Task-Guided Pair Embedding in Heterogeneous Network
Proceedings of the 28th ACM International Conference on Information and Knowledge Management, pp. 489-498, 2019.
author identification deep learning heterogeneous network representation learning
Many real-world tasks solved by heterogeneous network embedding methods can be cast as modeling the likelihood of a pairwise relationship between two nodes. For example, the goal of author identification task is to model the likelihood of a paper being written by an author (paper-author pairwise relationship). Existing taskguided embeddin...More
PPT (Upload PPT)