Collaborative Mean Estimation over Intermittently Connected Networks
with Peer-To-Peer Privacy
- URL: http://arxiv.org/abs/2303.00035v1
- Date: Tue, 28 Feb 2023 19:17:03 GMT
- Title: Collaborative Mean Estimation over Intermittently Connected Networks
with Peer-To-Peer Privacy
- Authors: Rajarshi Saha, Mohamed Seif, Michal Yemini, Andrea J. Goldsmith, H.
Vincent Poor
- Abstract summary: This work considers the problem of Distributed Mean Estimation (DME) over networks with intermittent connectivity.
The goal is to learn a global statistic over the data samples localized across distributed nodes with the help of a central server.
We study the tradeoff between collaborative relaying and privacy leakage due to the additional data sharing among nodes.
- Score: 86.61829236732744
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: This work considers the problem of Distributed Mean Estimation (DME) over
networks with intermittent connectivity, where the goal is to learn a global
statistic over the data samples localized across distributed nodes with the
help of a central server. To mitigate the impact of intermittent links, nodes
can collaborate with their neighbors to compute local consensus which they
forward to the central server. In such a setup, the communications between any
pair of nodes must satisfy local differential privacy constraints. We study the
tradeoff between collaborative relaying and privacy leakage due to the
additional data sharing among nodes and, subsequently, propose a novel
differentially private collaborative algorithm for DME to achieve the optimal
tradeoff. Finally, we present numerical simulations to substantiate our
theoretical findings.
Related papers
- Networked Communication for Mean-Field Games with Function Approximation and Empirical Mean-Field Estimation [59.01527054553122]
Decentralised agents can learn equilibria in Mean-Field Games from a single, non-episodic run of the empirical system.
We introduce function approximation to the existing setting, drawing on the Munchausen Online Mirror Descent method.
We additionally provide new algorithms that allow agents to estimate the global empirical distribution based on a local neighbourhood.
arXiv Detail & Related papers (2024-08-21T13:32:46Z) - Privacy Preserving Semi-Decentralized Mean Estimation over Intermittently-Connected Networks [59.43433767253956]
We consider the problem of privately estimating the mean of vectors distributed across different nodes of an unreliable wireless network.
In a semi-decentralized setup, nodes can collaborate with their neighbors to compute a local consensus, which they relay to a central server.
We study the tradeoff between collaborative relaying and privacy leakage due to the data sharing among nodes.
arXiv Detail & Related papers (2024-06-06T06:12:15Z) - Generalizing Differentially Private Decentralized Deep Learning with Multi-Agent Consensus [11.414398732656839]
We propose a framework that embeds differential privacy into decentralized deep learning and secures each agent's local dataset during and after cooperative training.
We prove convergence guarantees for algorithms derived from this framework and demonstrate its practical utility when applied to subgradient and ADMM decentralized approaches.
arXiv Detail & Related papers (2023-06-24T07:46:00Z) - Distributed Learning over Networks with Graph-Attention-Based
Personalization [49.90052709285814]
We propose a graph-based personalized algorithm (GATTA) for distributed deep learning.
In particular, the personalized model in each agent is composed of a global part and a node-specific part.
By treating each agent as one node in a graph the node-specific parameters as its features, the benefits of the graph attention mechanism can be inherited.
arXiv Detail & Related papers (2023-05-22T13:48:30Z) - Attention Based Feature Fusion For Multi-Agent Collaborative Perception [4.120288148198388]
We propose an intermediate collaborative perception solution in the form of a graph attention network (GAT)
The proposed approach develops an attention-based aggregation strategy to fuse intermediate representations exchanged among multiple connected agents.
This approach adaptively highlights important regions in the intermediate feature maps at both the channel and spatial levels, resulting in improved object detection precision.
arXiv Detail & Related papers (2023-05-03T12:06:11Z) - Robust Federated Learning with Connectivity Failures: A
Semi-Decentralized Framework with Collaborative Relaying [27.120495678791883]
Intermittent client connectivity is one of the major challenges in centralized federated edge learning frameworks.
We propose a collaborative relaying based semi-decentralized federated edge learning framework.
arXiv Detail & Related papers (2022-02-24T01:06:42Z) - RelaySum for Decentralized Deep Learning on Heterogeneous Data [71.36228931225362]
In decentralized machine learning, workers compute model updates on their local data.
Because the workers only communicate with few neighbors without central coordination, these updates propagate progressively over the network.
This paradigm enables distributed training on networks without all-to-all connectivity, helping to protect data privacy as well as to reduce the communication cost of distributed training in data centers.
arXiv Detail & Related papers (2021-10-08T14:55:32Z) - Two-Bit Aggregation for Communication Efficient and Differentially
Private Federated Learning [79.66767935077925]
In federated learning (FL), a machine learning model is trained on multiple nodes in a decentralized manner, while keeping the data local and not shared with other nodes.
The information sent from the nodes to the server may reveal some details about each node's local data, thus raising privacy concerns.
A novel two-bit aggregation algorithm is proposed with guaranteed differential privacy and reduced uplink communication overhead.
arXiv Detail & Related papers (2021-10-06T19:03:58Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.