Year: 2019
Type: conference-paper
Abstract: We consider unreliable distributed learning systems wherein the training data is kept confidential by external workers, and the learner has to interact closely with those workers to train a model. In particular, we assume that there exists a system adversary that can adaptively compromise some workers; the compromised workers deviate from their local designed specifications by sending out arbitrarily malicious messages.
Authors: Lili Su, Jiaming Xu
Institutions: Massachusetts Institute of Technology, Duke University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
Funder: National Science Foundation
Awards: G1513559549, CRII: CIF: Learning Hidden Structures in Networks: Fundamental Limits and Efficient Algorithms, Emerging Frontiers of Science of Information, BIGDATA: F: Collaborative Research: Mining for Patterns in Graphs and High-Dimensional Data: Achieving the Limits, CIF: Medium: Collaborative Research: Learning in Networks: Performance Limits and Algorithms
OpenAlex ID: W2940527161
