More Like this

1. Peer-to-Peer Model-Agnostic Meta-Learning

   https://doi.org/10.1109/SAM60225.2024.10636527  

   Qureshi, Muhammad I; Khan, Usman A (July 2024, IEEE)
2. DiPLe: Learning Directed Collaboration Graphs for Peer-to-Peer Personalized Learning

   https://doi.org/10.1109/ITW54588.2022.9965838  

   Zheng, Xue; Naghizadeh, Parinaz; Yener, Aylin (November 2022, 2022 IEEE Information Theory Workshop (ITW))
3. How to learn collaboratively - Federated learning to peer-to-peer learning and what's at stake.

   Sharma, Atul; Zhao, Joshua; Chen, Wei; Qiu, Qiang; Bagchi, Saurabh; Chaterji, Somali (June 2023, 53rd Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN), “Disrupt 23: Disruptive Ideas and New Interdisciplinary Results” Track)

   Standard ML relies on training using a centrally collected dataset, while collaborative learning techniques such as Federated Learning (FL) enable data to remain decentralized at client locations. In FL, a central server coordinates the training process, reducing computation and communication expenses for clients. However, this centralization can lead to server congestion and heightened risk of malicious activity or data privacy breaches. In contrast, Peer-to-Peer Learning (P2PL) is a fully decentralized system where nodes manage both local training and aggregation tasks. While P2PL promotes privacy by eliminating the need to trust a single node, it also results in increased computation and communication costs, along with potential difficulties in achieving consensus among nodes. To address the limitations of both FL and P2PL, we propose a hybrid approach called Hubs-and-Spokes Learning (HSL). In HSL, hubs function similarly to FL servers, maintaining consensus but exerting less control over spokes. This paper argues that HSL’s design allows for greater availability and privacy than FL, while reducing computation and communication costs compared to P2PL. Additionally, HSL maintains consensus and integrity in the learning process. 

   more » « less
4. Peer-to-Peer Federated Continual Learning for Naturalistic Driving Action Recognition

   https://doi.org/10.1109/CVPRW59228.2023.00553  

   Yuan, Liangqi; Ma, Yunsheng; Su, Lu; Wang, Ziran (June 2023, The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops)
5. Poster: Brave: Byzantine-resilient and privacy-preserving peer-to-peer federated learning

   Xu, Z; Jiang, F; Niu, L; Jia, J; Li, Bo; Poovendran, Radha (July 2024, In Proceedings of the 19th ACM Asia Conference on Computer and Communications Security (pp. 1934-1936).)

   Federated learning (FL) enables multiple participants to train a global machine learning model without sharing their private training data. Peer-to-peer (P2P) FL advances existing centralized FL paradigms by eliminating the server that aggregates local models from participants and then updates the global model. However, P2P FL is vulnerable to (i) honest-but-curious participants whose objective is to infer private training data of other participants, and (ii) Byzantine participants who can transmit arbitrarily manipulated local models to corrupt the learning process. P2P FL schemes that simultaneously guarantee Byzantine resilience and preserve privacy have been less studied. In this paper, we develop Brave, a protocol that ensures Byzantine Resilience And priVacy-prEserving property for P2P FL in the presence of both types of adversaries. We show that Brave preserves privacy by establishing that any honest-but-curious adversary cannot infer other participants’ private data by observing their models. We further prove that Brave is Byzantine-resilient, which guarantees that all benign participants converge to an identical model that deviates from a global model trained without Byzantine adversaries by a bounded distance. We evaluate Brave against three state-of-the-art adversaries on a P2P FL for image classification tasks on benchmark datasets CIFAR10 and MNIST. Our results show that global models learned with Brave in the presence of adversaries achieve comparable classification accuracy to global models trained in the absence of any adversary. 

   more » « less