowledge Management, Proceedings
SP - 589
EP - 598
BT - CIKM 2019 - Proceedings of the 28th ACM International Conference on Information and Knowledge Management
PB - Association for Computing Machinery
T2 - 28th ACM International Conference on Information and Knowledge Management, CIKM 2019
Y2 - 3 November 2019 through 7 November 2019
ER -