FedProto: Federated Prototype Learning across Heterogeneous Clients

Tan, Yue; Long, Guodong; Liu, Lu; Zhou, Tianyi; Lu, Qinghua; Jiang, Jing; Zhang, Chengqi

doi:10.1609/aaai.v36i8.20819

Cited by 256 publications

(102 citation statements)

References 23 publications

Supporting

Mentioning

102

Contrasting

Order By: Relevance

“…Herein, we empirically used the network that removed the last fully connected layer as the feature extractor [ 24 ].…”

Section: Methodsmentioning

confidence: 99%

“…Inspired by prototype learning, in which gathering the prototypes across heterogeneous datasets enables the incorporation of feature representations over various data distributions [ 24 , 25 ], we brought a global prototype

(

) aggregated across clients as consistent feature-level views to guide local training. We propose a new prototype guidance regularisation (PGReg) loss

as follows:

where

denotes the global prototype of the

-th category and

denotes the L2 distance.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

FedAAR: A Novel Federated Learning Framework for Animal Activity Recognition with Wearable Sensors

Mao

Huang

Gan

et al. 2022

Animals

View full text Add to dashboard Cite

Deep learning dominates automated animal activity recognition (AAR) tasks due to high performance on large-scale datasets. However, constructing centralised data across diverse farms raises data privacy issues. Federated learning (FL) provides a distributed learning solution to train a shared model by coordinating multiple farms (clients) without sharing their private data, whereas directly applying FL to AAR tasks often faces two challenges: client-drift during local training and local gradient conflicts during global aggregation. In this study, we develop a novel FL framework called FedAAR to achieve AAR with wearable sensors. Specifically, we devise a prototype-guided local update module to alleviate the client-drift issue, which introduces a global prototype as shared knowledge to force clients to learn consistent features. To reduce gradient conflicts between clients, we design a gradient-refinement-based aggregation module to eliminate conflicting components between local gradients during global aggregation, thereby improving agreement between clients. Experiments are conducted on a public dataset to verify FedAAR’s effectiveness, which consists of 87,621 two-second accelerometer and gyroscope data. The results demonstrate that FedAAR outperforms the state-of-the-art, on precision (75.23%), recall (75.17%), F1-score (74.70%), and accuracy (88.88%), respectively. The ablation experiments show FedAAR’s robustness against various factors (i.e., data sizes, communication frequency, and client numbers).

show abstract

“…Herein, we empirically used the network that removed the last fully connected layer as the feature extractor [ 24 ].…”

Section: Methodsmentioning

confidence: 99%

(

) aggregated across clients as consistent feature-level views to guide local training. We propose a new prototype guidance regularisation (PGReg) loss

as follows:

where

denotes the global prototype of the

-th category and

denotes the L2 distance.…”

Section: Methodsmentioning

confidence: 99%

FedAAR: A Novel Federated Learning Framework for Animal Activity Recognition with Wearable Sensors

Mao

Huang

Gan

et al. 2022

Animals

View full text Add to dashboard Cite

show abstract

“…FedAMP and HeurFedAMP [29] are novel attentive message passing mechanism to significantly facilitate the collaboration effectiveness between clients without infringing their data privacy which enables similar clients to have stronger collaboration than clients with dissimilar models, and this mechanism significantly improves the learning performance. In framework FedProto [30], the clients and server communicate the abstract class prototypes instead of the gradients, and aggregates the local prototypes collected from different clients, and then sends the global prototypes back to all clients to regularize the training of local models. The training on each client aims to minimize the classification error on the local data while keeping the resulting local prototypes sufficiently close to the corresponding global ones.…”

Section: Related Workmentioning

confidence: 99%

Personalized Federated Learning with Model Interpolation among Client Clusters and its Application in Smart Home

Yang

Liu

Zhang

et al. 2022

Preprint

View full text Add to dashboard Cite

The proliferation of high-performance personal devices and the widespread deployment of machine learning (ML) applications have led to two consequences: the volume of private data from individuals or groups has exploded over the past few years; and the traditional central servers for training ML models have experienced communication and performance bottlenecks in the face of massive amounts of data. However, this reality also provides the possibility of keeping data local for ML training and fusing models on a broader scale. As a new branch of ML application, Federated Learning (FL) aims to solve the problem of multi-party joint learning on the premise of protecting personal data privacy. However, due to the heterogeneity of devices, including network connection, network bandwidth, computing resources, etc., it is unrealistic to train, update and aggregate models in all devices in parallel, while personal data is often not independent and identically distributed (Non-IID) due to multiple reasons. This reality poses a challenge to the speed and convergence of FL. In this paper, we propose the pFedCAM algorithm, which aims to improve the robustness of the FL system to device heterogeneity and Non-IID data, while achieving some degree of federation model personalization. pFedCAM is based on the idea of clustering and model interpolation by classifying heterogeneous clients and performing FedAvg algorithm in parallel, and then combining them into personalized federated global models by inter-cluster model interpolation. Experiments show that the accuracy of pFedCAM improves 10.3% on Fashion-MNIST and 11.3% on CIFAR-10 compared to the benchmark in the case of Non-IID data. In the end, we applied pFedCAM to HomeProtect, a smart home privacy protection framework we designed, and achieved good practical results in the case of flame recognition.

show abstract

“…subgraph [32]). Graph contrastive learning also benefits diverse applications, such as chemical prediction [47], anomaly detection [18,24], federated learning [36,56], and recommendation [54]. However, it still remains unclear how to effectively improve GSL using contrastive learning.…”

Section: Contrastive Learning On Graphsmentioning

confidence: 99%

Dual Space Graph Contrastive Learning

Yang

Chen

Pan

et al. 2022

Proceedings of the ACM Web Conference 2022

View full text Add to dashboard Cite

In recent years, graph neural networks (GNNs) have emerged as a successful tool in a variety of graph-related applications. However, the performance of GNNs can be deteriorated when noisy connections occur in the original graph structures; besides, the dependence on explicit structures prevents GNNs from being applied to general unstructured scenarios. To address these issues, recently emerged deep graph structure learning (GSL) methods propose to jointly optimize the graph structure along with GNN under the supervision of a node classification task. Nonetheless, these methods focus on a supervised learning scenario, which leads to several problems, i.e., the reliance on labels, the bias of edge distribution, and the limitation on application tasks. In this paper, we propose a more practical GSL paradigm, unsupervised graph structure learning, where the learned graph topology is optimized by data itself without any external guidance (i.e., labels). To solve the unsupervised GSL problem, we propose a novel StrUcture Bootstrapping contrastive LearnIng fraMEwork (SUBLIME for abbreviation) with the aid of self-supervised contrastive learning. Specifically, we generate a learning target from the original data as an "anchor graph", and use a contrastive loss to maximize the agreement between the anchor graph and the learned graph. To provide persistent guidance, we design a novel bootstrapping mechanism that upgrades the anchor graph with learned structures during model learning. We also design a series of graph learners and post-processing schemes to model the structures to learn. Extensive experiments on eight benchmark datasets demonstrate the significant effectiveness of our proposed SUBLIME and high quality of the optimized graphs. CCS CONCEPTS• Mathematics of computing → Graph algorithms; • Computing methodologies → Neural networks.

show abstract

FedProto: Federated Prototype Learning across Heterogeneous Clients

Cited by 256 publications

References 23 publications

FedAAR: A Novel Federated Learning Framework for Animal Activity Recognition with Wearable Sensors

FedAAR: A Novel Federated Learning Framework for Animal Activity Recognition with Wearable Sensors

Personalized Federated Learning with Model Interpolation among Client Clusters and its Application in Smart Home

Dual Space Graph Contrastive Learning

Contact Info

Product

Resources

About