FedE: Embedding Knowledge Graphs in Federated Setting

Chen, Mingyang; Zhang, Wen; Yuan, Zonggang; Jia, Yunyi; Chen, Huajun

doi:10.1145/3502223.3502233

Cited by 42 publications

(18 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Federated KGE and Privacy Protection. FedE [9] is proposed as the first federated KGE framework, which aggregates locally computed updates of entity embeddings to train a global model. FedR [50] aggregate relation embeddings instead of entity embeddings.…”

Section: A Score Functionsmentioning

confidence: 99%

Quantifying and Defending against Privacy Threats on Federated Knowledge Graph Embedding

Liang

Wu³

et al. 2023

Proceedings of the ACM Web Conference 2023

View full text Add to dashboard Cite

Knowledge Graph Embedding (KGE) is a fundamental technique that extracts expressive representation from knowledge graph (KG) to facilitate diverse downstream tasks. The emerging federated KGE (FKGE) collaboratively trains from distributed KGs held among clients while avoiding exchanging clients' sensitive raw KGs, which can still suffer from privacy threats as evidenced in other federated model trainings (e.g., neural networks). However, quantifying and defending against such privacy threats remain unexplored for FKGE which possesses unique properties not shared by previously studied models. In this paper, we conduct the first holistic study of the privacy threat on FKGE from both attack and defense perspectives. For the attack, we quantify the privacy threat by proposing three new inference attacks, which reveal substantial privacy risk by successfully inferring the existence of the KG triple from victim clients. For the defense, we propose DP-Flames, a novel differentially private FKGE with private selection, which offers a better privacy-utility tradeoff by exploiting the entity-binding sparse gradient property of FKGE and comes with a tight privacy accountant by incorporating the state-of-the-art private selection technique. We further propose an adaptive privacy budget allocation policy to dynamically adjust defense magnitude across the training procedure. Comprehensive evaluations demonstrate that the proposed defense can successfully mitigate the privacy threat by effectively reducing the success rate of inference attacks from 83.1% to 59.4% on average with only a modest utility decrease.

show abstract

Section: A Score Functionsmentioning

confidence: 99%

Quantifying and Defending against Privacy Threats on Federated Knowledge Graph Embedding

Liang

Wu³

et al. 2023

Proceedings of the ACM Web Conference 2023

View full text Add to dashboard Cite

show abstract

“…Decentralized graph data widely exist in multiple applications such as traffic flow prediction (Yuan et al, 2022), graph-level clustering (Caldarola et al, 2021), and node classification (Mei et al, 2019). A knowledge graph could contain text, images, and other types of data, such as multimodal knowledge graphs (M. Chen et al, 2021). Knowledge graphs can categorize these graphs into intergraph, and intra-graph (H. Zhang, Shen, et al, 2021).…”

Section: Graph Representationmentioning

confidence: 99%

Towards federated learning: An overview of methods and applications

Silva

Vinagre

Gama

2023

WIREs Data Min & Knowl

View full text Add to dashboard Cite

Federated learning (FL) is a collaborative, decentralized privacy-preserving method to attach the challenges of storing data and data privacy. Artificial intelligence, machine learning, smart devices, and deep learning have strongly marked the last years. Two challenges arose in data science as a result. First, the regulation protected the data by creating the General Data Protection Regulation, in which organizations are not allowed to keep or transfer data without the owner's authorization. Another challenge is the large volume of data generated in the era of big data, and keeping that data in one only server becomes increasingly tricky. Therefore, the data is allocated into different locations or generated by devices, creating the need to build models or perform calculations without transferring data to a single location. The new term FL emerged as a sub-area of machine learning that aims to solve the challenge of making distributed models with privacy considerations. This survey starts by describing relevant concepts, definitions, and methods, followed by an indepth investigation of federated model evaluation. Finally, we discuss three promising applications for further research: anomaly detection, distributed data streams, and graph representation.

show abstract

“…There are several works focusing on federated graph neural networks 9 , 39 , 40 , 41 , 42 , 43 , 44 and federated molecular-property prediction. 45 , 46 GraphFL applies MAML to improve the robustness of training.…”

Section: Related Workmentioning

confidence: 99%