Network Representation Learning Algorithm Based on Neighborhood Influence Sequence

Meng Liu, Ziwei Quan, Yong Liu
Proceedings of The 12th Asian Conference on Machine Learning, PMLR 129:609-624, 2020.

Abstract

Network representation learning (NRL) is playing an important role in network analysis, aiming to represent complex network more concisely by transforming nodes into low-dimensional vectors. However, most of the current work only uses network structure and node attribute to learn network representation, and often ignores the historical interactions between nodes that will affect the future interactions. Therefore, we propose a network representation learning algorithm based on neighborhood influence sequence (NIS), by investigating the influence of node historical interactions on future interactions. We propose three kinds of influence when two nodes interact, and integrate them into NIS by introducing the Hawkes process. In experiments, we compare our model with existing NRL models on four real-world datasets. Experimental results demonstrate that the embedding learned from the proposed NIS model achieve better performance than state-of-the-art methods in various tasks including node classification, link prediction, and network visualization.

Cite this Paper

BibTeX
@InProceedings{pmlr-v129-liu20a, title = {Network Representation Learning Algorithm Based on Neighborhood Influence Sequence}, author = {Liu, Meng and Quan, Ziwei and Liu, Yong}, booktitle = {Proceedings of The 12th Asian Conference on Machine Learning}, pages = {609--624}, year = {2020}, editor = {Pan, Sinno Jialin and Sugiyama, Masashi}, volume = {129}, series = {Proceedings of Machine Learning Research}, month = {18--20 Nov}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v129/liu20a/liu20a.pdf}, url = {https://proceedings.mlr.press/v129/liu20a.html}, abstract = {Network representation learning (NRL) is playing an important role in network analysis, aiming to represent complex network more concisely by transforming nodes into low-dimensional vectors. However, most of the current work only uses network structure and node attribute to learn network representation, and often ignores the historical interactions between nodes that will affect the future interactions. Therefore, we propose a network representation learning algorithm based on neighborhood influence sequence (NIS), by investigating the influence of node historical interactions on future interactions. We propose three kinds of influence when two nodes interact, and integrate them into NIS by introducing the Hawkes process. In experiments, we compare our model with existing NRL models on four real-world datasets. Experimental results demonstrate that the embedding learned from the proposed NIS model achieve better performance than state-of-the-art methods in various tasks including node classification, link prediction, and network visualization.} }
Endnote
%0 Conference Paper %T Network Representation Learning Algorithm Based on Neighborhood Influence Sequence %A Meng Liu %A Ziwei Quan %A Yong Liu %B Proceedings of The 12th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2020 %E Sinno Jialin Pan %E Masashi Sugiyama %F pmlr-v129-liu20a %I PMLR %P 609--624 %U https://proceedings.mlr.press/v129/liu20a.html %V 129 %X Network representation learning (NRL) is playing an important role in network analysis, aiming to represent complex network more concisely by transforming nodes into low-dimensional vectors. However, most of the current work only uses network structure and node attribute to learn network representation, and often ignores the historical interactions between nodes that will affect the future interactions. Therefore, we propose a network representation learning algorithm based on neighborhood influence sequence (NIS), by investigating the influence of node historical interactions on future interactions. We propose three kinds of influence when two nodes interact, and integrate them into NIS by introducing the Hawkes process. In experiments, we compare our model with existing NRL models on four real-world datasets. Experimental results demonstrate that the embedding learned from the proposed NIS model achieve better performance than state-of-the-art methods in various tasks including node classification, link prediction, and network visualization.
APA
Liu, M., Quan, Z. & Liu, Y.. (2020). Network Representation Learning Algorithm Based on Neighborhood Influence Sequence. Proceedings of The 12th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 129:609-624 Available from https://proceedings.mlr.press/v129/liu20a.html.

Related Material