Reward Allocation Research Articles

FedFAIM: A Model Performance-Based Fair Incentive Mechanism for Federated Learning

Federated Learning (FL) has emerged as a privacy-preserving distributed machine learning paradigm. To motivate data owners to contribute towards FL, research on FL incentive mechanisms is gaining great interest. Existing monetary incentive mechanisms generally share the same FL model with all participants regardless of their contributions. Such an assumption can be unfair towards participants who contributed more and promote undesirable free-riding, especially when the final model is of great utility value to participants. In this paper, we propose a Fairness-Aware Incentive Mechanism for federated learning (FedFAIM) to address such problem. It satisfies two types of fairness notion: 1) aggregation fairness, which determines aggregation results according to data quality; 2) reward fairness, which assigns each participant a unique model with performance reflecting his contribution. Aggregation fairness is achieved through efficient gradient aggregation which examines local gradient quality and aggregates them based on data quality. Reward fairness is achieved through an efficient Shapley value-based contribution assessment method and a novel reward allocation method based on reputation and distribution of local and global gradients. We further prove reward fairness is theoretically guaranteed. Extensive experiments show that FedFAIM provides stronger incentives than similar non-monetary FL incentive mechanisms while achieving a high level of fairness.

Predictive air combat decision model with segmented reward allocation

In air combat missions, unmanned combat aerial vehicles (UCAVs) must take strategic actions to establish combat advantages, enabling effective tracking and attacking of enemy UCAVs. Currently, a lot of reinforcement learning algorithms are applied to the air combat mission of unmanned fighter aircraft. However, most algorithms can only select policies based on the current state of both sides. This leads to the inability to effectively track and attack when the enemy performs large angle maneuvering. Additionally, these algorithms cannot adapt to different situations, resulting in the unmanned fighter aircraft being at a disadvantage in some cases. To solve these problems, this paper proposes predictive air combat decision model with segmented reward allocation for air combat tracking and attacking. On the basis of the air combat environment, we propose the prediction soft actor-critic (Pre-SAC) algorithm, which combines the prediction of enemy states with the states of UCAV for model training. This enables the UCAV to predict the next move of the enemy UCAV in advance and establish a greater air combat advantage for us. Furthermore, by adopting a segmented reward allocation model and combining it with the Pre-SAC algorithm, we propose the segmented reward allocation soft actor-critic (Sra-SAC) algorithm, which solves the problem of UCAVs being unable to adapt to different situations. The results show that the prediction-based segmented reward allocation the Sra-SAC algorithm outperforms the traditional soft actor-critic (SAC) algorithm in terms of overall reward, travel distance, and relative advantage.

INFLUTRUST: Trust-Based Influencer Marketing Campaigns in Online Social Networks

This paper introduces the INFLUTRUST framework that is designed to address challenges in trust-based influencer marketing campaigns on Online Social Networks (OSNs). The INFLUTRUST framework enables the influencers to autonomously select products across the OSN platforms for advertisement by employing a reinforcement learning algorithm. The Stochastic Learning Automata reinforcement algorithm considers the OSN platforms’ provided monetary rewards, the influencers’ advertising profit, and the influencers’ trust levels towards the OSN platforms to enable the influencers to autonomously select an OSN platform. The trust model for the influencers incorporates direct and indirect trust, which are derived from past interactions and social ties among the influencers and the OSN platforms, respectively. The OSN platforms allocate rewards through a multilateral bargaining model that supports competition among the influencers. Simulation-based results validate the INFLUTRUST framework’s effectiveness across diverse scenarios, with the scalability analysis demonstrating its robustness. Comparative evaluations highlight the INFLUTRUST framework’s superiority in considering trust levels and reward allocation fairness, benefiting both the influencers and the OSN platforms.

Status positions and scientific Capital in Russian Science

The paper addresses scientific capital distribution and describes status positions of scientists in the field of modern Russian science. Inequalities in science are associated with a variety of factors including gender, wealth, symbolic and moral authority etc. However, technological development has emphasized the significance of new inequality forms based on digital and networking skills. An important question is how these new inequality factors change the field of science. The theoretical and methodological framework of the paper is based on the ideas of R. Merton on the differentiated allocation of rewards, as well as the provisions of P. Bourdieu on dominance in the field of science and on the types of scientific capital. The authors present the result of an online survey of Russian scientists (N=551), the aim of which was to identify the gaps and contradictions within the field of Russian science. To differentiate between the status positions of scientists the authors constructed an integral index of scientific status, according to which all the scientists were divided into three categories with low, medium and high status positions. Empirical data show that there is a contradiction between the scientific dominance based on formal status, and the one based on the production of advanced scientific knowledge. Formal characteristics of the scientific status do not fully reflect subjective perception of the return on the accumulated scientific capital. It is suggested that the elimination of contradictions by means of science policies may contribute to the development of Russian science.

Exploring Data Analytics in Attendance Systems: Unveiling Machine Learning Techniques, Patterns, Practices, and Emerging Trends

Purpose: The research aims to identify patterns and trends in attendance management through the application of reward and punishment systems as innovative solutions for improving employee attendance and well-being. Methods: This research utilizes a descriptive analysis approach with the application of Machine Learning (ML) techniques to enhance the accuracy of attendance pattern prediction and ML models for the classification of emerging trends and patterns. Research data were obtained through the company's attendance system and divided into two segments (80% for training and 20% for testing) while maintaining a balanced class proportion, then processed using SPSS and Python software with the Scikit-learn library. Result: The results of the study show that employee attendance is increased from 86.52% to 90.44% when the reward and punishment method is applied to the employee attendance system. Proper reward allocation can increase employee motivation to adhere to work schedules and consistently attend, while punishment tends to lead to lower attendance rates. Novelty: This research emphasizes the optimization of attendance management through data analytics approaches and the implementation of advanced technology in attendance systems with the application of ML techniques to analyze attendance data comprehensively and detect significant patterns.

Empathetic Influence: Charting a Course for Employee Well-being Through Leadership in the Service Sector

This study explores a crucial role of empathy in leadership style, focusing its impact on employee wellbeing. Through a comprehensive analysis it aims to inform leadership practices to develop a positive workforce environment, enhancing the overall organizational wellbeing. Empathetic leadership involves the understanding follower’s emotions and taking proactive caring actions, the leadership style works with the mediation of distributive justice that create a perception of fair and equal allocation of resources and rewards in organization. Such leadership style promotes positive relationships, enhanced teamwork and contribute in organizational productivity. Empathetic leaders possess skills that are crucial for adapting global trends and creating supporting work environment, particularly in adapting organizational change. Employee wellbeing is crucial for organizational success, which is significantly influenced by empathetic leadership with the perception of distributive justice, resulting in higher job satisfaction, organizational commitment and overall enhanced work environment.

CTDS: Centralized Teacher With Decentralized Student for Multiagent Reinforcement Learning

Due to the partial observability and communication constraints in many multi-agent reinforcement learning (MARL) tasks, centralized training with decentralized execution (CTDE) has become one of the most widely used MARL paradigms. In CTDE, centralized information is dedicated to learning the allocation of the team reward with a mixing network, while the learning of individual Q-values is usually based on local observations. The insufficient utility of global observation will degrade performance in challenging environments. To this end, this work proposes a novel Centralized Teacher with Decentralized Student (CTDS) framework, which consists of a teacher model and a student model. Specifically, the teacher model allocates the team reward by learning individual Q-values conditioned on global observation, while the student model utilizes the partial observations to approximate the Q-values estimated by the teacher model. In this way, CTDS balances the full utilization of global observation during training and the feasibility of decentralized execution for online inference. Our CTDS framework is generic which is ready to be applied upon existing CTDE methods to boost their performance. We conduct experiments on a challenging set of StarCraft II micromanagement tasks to test the effectiveness of our method and the results show that CTDS outperforms the existing value-based MARL methods.

Data privacy protection model based on blockchain in mobile edge computing

AbstractMobile edge computing (MEC) technology is widely used for real‐time and bandwidth‐intensive services, but its underlying heterogeneous architecture may lead to a variety of security and privacy issues. Blockchain provides novel solutions for data security and privacy protection in MEC. However, the scalability of traditional blockchain is difficult to meet the requirements of real‐time data processing, and the consensus mechanism is not suitable for resource‐constrained devices. Moreover, the access control of MEC data needs to be further improved. Given the above problems, a data privacy protection model based on sharding blockchain and access control is designed in this paper. First, a privacy‐preserving platform based on a sharding blockchain is designed. Reputation calculation and improved Proof‐of‐Work (PoW) consensus mechanism are proposed to accommodate resource‐constrained edge devices. The incentive mechanism with rewards and punishments is designed to constrain node behavior. A reward allocation algorithm is proposed to encourage nodes to actively contribute to obtaining more rewards. Second, an access control strategy using ciphertext policy attribute‐based encryption (CP‐ABE) and RSA is designed. A smart contract is deployed to implement the automatic access control function. The InterPlanetary File System is introduced to alleviate the blockchain storage burden. Finally, we analyze the security of the proposed privacy protection model and statistics of the GAS consumed by the access control policy. The experimental results show that the proposed data privacy protection model achieves fine‐grained control of access rights, and has higher throughput and security than traditional blockchain.

FedAVE: Adaptive data value evaluation framework for collaborative fairness in federated learning

Collaborative fairness in federated learning rewards high-contribution clients with high-performance models when multiple clients train a machine learning model cooperatively. Existing approaches ignore the information on data distribution when evaluating the clients’ data quality, resulting in a mismatch between the reward allocation and the real data quality of clients under different data heterogeneity settings. To address this problem, we propose a novel Federated learning framework with Adaptive data Value Evaluation mechanism (FedAVE) to ensure collaborative fairness without affecting the predictive performance of models. First, an adaptive reputation calculation module is designed to generate reputations that match the clients’ contributions based on the information of their data distribution, respectively. Second, a dynamic gradient reward distribution module is devised to allocate a certain number of aggregated model parameter updates/gradients as the rewards corresponding to the reputations and the data distribution information. Extensive experiments on three public benchmarks show that the proposed FedAVE outperforms all baseline methods in terms of fairness, and achieves comparable performance to the state-of-the-art methods in terms of accuracy. Code available at https://github.com/wangzihuixmu/FedAVE.

Fair Least Core: Efficient, Stable and Unique Game-Theoretic Reward Allocation in Energy Communities by Row-Generation

Fair Least Core: Efficient, Stable and Unique Game-Theoretic Reward Allocation in Energy Communities by Row-Generation

A cross-level study on the impact of team-based reward allocation on employees' innovative behavior in manufacturing enterprises

A cross-level study on the impact of team-based reward allocation on employees' innovative behavior in manufacturing enterprises

Collaborative Target Search With a Visual Drone Swarm: An Adaptive Curriculum Embedded Multistage Reinforcement Learning Approach.

Equipping drones with target search capabilities is highly desirable for applications in disaster rescue and smart warehouse delivery systems. Multiple intelligent drones that can collaborate with each other and maneuver among obstacles show more effectiveness in accomplishing tasks in a shorter amount of time. However, carrying out collaborative target search (CTS) without prior target information is extremely challenging, especially with a visual drone swarm. In this work, we propose a novel data-efficient deep reinforcement learning (DRL) approach called adaptive curriculum embedded multistage learning (ACEMSL) to address these challenges, mainly 3-D sparse reward space exploration with limited visual perception and collaborative behavior requirements. Specifically, we decompose the CTS task into several subtasks including individual obstacle avoidance, target search, and inter-agent collaboration, and progressively train the agents with multistage learning. Meanwhile, an adaptive embedded curriculum (AEC) is designed, where the task difficulty level (TDL) can be adaptively adjusted based on the success rate (SR) achieved in training. ACEMSL allows data-efficient training and individual-team reward allocation for the visual drone swarm. Furthermore, we deploy the trained model over a real visual drone swarm and perform CTS operations without fine-tuning. Extensive simulations and real-world flight tests validate the effectiveness and generalizability of ACEMSL. The project is available at https://github.com/NTU-UAVG/CTS-visual-drone-swarm.git.

Dollar or percentage? The effect of reward presentation on referral likelihood

PurposeAddressing the significant differences between referral programs and traditional promotional marketing, this paper aims to investigate and examine the impact of how reward-related information is presented within referral programs and how it interacts with reward size and reward allocation.Design/methodology/approachThis study adopts framing effect and equity theory to build the relationship between reward presentation, reward size and reward allocation. Then, two scenario-based experimental studies are designed and conducted on Amazon Mechanical Turk.FindingsThe results show that there is no direct impact of reward presentation on referral likelihood, while the effect relies on reward size. As the levels of reward size increase, the referral likelihood gradually shifts from percentage form to dollar form as perceived size mediates the interaction effect on referral likelihood. Further, adding information about reward allocation also indicate the different impacts of equity and inequity on influencing the above findings.Originality/valueThe study contributes to the literature by introducing reward presentation and emphasizes its impact on individual’s behavior decisions in the context of referral programs. This study extends and broadens the scope and effectiveness of the framing effect on traditional promotional marketing strategies, while also bridging the gap in the literature by examining the combined role of information about rewards.

The effect of competition on children's merit-based resource allocation: The difference between interpersonal and intergroup competition.

Competition usually exists in groups in everyday interactions, but how children allocate according to competition outcomes (e.g., merit-based allocation) after intergroup competition and the difference in children's allocations of rewards between interpersonal and intergroup competition remain unclear. Children aged 3-8 years were asked to complete interpersonal or intergroup competitive games and were further asked to allocate rewards between themselves and their partners (Study 1) or between their group and the other group (Studies 2 and 3) and to reason about their decisions. We found that after interpersonal competition, children tended to conduct merit-based allocations when they won but were more inclined to conduct equal allocations when they lost; after intergroup competition, children were more inclined to make equal allocations regardless of whether they won or lost, only less than half of children followed meritorious principles. However, children conducted more merit-based allocations with age after both interpersonal and intergroup competitions. In addition, children showed less bias towards their own side after intergroup competition than after interpersonal competition. Finally, they demonstrated an earlier proclivity towards being influenced by winning outcomes than by losing outcomes after interpersonal competition, whereas a converse tendency was found after intergroup competition.

A Cooperative PoW and Incentive Mechanism for Blockchain in Edge Computing

More and more works use blockchain to improve the data security of integrated edge computing and Internet of Things (IoT) system. However, there are some problems of Proof-of-Work (PoW) that hinder the application, such as high energy consumption, low resource utilization efficiency and insufficient incentive. In this paper, we present a cooperative PoW named relay mining based PoW (Relay-PoW) to reduce energy consumption and improve resource utilization efficiency, where the nodes can mine blocks together under the management of edge server. We further propose parallel relay mining method to increase the throughput, where the nodes can mine blocks with multiple heights in a pipeline manner. In addition, we design supervision group mechanism to ensure the security, where the edge server evaluates the trust values of the nodes according to the capability and quality, and eliminates abnormal nodes timely. Finally, we propose a Shapley-based reward allocation strategy (SRAS) to encourage node to participate in Relay-PoW. Experimental results show that Relay-PoW can effectively decrease the energy consumption, improve the throughput and resource utilization efficiency, SRAS can motivate nodes to cooperate, and they all have a better performance than other methods.

Attachment, stress and interactional justice

PurposeThis paper aims to examine how individuals' attachment dispositions relate to interactional justice perceptions, how work stressors moderate this association, and how together they associate with attitudes (satisfaction, turnover intention, commitment) and citizenship behaviors at work.Design/methodology/approachSurvey data were used in an observed variable path analysis examining mediation by interactional justice and moderation by stressors on the associations between attachment dimensions and work outcomes.FindingsAttachment avoidance was negatively related to interactional justice perceptions and attachment anxiety was also negatively related to interactional justice perceptions, but only under conditions of higher work stressors. Interactional justice mediated the associations between attachment avoidance and work outcomes, and between the interaction of attachment anxiety and work stressors on work outcomes.Practical implicationsThese findings are particularly relevant to multiple aspects of HR practice, including performance feedback, managing stressors, building resilience, reward allocation and recognition, designing wellness programs and other aspects of human resource management.Originality/valueThis research goes beyond contextual predictors of justice perceptions and demonstrates that jointly considering attachment dimensions and work stressors uniquely contributes to understanding the formation of justice perceptions and their combined influence on work attitudes and behavior.

Blockchain-Aided Edge Computing Market: Smart Contract and Consensus Mechanisms

Building upon the concept of edge computing (EC), a distributed EC market requires decentralized and verified transaction management to trade computing resources. Towards this goal, we study a blockchain-aided EC market wherein each data service operator (DSO) rents a group of edge computing nodes (ECNs) and leases the ECNs to the user terminals (UTs) to provide computation offloading services. First, we propose a smart contract based matching mechanism to establish the renting association between the DSOs and ECNs with the aim of maximizing the social welfare. Second, we propose a social welfare improved double auction (SWIDA) mechanism to build up the leasing association between the DSOs and UTs, and show that the proposed mechanism can achieve individual rationality, balanced budget, truthfulness in expectation, and an improved social welfare than the benchmark mechanisms. Moreover, we put forth a trustworthiness-driven Proof-of-Stake (PoS) consensus mechanism to enable verified transaction and fair reward allocation. We formulate the block generation as a coalitional game, wherein each stakeholder votes according to its trustworthiness and coinage, and shares the reward among the coalition according to the Shapley values. The simulation results show that the proposed PoS consensus mechanism can reduce the wealth inequality among the network entities.

Creation of a Holistic Platform for Health Boosting Using a Blockchain-Based Approach: Development Study

Low adherence to healthy habits, which is associated with a higher risk of disease and death, among citizens of Organization for Economic Co-operation and Development countries is a serious concern. The World Health Organization (WHO) and the physical activity (PA) guidelines for Americans provide recommendations on PA and healthy diets. To promote these habits, we suggest using a blockchain-based platform, using the PA Messaging Framework to deliver messages and rewards to users. Blockchain is a decentralized secure platform for data management, which can be used for value-added controls and services such as smart contracts (SCs), oracles, and decentralized applications (dApps). Of note, there is a substantial penetration of blockchain technologies in the field of PA, but there is a need for more implementations of dApps to take advantage of features such as nonfungible tokens. This study aimed to create a comprehensive platform for promoting healthy habits, using scientific evidence and blockchain technology. The platform will use gamification to encourage healthy PA and eating habits; in addition, it will monitor the activities through noninvasive means, evaluate them using open-source software, and follow up through blockchain messages. A literature search was conducted on the use of blockchain technology in the field of PA and healthy eating. On the basis of the results of this search, it is possible to define an innovative platform for promoting and monitoring healthy habits through health-related challenges on a dApp. Contact with the user will be maintained through messages following a proposed model in the literature to improve adherence to the challenges. The proposed strategy is based on a dApp that relies on blockchain technology. The challenges include PA and healthy eating habits based on the recommendations of the WHO and the Food and Agriculture Organization. The system is constituted of a blockchain network where challenge-related achievements are stored and verified using SCs. The user interacts with the system through a dApp that runs on their local device, monitors the challenge, and self-authenticates by providing their public and private keys. The SC verifies challenge fulfillment and generates messages, and the information stored in the network can be used to encourage competition among participants. The ultimate goal is to create a habit of healthy activities through rewards and peer competition. The use of blockchain technology has the potential to improve people's quality of life through the development of relevant services. In this work, strategies using gamification and blockchain are proposed for monitoring healthy activities, with a focus on transparency and reward allocation. The results are promising, but compliance with the General Data Protection Regulation is still a concern. Personal data are stored on personal devices, whereas challenge data are recorded on the blockchain.

Study on population behavior under home quarantine policies of COVID-19 in China based on double-layer network evolutionary games

In the practice of COVID-19 prevention and control in China, the home quarantine policy directly connects and manages the residents, which plays a significant role in preventing the spread of the epi-demic in the community. We evaluate the effectiveness of current home quarantine policy in the actual execution process based on the evolutionary game relationship between the community and res-idents. This paper establishes a double-layer coupled complex network game model, and uses the multi-agent modeling method to study the game relationship between the community and residents in the context of home quarantine policies. The results show that initial strategy of the community with strict supervision and reasonable government reward allocation will increase the proportion of the residents complying with the quarantine rule. When 80% of the communities chose to supervise strictly at the beginning, people are more likely to follow the rules. While when the residents can only get 20% of the government’s reward, the proportion of choosing to violate the quarantine rules is much higher than that when they can get 80% of the reward. Besides, the structure of small-world network and environmental noise will also affect the residents’ strategy. As the probability of reconnection of the small-world network rises from 0.2 to 0.8, the proportion of residents who choose to comply with the strategy becomes much higher. When the environmental noise reaches 0.5, the ratio of residents who choose to violate the strategy is higher than the ratio of complianc. The study is helpful to provide the basis for the government to formulate the quarantine policy and propose an optimization for making effective quarantine measures. In this way, the government can adjust the parameters to make residents achieve the possible level of compliance with quarantine policies as high as possible to contain the spread of the epidemic.

Tree Representation, Growth Rate of Blockchain and Reward Allocation in Ethereum With Multiple Mining Pools

It is interesting but difficult and challenging to study Ethereum with multiple mining pools. One of the main difficulties comes from not only how to represent such a general tree with multiple block branches (or sub-chains) related to the multiple mining pools, but also how to analyze a multi-dimensional stochastic system due to the mining competition among the multiple mining pools. In this paper, we first set up a mathematical representation for the tree with multiple block branches. Then we provide a block classification of Ethereum: Regular blocks (in the main chain), orphan blocks, uncle blocks, stale blocks, and nephew blocks, and give some key ratios and probabilities of generating the different types of blocks by applying the law of large numbers. Based on this, we further discuss the growth rate of blockchain and the reward allocation among the multiple mining pools through applying the renewal reward theorem. Finally, we use some simulation experiments to verify our theoretical results, and show that the approximate computation approaches developed, such as the key ratios and probabilities, the long-term growth rate of blockchain, and the long-term reward allocation (rate) among the multiple mining pools, can have a faster convergence. Therefore, we provide a powerful tool for observing and understanding the influence of the selfish mining attacks on the performance of Ethereum with multiple mining pools. We believe that the methodology and results developed in this paper will shed light on the study of Ethereum with multiple mining pools, such that a series of promising research can be inspired potentially.