activity
20162022
most citedFedSynth: Gradient Compression via Synthetic Data in Federated Learning

18 citations · 25 across the 5 of their papers we have counts for

collaborators

7 papers

cs.LG202218 cited

FedSynth: Gradient Compression via Synthetic Data in Federated Learning

Shengyuan Hu, Jack Goetz, Kshitiz Malik +3

Model compression is important in federated learning (FL) with large models to reduce communication cost. Prior works have been focusing on sparsification based compression that co…

cs.CL20213 cited

AutoNLU: Detecting, root-causing, and fixing NLU model errors

Pooja Sethi, Denis Savenkov, Forough Arabshahi +6

Improving the quality of Natural Language Understanding (NLU) models, and more specifically, task-oriented semantic parsing models, in production is a cumbersome task. In this work…

cs.CV20211 cited

Beyond Visual Attractiveness: Physically Plausible Single Image HDR Reconstruction for Spherical Panoramas

Wei Wei, Li Guan, Yue Liu +4

HDR reconstruction is an important task in computer vision with many industrial needs. The traditional approaches merge multiple exposure shots to generate HDRs that correspond to…

cs.LG20203 cited

Stable Prediction via Leveraging Seed Variable

Kun Kuang, Bo Li, Peng Cui +4

In this paper, we focus on the problem of stable prediction across unknown test data, where the test distribution is agnostic and might be totally different from the training one.…

cs.LG2020

Risk Variance Penalization

Chuanlong Xie, Haotian Ye, Fei Chen +3

The key of the out-of-distribution (OOD) generalization is to generalize invariance from training domains to target domains. The variance risk extrapolation (V-REx) is a practical…

cs.LG2019

Causal Discovery by Kernel Intrinsic Invariance Measure

Zhitang Chen, Shengyu Zhu, Yue Liu +1

Reasoning based on causality, instead of association has been considered as a key ingredient towards real machine intelligence. However, it is a challenging task to infer causal re…