Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userCentral Server Free Federated Learning over Single-sided Trust Social Networks
65
0
0.0
(
0
)
Added by
Chaoyang He
Publication date
2019
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Federated learning has become increasingly important for modern machine learning, especially for data privacy-sensitive scenarios. Existing federated learning mostly adopts the central server-based architecture or centralized architecture. However, in many social network scenarios, centralized federated learning is not applicable (e.g., a central agent or server connecting all users may not exist, or the communication cost to the central server is not affordable). In this paper, we consider a generic setting: 1) the central server may not exist, and 2) the social network is unidirectional or of single-sided trust (i.e., user A trusts user B but user B may not trust user A). We propose a central server free federated learning algorithm, named Online Push-Sum (OPS) method, to handle this challenging but generic scenario. A rigorous regret analysis is also provided, which shows very interesting results on how users can benefit from communication with trusted users in the federated learning scenario. This work builds upon the fundamental algorithm framework and theoretical guarantees for federated learning in the generic social network scenario.
rate research
Read More
Federated learning allows distributed devices to collectively train a model without sharing or disclosing the local dataset with a central server. The global model is optimized by training and averaging the model parameters of all local participants. However, the improved privacy of federated learning also introduces challenges including higher computation and communication costs. In particular, federated learning converges slower than centralized training. We propose the server averaging algorithm to accelerate convergence. Sever averaging constructs the shared global model by periodically averaging a set of previous global models. Our experiments indicate that server averaging not only converges faster, to a target accuracy, than federated averaging (FedAvg), but also reduces the computation costs on the client-level through epoch decay.
In federated learning (FL), reducing the communication overhead is one of the most critical challenges since the parameter server and the mobile devices share the training parameters over wireless links. With such consideration, we adopt the idea of SignSGD in which only the signs of the gradients are exchanged. Moreover, most of the existing works assume Channel State Information (CSI) available at both the mobile devices and the parameter server, and thus the mobile devices can adopt fixed transmission rates dictated by the channel capacity. In this work, only the parameter server side CSI is assumed, and channel capacity with outage is considered. In this case, an essential problem for the mobile devices is to select appropriate local processing and communication parameters (including the transmission rates) to achieve a desired balance between the overall learning performance and their energy consumption. Two optimization problems are formulated and solved, which optimize the learning performance given the energy consumption requirement, and vice versa. Furthermore, considering that the data may be distributed across the mobile devices in a highly uneven fashion in FL, a stochastic sign-based algorithm is proposed. Extensive simulations are performed to demonstrate the effectiveness of the proposed methods.
This paper formulates and studies a novel algorithm for federated learning from large collections of local datasets. This algorithm capitalizes on an intrinsic network structure that relates the local datasets via an undirected empirical graph. We model such big data over networks using a networked linear regression model. Each local dataset has individual regression weights. The weights of close-knit sub-collections of local datasets are enforced to deviate only little. This lends naturally to a network Lasso problem which we solve using a primal-dual method. We obtain a distributed federated learning algorithm via a message passing implementation of this primal-dual method. We provide a detailed analysis of the statistical and computational properties of the resulting federated learning algorithm.
Federated learning (FL) was proposed to achieve collaborative machine learning among various clients without uploading private data. However, due to model aggregation strategies, existing frameworks require strict model homogeneity, limiting the application in more complicated scenarios. Besides, the communication cost of FLs model and gradient transmission is extremely high. This paper proposes Loosely Coupled Federated Learning (LC-FL), a framework using generative models as transmission media to achieve low communication cost and heterogeneous federated learning. LC-FL can be applied on scenarios where clients possess different kinds of machine learning models. Experiments on real-world datasets covering different multiparty scenarios demonstrate the effectiveness of our proposal.
Social networks have become ubiquitous in our daily life, as such it has attracted great research interests recently. A key challenge is that it is of extremely large-scale with tremendous information flow, creating the phenomenon of Big Data. Under such a circumstance, understanding information diffusion over social networks has become an important research issue. Most of the existing works on information diffusion analysis are based on either network structure modeling or empirical approach with dataset mining. However, the information diffusion is also heavily influenced by network users decisions, actions and their socio-economic connections, which is generally ignored in existing works. In this paper, we propose an evolutionary game theoretic framework to model the dynamic information diffusion process in social networks. Specifically, we analyze the framework in uniform degree and non-uniform degree networks and derive the closed-form expressions of the evolutionary stable network states. Moreover, the information diffusion over two special networks, ErdH{o}s-Renyi random network and the Barabasi-Albert scale-free network, are also highlighted. To verify our theoretical analysis, we conduct experiments by using both synthetic networks and real-world Facebook network, as well as real-world information spreading dataset of Twitter and Memetracker. Experiments shows that the proposed game theoretic framework is effective and practical in modeling the social network users information forwarding behaviors.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
