Data Collaboration Analysis Framework Using Centralization of Individual Intermediate Representations for Distributed Data Sets

TL;DR: VFL is a federated learning setting where multiple parties train machine learning models without exposing their raw data or model parameters. It involves a comprehensive review of concepts, advances, and challenges in VFL, including effectiveness, efficiency, privacy, and fairness.

TL;DR: In this paper, a non-model sharing-type collaborative learning method for distributed data analysis is proposed, in which data are partitioned in both samples and features, by centralizing the intermediate representations which are individually constructed in each party.

TL;DR: A novel VFL method, called Multi-View Federated Learning with Data collaboration (FedMC), is proposed to solve the problem of insufficient overlapping samples by exploiting suitable non-overlapping samples for data training and can improve the classification result.

TL;DR: This work explores an alternative federated learning system that enables integration of dimensionality reduced representations of distributed data prior to a supervised learning task, thus avoiding model sharing among the parties.

TL;DR: A generic approach to cancer classification based on gene expression monitoring by DNA microarrays is described and applied to human acute leukemias as a test case and suggests a general strategy for discovering and predicting cancer classes for other types of cancer, independent of previous biological knowledge.

TL;DR: This paper is concerned with the construction of planes of closest fit to systems of points in space and the relationships between these planes and the planes themselves.

TL;DR: This work presents a practical method for the federated learning of deep networks based on iterative model averaging, and conducts an extensive empirical evaluation, considering five different model architectures and four datasets.

TL;DR: Looking for competent reading resources?