A Stochastic Team Formation Approach for Collaborative Mobile Crowdsourcing

Hamrouni, Aymen; Ghazzai, Hakim; Alelyani, Turki; Massoud, Yehia

doi:10.1109/icm48031.2019.9021910

Cited by 11 publications

(4 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a matter of fact, several approaches divide the complex tasks into multiple simple sub-tasks and assign those sub-tasks to a group of clients. Afterwards, the partial results from each client are combined to produce the overall result [22], [23], [24]. However, those approaches considered the skills of individual clients and ignored the interaction between them.…”

Section: Client Selectionmentioning

confidence: 99%

THF: 3-Way Hierarchical Framework for Efficient Client Selection and Resource Management in Federated Learning

Asad¹,

Rabhi²,

Aslam³

2022

IEEE Internet Things J.

View full text Add to dashboard Cite

Federated Learning (FL) is a promising technique for collaboratively training machine learning models on massively distributed clients data under privacy constraints. However, the existing FL literature focuses on speeding-up the learning process and ignores minimizing the communication cost which is critical for resource-constrained clients. To this end, in this paper, we propose a novel 3-way hierarchical framework (THF) to promote communication efficiency in FL. Using the proposed framework, only a cluster-head (CH) communicates with the cloud server through edge-aggregation in order to minimize the communication cost of clients. In particular, the clients upload their local models to their respective CHs, which are responsible to forward them to the corresponding edge-server. The edgeserver averages the local models and iterates until it achieves the edge-accuracy. Afterward, each edge-server uploads the edgemodels to the cloud server for global aggregation. In this way, model downloading and uploading requires less bandwidth due to the short distance from source to destination that makes an efficient 3-way hierarchical network structure. In addition, we formulate a joint communication and computation resource management scheme through efficient client selection in order to achieve global cost minimization in FL. We conduct extensive empirical evaluations on diverse data learning tasks on multiple datasets to signify that THF achieves global cost savings and converges within fewer communication rounds compared to other FL approaches.

show abstract

Section: Client Selectionmentioning

confidence: 99%

THF: 3-Way Hierarchical Framework for Efficient Client Selection and Resource Management in Federated Learning

Asad¹,

Rabhi²,

Aslam³

2022

IEEE Internet Things J.

View full text Add to dashboard Cite

show abstract

“…The second approach, identified as the "Stochastic approach", is a probabilistic technique that uses the optimal stopping strategies. It is based on the odds algorithm [59], [60]. The purpose of this Monte-Carlo simulation is to evaluate the recruitment key metrics: skills, skills uncertainty, edge degree, edge uncertainty, and the reward for each of these three algorithms for a large-scale As performed previously in Fig.…”

Section: Proposed Algorithm Performance Analysismentioning

confidence: 99%

Low Complexity Recruitment for Collaborative Mobile Crowdsourcing Using Graph Neural Networks

Hamrouni¹,

Ghazzai²,

Alelyani³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Collaborative Mobile crowdsourcing (CMCS) allows entities, e.g., local authorities or individuals, to hire a team of workers from the crowd of connected people, to execute complex tasks. In this paper, we investigate two different CMCS recruitment strategies allowing task requesters to form teams of socially connected and skilled workers: i) a platform-based strategy where the platform exploits its own knowledge about the workers to form a team and ii) a leader-based strategy where the platform designates a group leader that recruits its own suitable team given its own knowledge about its Social Network (SN) neighbors. We first formulate the recruitment as an Integer Linear Program (ILP) that optimally forms teams according to four fuzzy-logic-based criteria: level of expertise, social relationship strength, recruitment cost, and recruiter's confidence level. To cope with NP-hardness, we design a novel low-complexity CMCS recruitment approach relying on Graph Neural Networks (GNNs), specifically graph embedding and clustering techniques, to shrink the workers' search space and afterwards, exploiting a meta-heuristic genetic algorithm to select appropriate workers. Simulation results applied on a real-world dataset illustrate the performance of both proposed CMCS recruitment approaches. It is shown that our proposed low-complexity GNN-based recruitment algorithm achieves close performances to those of the baseline ILP with significant computational time saving and ability to operate on large-scale mobile crowdsourcing platforms. It is also shown that compared to the leader-based strategy, the platform-based strategy recruits a more skilled team but with lower SN relationships and higher cost.

show abstract

“…However, this approach missed to cover the fact that maximizing the number of matched tasks is not necessarily equivalent to maximizing the number of completed tasks if the travel costs and expiration time are taken into consideration. Hamrouni et al [29] proposed a stochastic approach in collaborative mobile crowdsourcing platforms where a team leader recruit skilled and socially connected workers. Kang et al [30] formulated the recruitment process in a hitchhiking style where workers have specific trajectories and can complete tasks located on their ways but failed to generalize this approach to different types of workers and limited their approach to human type (i.e., workers can be machines as well as humans).…”

Section: Related Workmentioning

confidence: 99%

Many-to-Many Recruitment and Scheduling in Spatial Mobile Crowdsourcing

2020

Self Cite

View full text Add to dashboard Cite

Spatial mobile crowdsourcing (SMCS) enables a task requester to commission workers to physically travel to specific locations to perform a set of spatial assignments (i.e., tasks are related to a specific geographical location besides time). To efficiently perform such tasks and guarantee the best possible quality of returned results, optimizing the worker recruitment and task assignment processes must be conducted. Because both workers and task requesters impose certain criteria, this procedure is not obvious. To tackle this issue, we propose a novel formulation of the SMCS recruitment where task matching and worker scheduling are jointly optimized. A Mixed Integer Linear Program (MILP) is first developed to optimally maximize the quality of matching measured as a weighted score function of different recruitment metrics while determining the trajectory of each selected worker executing tasks. To cope with NP-hardness, we propose a heuristic SMCS recruitment approach allowing the achievement of sub-optimal matching and recruitment solution by iteratively solving a weighted bipartite graph problem. Simulation results illustrate the performance of the SMCS framework for selected scenarios and show that our proposed SMCS recruitment algorithm outperforms an existing greedy recruitment approach. Moreover, compared to the optimal MILP solution, the proposed SMCS recruitment approach achieves close results with significant computational time saving.

show abstract

A Stochastic Team Formation Approach for Collaborative Mobile Crowdsourcing

Cited by 11 publications

References 9 publications

THF: 3-Way Hierarchical Framework for Efficient Client Selection and Resource Management in Federated Learning

THF: 3-Way Hierarchical Framework for Efficient Client Selection and Resource Management in Federated Learning

Low Complexity Recruitment for Collaborative Mobile Crowdsourcing Using Graph Neural Networks

Many-to-Many Recruitment and Scheduling in Spatial Mobile Crowdsourcing

Contact Info

Product

Resources

About