Popularity Prediction for Social Media over Arbitrary Time Horizons
Daniel Haimovich, Dima Karamshuk, Thomas Leeper, Evgeniy Riabenko, Milan Vojnovic
Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD)
Network embedding has been increasingly employed in network analysis as it can learn node representations that encode the network structure resulting from node interactions. In this paper, besides the network structure, the interaction content within which each interaction arises is also embedded because it reveals interaction preferences of the two nodes involved, and interaction preferences are essential characteristics that nodes expose in the network environment. Specifically, we propose interaction content aware network embedding (ICANE) via co-embedding of nodes and edges. The embedding of edges is to learn edge representations that preserve the interaction content. Then the interaction content can be incorporated into node representations through edge representations. Comprehensive evaluation demonstrates ICANE outperforms five recent network embedding models in applications including visualization, link prediction and classification.
Daniel Haimovich, Dima Karamshuk, Thomas Leeper, Evgeniy Riabenko, Milan Vojnovic
Liqi Yan, Qifan Wang, Yiming Cu, Fuli Feng, Xiaojun Quan, Xiangyu Zhang, Dongfang Liu
Barlas Oğuz, Kushal Lakhotia, Anchit Gupta, Patrick Lewis, Vladimir Karpukhin, Aleksandra Piktus, Xilun Chen, Sebastian Riedel, Wen-tau Yih, Sonal Gupta, Yashar Mehdad