Radin Hamidi Rad
Hossein Fani
Divesh Srivastava
Skip Abstract Section
Abstract
Team formation is concerned with the identification of a group of experts who have a high likelihood of effectively collaborating with each other 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 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 learned 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.
- [1] . 2021. Computing Steiner trees using graph neural networks. CoRR abs/2108.08368 (2021).Google Scholar
- [2] . 2013. Fast exact shortest-path distance queries on large networks by pruned landmark labeling. In Proceedings of the ACM SIGMOD International Conference on Management of Data. ACM, 349–360.
DOI: Google ScholarDigital Library
- [3] . 2000. Minimum-diameter covering problems. Networks 36, 3 (2000), 147–155.
DOI: Google ScholarCross Ref
- [4] . 2007. Project team selection using fuzzy optimization approach. Cybern. Syst. 38, 2 (2007), 155–185.
DOI: Google ScholarDigital Library - [5] . 2011. Keyword search over relational databases: A metadata approach. In Proceedings of the ACM SIGMOD International Conference on Management of Data. ACM, 565–576.
DOI: Google ScholarDigital Library - [6] . 2015. Weight uncertainty in neural networks. In Proceedings of the 32nd International Conference on International Conference on Machine Learning (ICML’15). JMLR.org, 1613–1622.Google Scholar
- [7] . 2020. Robust keyword search in large attributed graphs. Inf. Retr. J. 23, 5 (2020), 502–524.
DOI: Google ScholarDigital Library - [8] . 2021. Towards a theoretical understanding of the robustness of variational autoencoders. In Proceedings of the 24th International Conference on Artificial Intelligence and Statistics(
Proceedings of Machine Learning Research , Vol. 130). PMLR, 3565–3573. Retrieved from http://proceedings.mlr.press/v130/camuto21a.html.Google Scholar - [9] . 2000. Algorithms for the set covering problem. Ann. Oper. Res. 98, 1 (2000), 353–371.Google ScholarCross Ref
- [10] . 2006. Application of social network analysis to collaborative team formation. In Proceedings of the International Symposium on Collaborative Technologies and Systems. IEEE Computer Society, 306–311.
DOI: Google ScholarDigital Library - [11] . 2020. Team formation in software engineering: A systematic mapping study. IEEE Access 8 (2020), 145687–145712.
DOI: Google ScholarCross Ref - [12] . 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, 4171–4186.
DOI: Google ScholarCross Ref - [13] . 2011. Interaction mining and skill-dependent recommendations for multi-objective team composition. Data Knowl. Eng. 70, 10 (2011), 866–891.
DOI: Google ScholarDigital Library - [14] . 2020. GERF: A group event recommendation framework based on learning-to-rank. IEEE Trans. Knowl. Data Eng. 32, 4 (2020), 674–687.
DOI: Google ScholarCross Ref - [15] . 2014. Using hybrid scheduling for the semi-autonomous formation of expert teams. Fut. Gen. Comput. Syst. 31 (2014), 200–212.
DOI: Google ScholarDigital Library - [16] . 2005. A survey on web services composition. Int. J. Web Grid Serv. 1, 1 (2005), 1–30.
DOI: Google ScholarDigital Library - [17] . 2016. Effective community search for large attributed graphs. Proc. VLDB Endow. 9, 12 (2016), 1233–1244.
DOI: Google ScholarDigital Library - [18] . 2020. User community detection via embedding of social network structure and temporal content. Inf. Process. Manag. 57, 2 (2020), 102056.
DOI: Google ScholarDigital Library - [19] . 2005. Forming effective worker teams with multi-functional skill requirements. Comput. Industr. Eng. 48, 3 (2005), 593–608.
DOI: Google ScholarCross Ref - [20] . 2004. Adapting network structure for efficient team formation. In Artificial Multiagent Learning, Papers from the 2004 AAAI Fall Symposium. Arlington, VA, USA, October 22-24, 2004, Vol. FS-04-02. AAAI Press, 1–8. Retrieved from https://www.aaai.org/Library/Symposia/Fall/2004/fs04-02-001.php.Google Scholar
- [21] . 2011. Practical variational inference for neural networks. In Proceedings of the 25th Annual Conference on Neural Information Processing Systems. 2348–2356. Retrieved from https://proceedings.neurips.cc/paper/2011/hash/7eb3c8be3d411e8ebfab08eba5f49632-Abstract.html.Google Scholar
- [22] . 2022. Hands-on bayesian neural networks—A tutorial for deep learning users. IEEE Comput. Intell. Mag. 17, 2 (2022), 29–48.
DOI: Google ScholarCross Ref - [23] . 2011. Discovering top-k teams of experts with/without a leader in social networks. In Proceedings of the 20th ACM Conference on Information and Knowledge Management. ACM, 985–994.
DOI: Google ScholarDigital Library - [24] . 2022. Effective keyword search over weighted graphs. IEEE Trans. Knowl. Data Eng. 34, 2 (2022), 601–616.
DOI: Google ScholarDigital Library - [25] . 1972. Reducibility among combinatorial problems. In Proceedings of a Symposium on the Complexity of Computer Computations. Plenum Press, New York, 85–103.
DOI: Google ScholarCross Ref - [26] . 2019. Using machine learning to predict links and improve Steiner tree solutions to team formation problems. In Complex Networks and Their Applications VIII - Volume 2 Proceedings of the Eighth International Conference on Complex Networks and Their Applications COMPLEX NETWORKS 2019, Lisbon, Portugal, December 10-12, 2019(
Studies in Computational Intelligence , Vol. 882), , , , , and (Eds.). Springer, 995–1006.DOI: Google ScholarCross Ref - [27] . 2020. Using machine learning to predict links and improve Steiner tree solutions to team formation problems—A cross company study. Appl. Netw. Sci. 5, 1 (2020), 57.
DOI: Google ScholarCross Ref - [28] . 2017. Learning combinatorial optimization algorithms over graphs. In Proceedings of the Annual Conference on Neural Information Processing Systems. 6348–6358. Retrieved from https://proceedings.neurips.cc/paper/2017/hash/d9896106ca98d3d05b8cbdf4fd8b13a1-Abstract.html.Google Scholar
- [29] . 2020. Compact group discovery in attributed graphs and social networks. Inf. Process. Manag. 57, 2 (2020), 102054.
DOI: Google ScholarDigital Library - [30] . 2009. Collaborative filtering with temporal dynamics. In Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 447–456.
DOI: Google ScholarDigital Library - [31] . 2011. Combinatorial Optimization. Vol. 1. Springer.Google Scholar
- [32] . 2009. Finding a team of experts in social networks. In Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 467–476.
DOI: Google ScholarDigital Library - [33] . 2020. Social influence based community detection in event-based social networks. Inf. Process. Manag. 57, 6 (2020), 102353.
DOI: Google ScholarCross Ref - [34] . 2022. Group event recommendation based on graph multi-head attention network combining explicit and implicit information. Inf. Process. Manag. 59, 2 (2022), 102797.
DOI: Google ScholarDigital Library - [35] . 2007. Towards a context-based multi-type policy approach for web services composition. Data Knowl. Eng. 62, 2 (2007), 327–351.
DOI: Google ScholarDigital Library - [36] . 2013. Efficient estimation of word representations in vector space. In Proceedings of the 1st International Conference on Learning Representations. Retrieved from http://arxiv.org/abs/1301.3781.Google Scholar
- [37] . 2010. Recurrent neural network based language model. In Proceedings of the 11th Annual Conference of the International Speech Communication Association. ISCA, 1045–1048. Retrieved from http://www.isca-speech.org/archive/interspeech_2010/i10_1045.html.Google ScholarCross Ref
- [38] . 1998. WordNet: An Electronic Lexical Database. MIT Press.Google Scholar
- [39] . 2019. Multi-aspect review-team assignment using latent research areas. Inf. Process. Manag. 56, 3 (2019), 858–878.
DOI: Google ScholarDigital Library - [40] . 2014. Expert group formation using facility location analysis. Inf. Process. Manag. 50, 2 (2014), 361–383.
DOI: Google ScholarDigital Library - [41] . 2022. PyDHNet: A Python library for dynamic heterogeneous network representation learning and evaluation. In Proceedings of the 31st ACM International Conference on Information & Knowledge Management. ACM, 4936–4940.
DOI: Google ScholarDigital Library - [42] . 2021. ExEm: Expert embedding using dominating set theory with deep learning approaches. Expert Syst. Appl. 177 (2021), 114913.
DOI: Google ScholarDigital Library - [43] . 1991. A branch-and-cut algorithm for the resolution of large-scale symmetric traveling salesman problems. SIAM Rev. 33, 1 (1991), 60–100.
DOI: Google ScholarDigital Library - [44] . 2007. Improving the quality of collaboration requirements for information management through social networks analysis. Int. J. Inf. Manag. 27, 2 (2007), 86–103.
DOI: Google ScholarDigital Library - [45] . 1996. Neural network for optimal {steiner} tree computation. Neural Process. Lett. 3, 3 (1996), 139–149.
DOI: Google ScholarDigital Library - [46] . 2007. The service ecosystem: Dynamic self-aggregation of pervasive communication services. In Proceedings of the 1st International Workshop on Software Engineering for Pervasive Computing Applications, Systems, and Environments (SEPCASE’07). IEEE, 1–1.Google ScholarDigital Library
- [47] . 2021. Retrieving skill-based teams from collaboration networks. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM, 2015–2019.
DOI: Google ScholarDigital Library - [48] . 2022. Subgraph representation learning for team mining. In Proceedings of the 14th ACM Web Science Conference. ACM, 148–153.
DOI: Google ScholarDigital Library - [49] . 2020. Learning to form skill-based teams of experts. In Proceedings of the 29th ACM International Conference on Information and Knowledge Management. ACM, 2049–2052.
DOI: Google ScholarDigital Library - [50] . 2021. PyTFL: A Python-based neural team formation toolkit. In Proceedings of the 30th ACM International Conference on Information and Knowledge Management. ACM, 4716–4720.
DOI: Google ScholarDigital Library - [51] . 2022. A neural approach to forming coherent teams in collaboration networks. In Proceedings of the 25th International Conference on Extending Database Technology. OpenProceedings.org, 2:440–2:444.
DOI: Google ScholarCross Ref - [52] . 2019. Deep neural networks for optimal team composition. Front. Big Data 2 (2019), 14.
DOI: Google ScholarCross Ref - [53] . 2010. The community-search problem and how to plan a successful cocktail party. In Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 939–948.
DOI: Google ScholarDigital Library - [54] . 2020. Learning to hash with graph neural networks for recommender systems. In Proceedings of the Web Conference. ACM/IW3C2, 1988–1998.
DOI: Google ScholarDigital Library - [55] . 2009. A team formation model based on knowledge and collaboration. Expert Syst. Appl. 36, 5 (2009), 9121–9134.
DOI: Google ScholarDigital Library - [56] . 2017. Recurrent recommender networks. In Proceedings of the 10th ACM International Conference on Web Search and Data Mining. ACM, 495–503.
DOI: Google ScholarDigital Library - [57] . 2021. A comprehensive survey on graph neural networks. IEEE Trans. Neural Netw. Learn. Syst. 32, 1 (2021), 4–24.
DOI: Google ScholarCross Ref - [58] . 2006. Context-aware dynamic personalised service re-composition in a pervasive service environment. In Proceedings of the 3rd International Conference on Ubiquitous Intelligence and Computing(
Lecture Notes in Computer Science , Vol. 4159). Springer, 724–735.DOI: Google ScholarDigital Library - [59] . 2017. Authority-based team discovery in social networks. In Proceedings of the 20th International Conference on Extending Database Technology. OpenProceedings.org, 498–501.
DOI: Google ScholarCross Ref - [60] . 1999. Forming teams: An analytical approach. IIE Trans. 31, 1 (1999), 85–97.Google ScholarCross Ref
Index Terms
-
A Variational Neural Architecture for Skill-based Team Formation
-
Recommendations
-
Retrieving Skill-Based Teams from Collaboration Networks
SIGIR '21: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information RetrievalGiven a set of required skills, the objective of the team formation problem is to form a team of experts that cover the required skills. Most existing approaches are based on graph methods, such as minimum-cost spanning trees. These approaches, due to ...
-
Learning to Form Skill-based Teams of Experts
CIKM '20: Proceedings of the 29th ACM International Conference on Information & Knowledge ManagementWe 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 ...
-
Agent-organized networks for dynamic team formation
AAMAS '05: Proceedings of the fourth international joint conference on Autonomous agents and multiagent systemsMany multi-agent systems consist of a complex network of autonomous yet interdependent agents. Examples of such networked multi-agent systems include supply chains and sensor networks. In these systems, agents have a select set of other agents with whom ...
Comments