Publications

Learning to Form Skill-based Teams of Experts

Radin Hamidi Rad and Hossein Fani and Mehdi Kargar and Jaroslaw Szlichta and Ebrahim Bagheri
Reference:
Radin Hamidi Rad; Hossein Fani; Mehdi Kargar; Jaroslaw Szlichta and Ebrahim Bagheri Learning to Form Skill-based Teams of Experts. In The 29th ACM International Conference on Information and Knowledge Management, (CIKM2020), 2020.
Links to Publication:
Abstract:
We focus on the composition of teams of experts that collectively cover a set of required skills based on their historical collaboration network and expertise. Prior works are primarily based on the shortest path between experts on the expert collaboration network, and suffer from three major shortcomings: (1) they are computationally expensive due to the complexity of finding paths on large network structures; (2) they use a small portion of the entire historical collaboration network to reduce the search space; hence, may form sub-optimal teams; and, (3) they fall short in sparse networks where the majority of the experts have only participated in a few teams in the past. Instead of forming a large network of experts, we propose to learn relationships among experts and skills through a variational Bayes neural architecture wherein: i) we consider all past team compositions as training instances to predict future teams; ii) we bring scalability for large networks of experts due to the neural architecture; and, iii) we address sparsity by incorporating uncertainty on the neural network's parameters which yields a richer representation and more accurate team composition. We empirically demonstrate how our proposed model outperforms the state-of-the-art approaches in terms of effectiveness and efficiency.
Bibtex Entry:
@inproceedings{cikm-team, author = {Radin Hamidi Rad and Hossein Fani and Mehdi Kargar and Jaroslaw Szlichta and Ebrahim Bagheri}, title = {Learning to Form Skill-based Teams of Experts}, abstract = {We focus on the composition of teams of experts that collectively cover a set of required skills based on their historical collaboration network and expertise. Prior works are primarily based on the shortest path between experts on the expert collaboration network, and suffer from three major shortcomings: (1) they are computationally expensive due to the complexity of finding paths on large network structures; (2) they use a small portion of the entire historical collaboration network to reduce the search space; hence, may form sub-optimal teams; and, (3) they fall short in sparse networks where the majority of the experts have only participated in a few teams in the past. Instead of forming a large network of experts, we propose to learn relationships among experts and skills through a variational Bayes neural architecture wherein: i) we consider all past team compositions as training instances to predict future teams; ii) we bring scalability for large networks of experts due to the neural architecture; and, iii) we address sparsity by incorporating uncertainty on the neural network's parameters which yields a richer representation and more accurate team composition. We empirically demonstrate how our proposed model outperforms the state-of-the-art approaches in terms of effectiveness and efficiency.}, booktitle = {The 29th ACM International Conference on Information and Knowledge Management, (CIKM2020)}, year = {2020} }




Powered by WordPress