Nonparametric exponential family graph embeddings for multiple representation learning

Chien Lu, Jaakko Peltonen, Timo Nummenmaa, Jyrki Nummenmaa
Proceedings of the Thirty-Eighth Conference on Uncertainty in Artificial Intelligence, PMLR 180:1275-1285, 2022.

Abstract

In graph data, each node often serves multiple functionalities. However, most graph embedding models assume that each node can only possess one representation. We address this issue by proposing a nonparametric graph embedding model. The model allows each node to learn multiple representations where they are needed to represent the complexity of random walks in the graph. It extends the Exponential family graph embedding model with two nonparametric prior settings, the Dirichlet process and the uniform process. The model combines the ability of Exponential family graph embedding to take the number of occurrences of context nodes into account with nonparametric priors giving it the flexibility to learn more than one latent representation for each node. The learned embeddings outperform other state of the art approaches in link prediction and node classification tasks.

Cite this Paper

BibTeX
@InProceedings{pmlr-v180-lu22a, title = {Nonparametric exponential family graph embeddings for multiple representation learning}, author = {Lu, Chien and Peltonen, Jaakko and Nummenmaa, Timo and Nummenmaa, Jyrki}, booktitle = {Proceedings of the Thirty-Eighth Conference on Uncertainty in Artificial Intelligence}, pages = {1275--1285}, year = {2022}, editor = {Cussens, James and Zhang, Kun}, volume = {180}, series = {Proceedings of Machine Learning Research}, month = {01--05 Aug}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v180/lu22a/lu22a.pdf}, url = {https://proceedings.mlr.press/v180/lu22a.html}, abstract = {In graph data, each node often serves multiple functionalities. However, most graph embedding models assume that each node can only possess one representation. We address this issue by proposing a nonparametric graph embedding model. The model allows each node to learn multiple representations where they are needed to represent the complexity of random walks in the graph. It extends the Exponential family graph embedding model with two nonparametric prior settings, the Dirichlet process and the uniform process. The model combines the ability of Exponential family graph embedding to take the number of occurrences of context nodes into account with nonparametric priors giving it the flexibility to learn more than one latent representation for each node. The learned embeddings outperform other state of the art approaches in link prediction and node classification tasks.} }
Endnote
%0 Conference Paper %T Nonparametric exponential family graph embeddings for multiple representation learning %A Chien Lu %A Jaakko Peltonen %A Timo Nummenmaa %A Jyrki Nummenmaa %B Proceedings of the Thirty-Eighth Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2022 %E James Cussens %E Kun Zhang %F pmlr-v180-lu22a %I PMLR %P 1275--1285 %U https://proceedings.mlr.press/v180/lu22a.html %V 180 %X In graph data, each node often serves multiple functionalities. However, most graph embedding models assume that each node can only possess one representation. We address this issue by proposing a nonparametric graph embedding model. The model allows each node to learn multiple representations where they are needed to represent the complexity of random walks in the graph. It extends the Exponential family graph embedding model with two nonparametric prior settings, the Dirichlet process and the uniform process. The model combines the ability of Exponential family graph embedding to take the number of occurrences of context nodes into account with nonparametric priors giving it the flexibility to learn more than one latent representation for each node. The learned embeddings outperform other state of the art approaches in link prediction and node classification tasks.
APA
Lu, C., Peltonen, J., Nummenmaa, T. & Nummenmaa, J.. (2022). Nonparametric exponential family graph embeddings for multiple representation learning. Proceedings of the Thirty-Eighth Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research 180:1275-1285 Available from https://proceedings.mlr.press/v180/lu22a.html.

Related Material