Incentive Mechanism Design for Resource Sharing in Collaborative Edge Learning
Alibaba Group（阿里巴巴集团）；Alibaba-NTU Joint Research Institute (JRI)（阿里巴巴-南洋理工大学联合研究院（JRI））；Nanyang Technological University (NTU)（南洋理工大学（NTU））；The University of British Columbia（不列颠哥伦比亚大学）；Hong Kong University of Science and Technology（香港科技大学）
Wei Yang Bryan Lim, Jer Shyuan Ng, Zehui Xiong, Dusit Niyato, Cyril Leung, Chunyan Miao, Qiang Yang
In 5G and Beyond networks, Artificial Intelligence applications are expected to be increasingly ubiquitous. This necessitates a paradigm shift from the current cloud-centric model training approach to the Edge Computing based collaborative learning scheme known as edge learning, in which model training is executed at the edge of the network. In this article, we first introduce the principles and technologies of collaborative edge learning. Then, we establish that a successful, scalable implementation of edge learning requires the communication, caching, computation, and learning resources (3C-L) of end devices and edge servers to be leveraged jointly in an efficient manner. However, users may not consent to contribute their resources without receiving adequate compensation. In consideration of the heterogeneity of edge nodes, e.g., in terms of available computation resources, we discuss the challenges of incentive mechanism design to facilitate resource sharing for edge learning. Furthermore, we present a case study involving optimal auction design using Deep Learning to price fresh data contributed for edge learning. The performance evaluation shows the revenue maximizing properties of our proposed auction over the benchmark schemes.
This document is an Internet Appendix of paper entitled "Sequential Bargaining Based Incentive Mechanism for Collaborative Internet Access". It includes information about LTE signal metrics, results of idle state experiments, and linear regression assumptions of the models presented in the related paper.
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Peng Cheng Laboratory（鹏城实验室）
As an effective learning paradigm against insufficient training samples, Multi-Task Learning (MTL) encourages knowledge sharing across multiple related tasks so as to improve the overall performance. In MTL, a major challenge springs from the phenomenon that sharing the knowledge with dissimilar and hard tasks, known as negative transfer, often results in a worsened performance. Though a substantial amount of studies have been carried out against the negative transfer, most of the existing methods only model the transfer relationship as task correlations, with the transfer across features and …
Alibaba Group（阿里巴巴集团）；Beijing Institute of Technology（北京理工大学）；Weill Cornell Medicine（威尔康奈尔医学院）
In this paper, we focus on learning effective entity matching models over multi-source large-scale data. For real applications, we relax typical assumptions that data distributions/spaces, or entity identities are shared between sources, and propose a Relaxed Multi-source Large-scale Entity-matching (RMLE) problem. Challenges of the problem include 1) how to align large-scale entities between sources to share information and 2) how to mitigate negative transfer from joint learning multi-source data. What's worse, one practical issue is the entanglement between both challenges. Specifically, in…
Peer-to-peer protocols play an increasingly instrumental role in Internet content distribution. Consequently, it is important to gain a full understanding of how these protocols behave in practice and how their parameters impact overall performance. We present the first experimental investigation of the peer selection strategy of the popular BitTorrent protocol in an instrumented private torrent. By observing the decisions of more than 40 nodes, we validate three BitTorrent properties that, though widely believed to hold, have not been demonstrated experimentally. These include the clustering …
User-generated content can be distributed at a low cost using peer-to-peer (P2P) networks, but the free-rider problem hinders the utilization of P2P networks. In order to achieve an efficient use of P2P networks, we investigate fundamental issues on incentives in content production and sharing using game theory. We build a basic model to analyze non-cooperative outcomes without an incentive scheme and then use different game formulations derived from the basic model to examine five incentive schemes: cooperative, payment, repeated interaction, intervention, and enforced full sharing. The resul…
Peer-to-peer (p2p) networks are not independent of their peers, and the network efficiency depends on peers contributing resources. Because shared resources are not free, this contribution must be rewarded. Peers across the network may share computation power, storage capacity, and bandwidth. This paper looks at how bandwidth incentive encourages peers to share bandwidth and rewards them for their contribution. With the advent of blockchain technology, many p2p networks attempt to reward contributions by crypto-assets. We conduct simulations to better understand current incentive mechanisms, a…
We study the interaction between network effects and external incentives on file sharing behavior in Peer-to-Peer (P2P) networks. Many current or envisioned P2P networks reward individuals for sharing files, via financial incentives or social recognition. Peers weigh this reward against the cost of sharing incurred when others download the shared file. As a result, if other nearby nodes share files as well, the cost to an individual node decreases. Such positive network sharing effects can be expected to increase the rate of peers who share files. In this paper, we formulate a natural model fo…
Peer-to-peer protocols play an increasingly instrumental role in Internet content distribution. It is therefore important to gain a complete understanding of how these protocols behave in practice and how their operating parameters affect overall system performance. This paper presents the first detailed experimental investigation of the peer selection strategy in the popular BitTorrent protocol. By observing more than 40 nodes in instrumented private torrents, we validate three protocol properties that, though believed to hold, have not been previously demonstrated experimentally: the cluster…
Although sharing data across organizations is often advocated as a promising way to enhance cybersecurity, collaborative initiatives are rarely put into practice owing to confidentiality, trust, and liability challenges. In this paper, we investigate whether collaborative threat mitigation can be realized via a controlled data sharing approach, whereby organizations make informed decisions as to whether or not, and how much, to share. Using appropriate cryptographic tools, entities can estimate the benefits of collaboration and agree on what to share in a privacy-preserving way, without having…
With the fast expanding scale of vehicular networks, vehicular edge computing (VEC) has emerged and attracted growing attention from both industry and academia. Parked vehicles (PVs) have great potential to join vehicular networks for sharing their idle computing and networking resources. However, due to the underlying security and privacy threats, it is challenging to fairly motivate PVs for resource sharing in an efficient and secure way. In this paper, we propose a permissioned vehicular blockchain for secure and efficient resource sharing in VEC, namely, Parkingchain. We first design smart…
Interconnecting multiple sensor networks is a relatively new research field which has emerged in the Wireless Sensor Network domain. Wireless Sensor Networks (WSNs) have typically been seen as logically separate, and few works have considered interconnection and interaction between them. Interconnecting multiple heterogeneous sensor networks therefore opens up a new field besides more traditional research on, e.g., routing, self organization, or MAC layer development. Up to now, some approaches have been proposed for interconnecting multiple sensor networks with goals like information sharing …
Cloud computing has been a dominant paradigm for a variety of information processing platforms, particularly for enabling various popular applications of sharing economy. However, there is a major concern regarding data privacy on these cloud-based platforms. This work presents novel cloud-based privacy-preserving solutions to support collaborative consumption applications for sharing economy. In typical collaborative consumption, information processing platforms need to enable fair cost-sharing among multiple users for utilizing certain shared facilities and communal services. Our cloud-based…
Mobile peer-to-peer networks are quite prevalent and popular now days due to advent of business scenarios where all the services are going mobile like whether it's to find good restaurants, healthy diet books making friends, job-hunting, real state info or cab-sharing etc. As the mobile users are increasing day by day, peer-to-peer networks getting bigger and complex. In contrast to client server system in peer-to-peer network resource sharing is done on the basis of mutual consent and agreed policies with no central authority and controlling entity. Incentive schemes for P2P networks are devi…
The rise of fast communication media both at the core and at the edge has resulted in unprecedented numbers of sophisticated and intelligent wireless IoT devices. Tactile Internet has enabled the interaction between humans and machines within their environment to achieve revolutionized solutions both on the move and in real-time. Many applications such as intelligent autonomous self-driving, smart agriculture and industrial solutions, and self-learning multimedia content filtering and sharing have become attainable through cooperative, distributed and decentralized systems, namely, volunteer c…
With the rapid growth of sensor technology, smartphone sensing has become an effective approach to improve the quality of smartphone applications. However, due to time-varying wireless channels and lack of incentives for the users to participate, the quality and quantity of the data uploaded by the smartphone users are not always satisfying. In this paper, we consider a smartphone sensing system in which a platform publicizes multiple tasks, and the smartphone users choose a set of tasks to participate in. In the traditional non-cooperative approach with incentives, each smartphone user gets r…
Honeypot technologies provide an effective defense strategy for the Industrial Internet of Things (IIoT), particularly in enhancing the Advanced Metering Infrastructure's (AMI) security by bolstering the network intrusion detection system. For this security paradigm to be fully realized, it necessitates the active participation of small-scale power suppliers (SPSs) in implementing honeypots and engaging in collaborative data sharing with traditional power retailers (TPRs). To motivate this interaction, TPRs incentivize data sharing with tangible rewards. However, without access to an SPS's con…
To balance the load and to discourage the free-riding in peer-to-peer (P2P) networks, many incentive mechanisms and policies have been proposed in recent years. Global peer ranking is one such mechanism. In this mechanism, peers are ranked based on a metric called contribution index. Contribution index is defined in such a manner that peers are motivated to share the resources in the network. Fairness in the terms of upload to download ratio in each peer can be achieved by this method. However, calculation of contribution index is not trivial. It is computed distributively and iteratively in t…
Computation offloading via device-to-device (D2D) communication, or D2D offloading, has recently been proposed to enhance mobile computing performance by exploiting spare computing resources of nearby user devices. The success of D2D offloading relies on user participation in collaborative service provisioning, which incurs extra costs to users providing the service, thus mandating an incentive mechanism that can compensate for these costs. Although incentive mechanism design has been intensively studied in the literature, this paper considers a much more challenging yet less investigated prob…
The base motivation of Mobile Cloud Computing was empowering mobile devices by application offloading onto powerful cloud resources. However, this goal can't entirely be reached because of the high offloading cost imposed by the long physical distance between the mobile device and the cloud. To address this issue, we propose an application offloading onto a nearby mobile cloud composed of the mobile devices in the vicinity-a Spontaneous Proximity Cloud. We introduce our proposed dynamic, ant-inspired, bi-objective offloading middleware-ACOMMA, and explain its extension to perform a close mobil…
We consider a group of neighboring smartphone users who are roughly at the same time interested in the same network content, called common interests. However, ever-increasing data traffic challenges the limited capacity of base-stations (BSs) in wireless networks. To better utilize the limited BSs' resources under unreliable wireless networks, we propose local common-interests sharing (enabled by D2D communications) by motivating the physically neighboring users to form a social group. As users are selfish in practice, an incentive mechanism is needed to motivate social grouping. We propose a …
Crowd sensing is a new paradigm that leverages pervasive sensor-equipped mobile devices to provide sensing services like forensic analysis, documenting public spaces, and collaboratively constructing statistical models. Extensive user participation is indispensable for achieving good service quality. Nowadays, most of existing mechanisms focus on guaranteeing good service quality based on instantaneous extensive user participation for crowd sensing applications. Little attention has been dedicated to maximizing long-term service quality for crowd sensing applications due to their asymmetric in…
This article proposes a self-organizing collaborative computing network with an approach to enhance the expectation of a collaborating node for joining the self-organizing network. The proposed approach relies on Ethereum cryptocurrency and Smart Contract to enhance the expectation of collaborating nodes by monetizing the services provided to the self-organizing network. Furthermore, an escrow based smart contract is formalized in the proposed framework to sustains the monetary trust issue between collaborating nodes. The proposed scheme can enforce an autonomic incentive management mechanism …
