相关论文: iDML: Incentivized Decentralized Machine Learning

Collaborative machine learning (CML) provides a promising paradigm for democratizing advanced technologies by enabling cost-sharing among participants. However, the potential for rent-seeking behaviors among parties can undermine such…

Incentive mechanism is crucial for federated learning (FL) when rational clients do not have the same interests in the global model as the server. However, due to system heterogeneity and limited budget, it is generally impractical for the…

The widespread adoption of smartphones and smart wearable devices has led to the widespread use of Centralized Federated Learning (CFL) for training powerful machine learning models while preserving data privacy. However, CFL faces…

We present models that utilize smart contracts and interledger mechanisms to provide decentralized authorization for constrained IoT devices. The models involve different tradeoffs in terms of cost, delay, complexity, and privacy, while…

Blockchain is considered the critical backbone technology for secure and trusted Internet of Things (IoT) in the future 6G network. However, deploying a blockchain system in a complex wireless IoT network is challenging due to the limited…

The integration of machine learning with blockchain technology has witnessed increasing interest, driven by the vision of decentralized, secure, and transparent AI services. In this context, we introduce opML (Optimistic Machine Learning on…

Federated learning (FL) enables collaborative training of a shared model on edge devices while maintaining data privacy. FL is effective when dealing with independent and identically distributed (iid) datasets, but struggles with non-iid…

Decentralized learning is widely employed for collaboratively training models using distributed data over wireless networks. Existing decentralized learning methods primarily focus on training single-modal networks. For the decentralized…

Recent advances in decentralized deep learning algorithms have demonstrated cutting-edge performance on various tasks with large pre-trained models. However, a pivotal prerequisite for achieving this level of competitiveness is the…

Wider coverage and a better solution to a latency reduction in 5G necessitate its combination with multi-access edge computing (MEC) technology. Decentralized deep learning (DDL) such as federated learning and swarm learning as a promising…

Blockchain has attracted broad interests to build decentralised applications. Blockchain has attracted broad interests to build decentralised applications. However, developing such applications without introducing vulnerabilities is hard…

We consider the problem of decentralized deep learning where multiple agents collaborate to learn from a distributed dataset. While there exist several decentralized deep learning approaches, the majority consider a central parameter-server…

The advent of Federated Learning (FL) has ignited a new paradigm for parallel and confidential decentralized Machine Learning (ML) with the potential of utilizing the computational power of a vast number of IoT, mobile and edge devices…

In the era of big data, large-scale machine learning models have revolutionized various fields, driving significant advancements. However, large-scale model training demands high financial and computational resources, which are only…

Motivated by the explosive computing capabilities at end user equipments, as well as the growing privacy concerns over sharing sensitive raw data, a new machine learning paradigm, named federated learning (FL) has emerged. By training…

In the realm of real-world devices, centralized servers in Federated Learning (FL) present challenges including communication bottlenecks and susceptibility to a single point of failure. Additionally, contemporary devices inherently exhibit…

An increasing number of applications rely on complex inference tasks that are based on machine learning (ML). Currently, there are two options to run such tasks: either they are served directly by the end device (e.g., smartphones, IoT…

Conventional machine learning (ML) relies heavily on manual design from machine learning experts to decide learning tasks, data, models, optimization algorithms, and evaluation metrics, which is labor-intensive, time-consuming, and cannot…

Federated learning (FL) is a popular technique for distributing machine learning (ML) across a set of edge devices. In this paper, we study fully decentralized FL, where in addition to devices conducting training locally, they carry out…

Recently, blockchain has gained momentum in the academic community thanks to its decentralization, immutability, transparency and security. As an emerging paradigm, Multi-access Edge Computing (MEC) has been widely used to provide…