Using Machine Learning to Predict Links and Improve Steiner Tree Solutions to Team Formation Problems

Keane, Peter; Ghaffar, Faisal; Malone, David

doi:10.1007/978-3-030-36683-4_79

Cited by 4 publications

(4 citation statements)

References 14 publications

(19 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We first note that our results are consistent with our previous evaluation on a more limited IBM data set (Keane et al 2019), where we observed smaller teams using the graph augmented using machine learning. One particularly interesting new observation we've made is that when we augment the graph with machine learning we end up with more isolated nodes than if we randomly augment the graph.…”

Section: Discussionsupporting

confidence: 91%

“…In this section we present our notation and summarise the work which we build on most directly. We note that this paper is an extended version of Keane et al (2019). The original results were produced using data from 1976 to 2011 for IBM alone, however this paper uses a broader dataset, ranging from 1976 to 2019.…”

Section: Preliminariesmentioning

confidence: 99%

“…Our previous application of this method focused on the years from 1976-2011 (Keane et al 2019). However, the USPTO now provide an updated databases and the records we use now run until August 2019.…”

Section: The Uspto Databasementioning

confidence: 99%

See 2 more Smart Citations

Using machine learning to predict links and improve Steiner tree solutions to team formation problems - a cross company study

Keane

Ghaffar²,

Malone

2020

Appl Netw Sci

Self Cite

View full text Add to dashboard Cite

The team formation problem has existed for many years in various guises. One important challenge in the team formation problem is to produce small teams that have a required set of skills. We propose a framework that incorporates machine learning to augment a collaboration graph with latent links between collaborators. This is combined with the solution of Steiner tree problems to form small teams that cover a specified set of tasks. Our framework not only considers the size of the team but also the likelihood that team members are going to collaborate with each other. We demonstrate our results using data from the US Patent office covering two different companies' inventor networks. The results show that this technique can reduce the size of suggested teams.

show abstract

Section: Discussionsupporting

confidence: 91%

Section: Preliminariesmentioning

confidence: 99%

See 1 more Smart Citation

Using machine learning to predict links and improve Steiner tree solutions to team formation problems - a cross company study

Keane

Ghaffar²,

Malone

2020

Appl Netw Sci

Self Cite

View full text Add to dashboard Cite

show abstract

“…Hence, an optimum team is a subgraph from a collaboration network that minimizes the communication cost among weighted edges and maximized the candidates' weights within the subgraph based on their h-index. In another extension to the [3] method, [21,22] tried to solve the team discovery problem by predicting explicit candidate collaboration in a team based on the potential link utilizing a link prediction technique. Following heuristic approach proposed by [3], they detected the minimum spanning subgraph as the optimum team.…”

Section: Team Discoverymentioning

confidence: 99%

Learning heterogeneous subgraph representations for team discovery

Hamidi Rad,

Nguyen,

Al-Obeidat

et al. 2023

Inf Retrieval J

View full text Add to dashboard Cite

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 subgraphs 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 bibliographic 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

show abstract

A Variational Neural Architecture for Skill-based Team Formation

Rad

Fani

Bagheri

et al. 2023

ACM Trans. Inf. Syst.

View full text Add to dashboard Cite

Team formation is concerned with the identification of a group of experts who have a high likelihood of effectively collaborating with each other in order to satisfy a collection of input skills. Solutions to this task have mainly adopted graph operations and at least have the following limitations: (1) they are computationally demanding as they require finding shortest paths on large collaboration networks; (2) they use various types of heuristics to reduce the exploration space over the collaboration network in order to become practically feasible; therefore, their results are not necessarily optimal; and, (3) they are not well-suited for collaboration network structures given the sparsity of these networks. Our work proposes a variational Bayesian neural network architecture that learns representations for teams whose members have collaborated with each other in the past. The learnt representations allow our proposed approach to mine teams that have a past collaborative history and collectively cover the requested desirable set of skills. Through our experiments, we demonstrate that our approach shows stronger performance compared to a range of strong team formation techniques from both quantitative and qualitative perspectives.

show abstract

Using Machine Learning to Predict Links and Improve Steiner Tree Solutions to Team Formation Problems

Cited by 4 publications

References 14 publications

Using machine learning to predict links and improve Steiner tree solutions to team formation problems - a cross company study

Using machine learning to predict links and improve Steiner tree solutions to team formation problems - a cross company study

Learning heterogeneous subgraph representations for team discovery

A Variational Neural Architecture for Skill-based Team Formation

Contact Info

Product

Resources

About