Federated Graph Machine Learning

Fu, Xingbo; Zhang, Binchi; Dong, Yushun; Chen, Chen; Li, Jundong

doi:10.1145/3575637.3575644

Cited by 34 publications

(9 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unfortunately, DL is data-hungry: larger and larger DL models require more and more data to be trained, and data pooling data is often needed to build an appropriate dataset. Pooling increases the model generalizability 26,27 , i.e. the ability of a model to deal with unseen data reliably 28 .…”

Section: Federated Learning In the Bio-medical Fieldmentioning

confidence: 99%

MiFL: Multi-Input Neural Networks in Federated Learning

Casella¹,

Riviera²,

Aldinucci³

et al. 2023

Preprint

View full text Add to dashboard Cite

<p>Driven by the Deep Learning (DL) revolution, Artificial intelligence (AI) has become a fundamental tool for many Bio-Medical tasks, including AI-assisted diagnosis. These include analysing and classifying images (2D and 3D), where, for some tasks, DL exhibits superhuman performance. Diagnostic imaging, however, is not the only diagnostic tool. Tabular data, such as personal data, vital signs, and genomic/blood tests, are commonly collected for every patient entering a clinical institution. However, it is rarely considered in DL pipelines, although it carries diagnostic information. The training of DL models requires large datasets, so large that every institution might need more data that should be pooled from different sites. Data pooling generates newfound concerns about data access and movement across other institutions spawning multiple dimensions, such as performance, energy efficiency, privacy, criticality, and security. Federated Learning (FL) is a cooperative learning paradigm aiming at addressing these concerns by moving models instead of data across different institutions. This paper proposes a Federated multi-input model that leverages images and tabular data, providing a proof of concept of the feasibility of multi-input FL architectures. The proposed model was evaluated on two showcases: the prognosis of CoViD-19 disease and the patients’ stratification for Alzheimer’s disease. Results show that enabling multi-input architectures in the FL framework allows for improving the performance regarding both accuracy and generalizability with respect to non-federated models while ensuring security and data protection peculiar to FL.</p>

show abstract

Section: Federated Learning In the Bio-medical Fieldmentioning

confidence: 99%

MiFL: Multi-Input Neural Networks in Federated Learning

Casella¹,

Riviera²,

Aldinucci³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Federated Learning (FL) enables multiple clients to collaboratively train a model without exchanging the local data explicitly [16,22,30,48,59,64]. As a classic example, FedAvg [36] performs stochastic gradient descent (SGD) on each client to update model parameters and send them to the server.…”

Section: Federated Learningmentioning

confidence: 99%

Federated Few-shot Learning

Wang

Ding

et al. 2023

Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

Self Cite

View full text Add to dashboard Cite

Federated Learning (FL) enables multiple clients to collaboratively learn a machine learning model without exchanging their own local data. In this way, the server can exploit the computational power of all clients and train the model on a larger set of data samples among all clients. Although such a mechanism is proven to be effective in various fields, existing works generally assume that each client preserves sufficient data for training. In practice, however, certain clients may only contain a limited number of samples (i.e., few-shot samples). For example, the available photo data taken by a specific user with a new mobile device is relatively rare. In this scenario, existing FL efforts typically encounter a significant performance drop on these clients. Therefore, it is urgent to develop a few-shot model that can generalize to clients with limited data under the FL scenario. In this paper, we refer to this novel problem as federated few-shot learning. Nevertheless, the problem remains challenging due to two major reasons: the global data variance among clients (i.e., the difference in data distributions among clients) and the local data insufficiency in each client (i.e., the lack of adequate local data for training). To overcome these two challenges, we propose a novel federated few-shot learning framework with two separately updated models and dedicated training strategies to reduce the adverse impact of global data variance and local data insufficiency. Extensive experiments on four prevalent datasets that cover news articles and images validate the effectiveness of our framework compared with the state-of-the-art baselines. Our code is provided 1 . CCS CONCEPTS• Computing methodologies → Distributed algorithms.

show abstract

“…With its powerful spatial graph structure, Graph Neural Network helps various industries deeply explore the value of their own data. GNN obtains dependencies in the graph by capturing the message passing mechanism and aggregation method between adjacent nodes in the graph structure, and converts it into standardized complete node embedding information and rich data information Fu et al [4], Liu et al [5].…”

Section: Introductionmentioning

confidence: 99%

Personalized and privacy-preserving federated graph neural network

Liu,

Li,

Hao

2024

Front. Phys.

View full text Add to dashboard Cite

High-performance GNN obtains dependencies within a graph by capturing the mechanism of message passing and aggregation between neighboring nodes in the graph, and successfully updates node embeddings. However, in practical applications, the inherent model structure of the graph is highly susceptible to privacy attacks, and the heterogeneity of external data can lead to a decrease in model performance. Motivated by this challenge, this work proposes a novel framework called Personalized Federated Graph Neural Network for Privacy-Preserving (PFGNN). Specifically, firstly, this work introduces a graph similarity strategy. Based on the principle that clients with similar features exhibit stronger homophily, this work divides all participating clients into multiple clusters for collaborative training. Furthermore, within each group, this work employs an attention mechanism to design a federated aggregation weighting scheme. This scheme is used to construct a global model on the server, which helps mitigate the difficulty of model generalization resulting from data heterogeneity collected from different clients. Lastly, to ensure the privacy of model parameters during the training process and prevent malicious adversaries from stealing them, this work implements privacy-enhancing technology by introducing an optimized function-hiding multi-input function encryption scheme. This ensures the security of both model data and user privacy. Experiments on real datasets show that our scheme outperforms FedAvg in accuracy, and the communication overhead is linearly related to the number of clients. Through this framework, PFGNN can handle all kinds of non-Euclidean structured data, multiple clients collaborate to train high-quality and highly secure global models. This work provides the foundation for designing efficient and privacy-preserving personalized federated graph neural networks.

show abstract

Federated Graph Machine Learning

Cited by 34 publications

References 49 publications

MiFL: Multi-Input Neural Networks in Federated Learning

MiFL: Multi-Input Neural Networks in Federated Learning

Federated Few-shot Learning

Personalized and privacy-preserving federated graph neural network

Contact Info

Product

Resources

About