Online training data acquisition for federated learning in cloud–edge networks

Zhu, Konglin; Chen, Wentao; Jiao, Lei; Wang, Jiaxing; Peng, Yuyang; Zhang, Lin

doi:10.1016/j.comnet.2023.109556

Cited by 6 publications

(5 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several other works study content creator competition under different modelling assumptions: e.g., where content quality is fixed and all creator actions are gaming [Milli et al, 2023b], where content creators have fixed content but may dynamically leave the platform over time [Mladenov et al, 2020, Ben-Porat and Torkan, 2023, Huttenlocher et al, 2024, where the recommendation algorithm biases affect market concentration but content creators have fixed content [Calvano et al, 2023, Castellini et al, 2023, where the platform designs a contract determining payments and recommendations [Zhu et al, 2023], where the platform creates its own content [Aridor and Gonçalves, 2021], and where the platform designs badges to incentivize user-generated content [Immorlica et al, 2015]. This line of work also builds on Hotelling models of product selection from economics (e.g.…”

Section: Related Workmentioning

confidence: 99%

Designing Approximately Optimal Search on Matching Platforms

et al. 2023

View full text Add to dashboard Cite

We study the design of a decentralized two-sided matching market in which agents’ search is guided by the platform. There are finitely many agent types, each with (potentially random) preferences drawn from known type-specific distributions. Equipped with knowledge of these distributions, the platform guides the search process by determining the meeting rate between each pair of types from the two sides. Focusing on symmetric pairwise preferences in a continuum model, we first characterize the unique stationary equilibrium that arises given a feasible set of meeting rates. We then introduce the platform’s optimal directed search problem, which involves optimizing meeting rates to maximize equilibrium social welfare. We first show that incentive issues arising from congestion and cannibalization make the design problem fairly intricate. Nonetheless, we develop an efficiently computable search design whose corresponding equilibrium achieves at least [Formula: see text] the social welfare of the optimal design. In fact, our construction always recovers at least [Formula: see text] the first-best social welfare, where agents’ incentives are disregarded. Our search design is simple and easy to implement, as its corresponding bipartite graph consists of disjoint stars. Furthermore, our design implies the platform can substantially limit choice and yet induce an equilibrium with approximately optimal welfare. We offer alternative search designs with improved approximation factors for markets with certain special structures. Finally, we show that approximation is likely the best one can hope for by establishing that the problem of designing optimal directed search is [Formula: see text]-hard to even approximate beyond a certain constant factor. This paper was accepted by Omar Besbes, revenue management and market analytics. Supplemental Material: The online appendix is available at https://doi.org/10.1287/mnsc.2022.4601 .

show abstract

Section: Related Workmentioning

confidence: 99%

Designing Approximately Optimal Search on Matching Platforms

et al. 2023

View full text Add to dashboard Cite

show abstract

“…(2) Prover Node P Generates Evidence Process In the consensus of the first-level main chain of the industrial internet, the first-level nodes of each industry not only generate evidence as prover nodes but also serve as verifier nodes to verify evidence during the verification. Each prover node (18), where the calculation formula (A j , B j , C j ) is shown in ( 19)- (21). Each node calls the Producer API as a prover to send the specified Topic information, and the specified partition function sends the evidence generated by each node to different Broker proxy nodes with n − 1 pieces for each group.…”

Section: Design Of Main Chain Consensus Algorithm Based On Zero-knowl...mentioning

confidence: 99%

“…Considering that the management of the industrial internet identify resolution data faces many problems, such as complex types, large amounts of information, wide range, rapid growth, and reduced security [21,22], this study proposes a trusted management model of the industrial internet identify resolution data based on blockchain multi-chain, which provides a common model for the industrial internet across industries on the whole, which divides sub-chains of different industries. In this way, data autonomy across industries can be realized while data from different industries can be isolated.…”

Section: Introductionmentioning

confidence: 99%

Research on Trusted Management of Industrial Internet Identity Analysis Data Based on Blockchain

Qi,

Huang,

Zhang

et al. 2023

Symmetry

View full text Add to dashboard Cite

As an important part of the industrial internet, identity analysis data are growing with the expansion of the field involved in the industrial internet. The management of industrial internet identity analysis data faces many problems, such as complex types, a wide range of information, rapid growth, reduced security, etc. In view of the above problems, a trusted management model of industrial internet identity analysis data based on blockchain is first designed. Meanwhile, the identity analysis data information is analyzed and classified, and industrial data are divided into three levels according to the degree of privacy for hierarchical encryption. Secondly, the “on-chain + off-chain” storage model combining the blockchain main-slave chain and the off-chain database is designed to improve the efficiency of the whole model. Then, a collaborative consensus mechanism suitable for the main-slave multi-chain of the industrial internet is also designed, including slave-chain CIPBFT consensus, inter-chain cross-chain transmission protocol and main chain KZKP consensus. Finally, a prototype system is built to analyze the correctness, security, scalability and consensus efficiency of the model proposed in this study. The results show that the model proposed in this study can be applied to trusted management of data information for industrial internet identity analysis, and also provides an optimized solution for the same problem in fields of the industrial internet.

show abstract

“…Recently, autonomous vehicles have been applied for transporting ore at mining sites [1][2][3]. The aim is to improve productivity by decreasing labor costs and accidents and increasing working time.…”

Section: Introductionmentioning

confidence: 99%

A Secure Trajectory Planning Method for Connected Autonomous Vehicles at Mining Site

Li,

Chen

et al. 2023

Symmetry

View full text Add to dashboard Cite

Recently, with the assistance of 5G networks and the Internet of Things, specialized applications of autonomous driving to mining sites have been explored, with the goal of realizing the unmanned operation of mining systems and enhancing the safety of the mining industry. After receiving the loading task, the autonomous driving system will generate a feasible trajectory for the mining truck. It requires that the trajectory be generated in advanced within a limited-time high-latency network. In addition, the secure trajectory planning for mining sites involves factors in the complex environment and an unstable network. Thus, a secure trajectory planning method for autonomous trucks at mining sites is proposed. It simplifies the planning by decoupling the planning into front-end path searching and back-end trajectory generation. First, the planner enhances the Hybrid A* search algorithm to find the hauling path within the boundary of the mining site, and then, it post-processes the path with a well-designed symmetric optimization-based method. Then, considering the interaction with other autonomous trucks, a topology-guided search method for secure decision making is proposed, considering the possibility of cybersecurity. The proposed method was validated in real scenarios of the mining environment. The results verify that the planner can generate the secure trajectory under network delay 2.0 s conditions.

show abstract

Online training data acquisition for federated learning in cloud–edge networks

Cited by 6 publications

References 25 publications

Designing Approximately Optimal Search on Matching Platforms

Designing Approximately Optimal Search on Matching Platforms

Research on Trusted Management of Industrial Internet Identity Analysis Data Based on Blockchain

A Secure Trajectory Planning Method for Connected Autonomous Vehicles at Mining Site

Contact Info

Product

Resources

About