78 citations · 84 across the 12 of their papers we have counts for
4 papers · 1 filter
Election Coding for Distributed Learning: Protecting SignSGD against Byzantine Attacks
Jy-yong Sohn, Dong-Jun Han, Beongjun Choi +1
Recent advances in large-scale distributed learning algorithms have enabled communication-efficient training via SignSGD. Unfortunately, a major issue continues to plague distribut…
TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning
Sung Whan Yoon, Jun Seo, Jaekyun Moon
Handling previously unseen tasks after given only a few training examples continues to be a tough challenge in machine learning. We propose TapNets, neural networks augmented with…
Coded Matrix Multiplication on a Group-Based Model
Muah Kim, Jy-yong Sohn, Jaekyun Moon
Coded distributed computing has been considered as a promising technique which makes large-scale systems robust to the "straggler" workers. Yet, practical system models for distrib…
Coded Distributed Computing over Packet Erasure Channels
Dong-Jun Han, Jy-yong Sohn, Jaekyun Moon
Coded computation is a framework which provides redundancy in distributed computing systems to speed up largescale tasks. Although most existing works assume an error-free scenario…