The team discovery task is concerned with finding a group of experts from a collaboration network who would collectively cover a desirable set of skills. Most prior work for team discovery either adopt graph-based or neural mapping approaches. Graph-based approaches are computationally intractable often leading to sub-optimal team selection. Neural mapping approaches have better performance, however, are still limited as they learn individual representations for skills and experts and are often prone to overfitting given the sparsity of collaboration networks. Thus, we define the team discovery task as one of learning subgraph representations from heterogeneous collaboration network where the sub-graphs represent teams which are then used to identify relevant teams for a given set of skills. As such, our approach captures local (node interactions with each team) and global (subgraph interactions between teams) characteristics of the representation network and allows us to easily map between any homogeneous and heterogeneous subgraphs in the network to effectively discover teams. Our experiments over two real-world datasets from different domains, namely the DBLP biblio-graphic dataset with 10, 647 papers and IMDB with 4, 882 movies, illustrate that our approach outperforms the state-of-the-art baselines on a range of ranking and quality metrics. More specifically, in terms of ranking metrics, we are superior to the best baseline by approximately 15% on the DBLP dataset and by approximately 20% on the IMDB dataset. Further, our findings illustrate that our approach consistently shows a robust performance improvement over the baselines.

No abstract

Many real-world networks, such as social networks, contain structuralheterogeneity and experience temporal evolution. However, while therehas been growing literature on network representation learning, only afew have addressed the need to learn representations for dynamic hetero-geneous networks. The objective of our work in this paper is to introduce DyHNet, which learns representations for such networks and distinguishesitself from the state-of-the-art by systematically capturing (1) local nodesemantics, (2) global network semantics, and (3) longer-range temporalassociations between network snapshots when learning network repre-sentations. Through experiments on four real-world datasets, we demon-strate that our proposed method is able to show consistently better andmore robust performance compared to the state-of-the-art techniques.