English
Related papers

Related papers: Gromov-Wasserstein Discrepancy with Local Differen…

200 papers

Federated learning (FL) allows to train a massive amount of data privately due to its decentralized structure. Stochastic gradient descent (SGD) is commonly used for FL due to its good empirical performance, but sensitive user information…

Machine Learning · Computer Science 2021-02-10 Muah Kim , Onur Günlü , Rafael F. Schaefer

The rapid growth of graph-structured data necessitates partitioning and distributed storage across decentralized systems, driving the emergence of federated graph learning to collaboratively train Graph Neural Networks (GNNs) without…

Machine Learning · Computer Science 2025-09-19 Linfeng Luo , Zhiqi Guo , Fengxiao Tang , Zihao Qiu , Ming Zhao

Analyzing data owned by several parties while achieving a good trade-off between utility and privacy is a key challenge in federated learning and analytics. In this work, we introduce a novel relaxation of local differential privacy (LDP)…

Machine Learning · Computer Science 2022-03-08 Edwige Cyffers , Aurélien Bellet

Privacy-preserving genomic data sharing is prominent to increase the pace of genomic research, and hence to pave the way towards personalized genomic medicine. In this paper, we introduce ($\epsilon , T$)-dependent local differential…

Cryptography and Security · Computer Science 2021-02-16 Emre Yilmaz , Tianxi Ji , Erman Ayday , Pan Li

We present a framework for embedding graph structured data into a vector space, taking into account node features and topology of a graph into the optimal transport (OT) problem. Then we propose a novel distance between two graphs, named…

Machine Learning · Computer Science 2023-07-04 Dai Hai Nguyen , Koji Tsuda

Local differential privacy (LDP) can provide each user with strong privacy guarantees under untrusted data curators while ensuring accurate statistics derived from privatized data. Due to its powerfulness, LDP has been widely adopted to…

Cryptography and Security · Computer Science 2019-06-06 Teng Wang , Jun Zhao , Xinyu Yang , Xuebin Ren

Graph neural networks (GNNs) achieve strong performance on relational data, but real-world graphs are often distributed across organizations that cannot share raw data due to privacy and policy constraints. Existing federated GNN methods…

Machine Learning · Computer Science 2026-05-27 Zhishuai Guo , Wenhan Wu , Chen Chen , Lei Zhang , Olivera Kotevska , Ravi K Madduri

Gromov--Wasserstein (GW) distances compare graphs, shapes, and point clouds through internal distances, without requiring a common coordinate system. This invariance is powerful, but discrete GW is a nonconvex quadratic optimal transport…

Machine Learning · Computer Science 2026-05-15 Ao Xu , Tieru Wu

Current practices for reporting the level of differential privacy (DP) protection for machine learning (ML) algorithms such as DP-SGD provide an incomplete and potentially misleading picture of the privacy guarantees. For instance, if only…

Machine Learning · Computer Science 2025-10-03 Juan Felipe Gomez , Bogdan Kulynych , Georgios Kaissis , Flavio P. Calmon , Jamie Hayes , Borja Balle , Antti Honkela

We consider the problem of generating private synthetic versions of real-world graphs containing private information while maintaining the utility of generated graphs. Differential privacy is a gold standard for data privacy, and the…

Machine Learning · Computer Science 2021-11-18 Xu Zheng , Nicholas McCarthy , Jer Hayes

Graph Neural Networks (GNNs) have established themselves as the state-of-the-art models for many machine learning applications such as the analysis of social networks, protein interactions and molecules. Several among these datasets contain…

The Gromov-Wasserstein (GW) distance enables comparing metric measure spaces based solely on their internal structure, making it invariant to isomorphic transformations. This property is particularly useful for comparing datasets that…

Statistics Theory · Mathematics 2024-10-24 Gabriel Rioux , Ziv Goldfeld , Kengo Kato

Developing machine learning methods that are privacy preserving is today a central topic of research, with huge practical impacts. Among the numerous ways to address privacy-preserving learning, we here take the perspective of computing the…

Machine Learning · Computer Science 2021-07-06 Alain Rakotomamonjy , Liva Ralaivola

Graphs offer unique insights into relationships between entities, complementing data modalities like text and images and enabling AI models to extend their capabilities beyond traditional tasks. However, learning from graphs often involves…

Machine Learning · Computer Science 2025-09-18 Haoteng Yin , Rongzhe Wei , Eli Chien , Pan Li

Tensor-valued data, increasingly common in distributed big data applications like autonomous driving and smart healthcare, poses unique challenges for privacy protection due to its multidimensional structure and the risk of losing critical…

Cryptography and Security · Computer Science 2025-09-12 Yachao Yuan , Xiao Tang , Yu Huang , Yingwen Wu , Jin Wang

Differential privacy has seen remarkable success as a rigorous and practical formalization of data privacy in the past decade. This privacy definition and its divergence based relaxations, however, have several acknowledged weaknesses,…

Machine Learning · Computer Science 2019-06-03 Jinshuo Dong , Aaron Roth , Weijie J. Su

Publishing graph statistics under node differential privacy has attracted much attention since it provides a stronger privacy guarantee than edge differential privacy. Existing works related to node differential privacy assume a trusted…

Cryptography and Security · Computer Science 2023-04-18 Shang Liu , Yang Cao , Takao Murakami , Masatoshi Yoshikawa

Graph convolutional networks (GCNs) are a powerful architecture for representation learning on documents that naturally occur as graphs, e.g., citation or social networks. However, sensitive personal information, such as documents with…

Social and Information Networks · Computer Science 2022-05-03 Timour Igamberdiev , Ivan Habernal

This paper presents a personalized graph federated learning (PGFL) framework in which distributedly connected servers and their respective edge devices collaboratively learn device or cluster-specific models while maintaining the privacy of…

Machine Learning · Computer Science 2023-10-31 Francois Gauthier , Vinay Chakravarthi Gogineni , Stefan Werner , Yih-Fang Huang , Anthony Kuh

Comparing structured data from possibly different metric-measure spaces is a fundamental task in machine learning, with applications in, e.g., graph classification. The Gromov-Wasserstein (GW) discrepancy formulates a coupling between the…

Machine Learning · Computer Science 2022-07-12 Hongwei Jin , Zishun Yu , Xinhua Zhang