FLAME: Federated Learning Across Multi-device Environments

Abstract

Federated Learning (FL) enables distributed training of machine learning models while keeping personal data on user devices private. While we witness increasing applications of FL in the area of mobile sensing, such as human-activity recognition, FL has not been studied in the context of a multi-device environment (MDE), wherein each user owns multiple data-producing devices. With the proliferation of mobile and wearable devices, MDEs are increasingly becoming popular in ubicomp settings, therefore necessitating the study of FL in them. FL in MDEs is characterized by high non-IID-ness across clients, complicated by the presence of both user and device heterogeneities. Further, ensuring efficient utilization of system resources on FL clients in a MDE remains an important challenge. In this paper, we propose FLAME, a user-centered FL training approach to counter statistical and system heterogeneity in MDEs, and bring consistency in inference performance across devices. FLAME features (i) user-centered FL training utilizing the time alignment across devices from the same user; (ii) accuracy-and efficiency-aware device selection; and (iii) model personalization to devices. We also present an FL evaluation testbed with realistic energy drain and network bandwidth profiles, and a novel class-based data partitioning scheme to extend existing HAR datasets to a federated setup. Our experiment results on three multi-device HAR datasets show that FLAME outperforms various baselines by 4.8-33.8% higher 𝐹 1 score, 1.02-2.86× greater energy efficiency, and up to 2.02× speedup in convergence to target accuracy through fair distribution of the FL workload.CCS Concepts: • Human-centered computing → Ubiquitous and mobile computing systems and tools; • Computing methodologies → Cooperation and coordination.

SemiPFL: Personalized Semi-Supervised Federated Learning Framework for Edge Intelligence

“…delays [34], [41]- [43], b) heterogeneity in the distribution of data and labels [43]- [48], c) heterogeneity in the learning task [34], [41], [43], d) heterogeneity in learning models [29], [43], and e) heterogeneity in the number of devices per users [42]. To address this challenge, recent works aimed at developing a personalized model for each user [31], [32], [42], [43], [49], [50]. An overview of personalized federated learning models is illustrated in Fig.…”

“…IoT solutions face several challenges, including a) scarcity and heterogeneity of computational and storage resources on edge devices [9], [12], [42], b) heterogeneity of data on edge devices from distribution [33], [42], availability of labeled data, and c) the requirement for having a smaller and less complex model architecture [9], [33], [42]. The proposed SemiPFL aims at unifying semi-supervised learning with personalized federated learning for multi-sensory time-series edge inputs.…”

“…FedHealth 2 [31] measures users' similarities with the pretrained model and then aggregates all weighted models while users keep their batch normalization layer. Flame [42] focuses on a multi-device-environment (MDE), where each user can have multiple devices with different processing power. They propose personalized federated learning for scenarios where users can have sufficient labeled data on one of their edge devices.…”

Towards developing a data security aware federated training framework in multi-modal contested environments

“…Along with this, the investigation on the applicability of federated learning to different fields [16][17][18][19] has become an interesting research area. To note some of those, in the medical domain, a multi-modal approach to detect Covid-19 using the combination of information from X-ray and Ultrasound images is demonstrated in.…”

Confident federated learning to tackle label flipped data poisoning attacks

“…[3][4][5] With the rapid increase in computational capacity of edge devices [6][7][8] and advancements in efficient communication technologies with low power consumption, 9 FL is being applied nowadays in many fields. 10,11 The concept of federated machine learning involves collaborative machine learning model building across multiple workers while ensuring data privacy, where the raw data remains locally across numerous local devices. Despite recent progress in federated learning on privacy preservation, FL is still vulnerable to poisoning attacks, e.g., data poisoning attacks.…”