Article · 2022

“FedSynth: Gradient Compression via Synthetic Data in Federated Learning” (with Shengyuan Hu, Kshitiz Malik, Hongyuan Zhan, Zhe Liu & Yue Liu)

by Jack Goetz · Columbia College, Class of 2014

Publication

Title: “FedSynth: Gradient Compression via Synthetic Data in Federated Learning” (with Shengyuan Hu, Kshitiz Malik, Hongyuan Zhan, Zhe Liu & Yue Liu)
Author: Jack Goetz (Columbia College, Class of 2014)
Form: Article
First published: 2022
Publisher: arXiv/CoRR preprint

Complete works of Jack Goetz (6)

2017 “Online Multiclass Boosting” (with Young Hun Jung & Ambuj Tewari) · NIPS 2017 proceedings
2018 “Active Learning for Non-Parametric Regression Using Purely Random Trees” (with Ambuj Tewari & Paul M. Zimmerman) · NeurIPS 2018 proceedings
2019 “Active Federated Learning” (with Kshitiz Malik, Duc Bui, Seungwhan Moon, Honglei Liu & Anuj Kumar) · arXiv/NeurIPS federated-learning workshop
2020 “What Does the Machine Learn? Knowledge Representations of Chemical Reactivity” (with Joshua Kammeraad, Eric Walker, Ambuj Tewari & Paul M. Zimmerman) · Journal of Chemical Information and Modeling, 60(3)
2022 “FedSynth: Gradient Compression via Synthetic Data in Federated Learning” (with Shengyuan Hu, Kshitiz Malik, Hongyuan Zhan, Zhe Liu & Yue Liu) · arXiv/CoRR preprint this record
2023 “Towards Zero-Shot Frame Semantic Parsing with Task Agnostic Ontologies and Simple Labels” (with Danilo Neves Ribeiro et al.) · arXiv/CoRR preprint

Cite this record

Goetz, Jack. “FedSynth: Gradient Compression via Synthetic Data in Federated Learning” (with Shengyuan Hu, Kshitiz Malik, Hongyuan Zhan, Zhe Liu & Yue Liu). arXiv/CoRR preprint, 2022.

Foundation record: https://philolexianfoundation.org/members/goetz-jack-cc-2014/fedsynth-gradient-compression-via-synthetic-data-in-federated-learning-with-shen-2022.html