activity
20152020
most citedLearn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting

79 citations · 119 across the 6 of their papers we have counts for

collaborators

14 papers

cs.LG2020

Online Structured Meta-learning

Huaxiu Yao, Yingbo Zhou, Mehrdad Mahdavi +3

Learning quickly is of great importance for machine intelligence deployed in online platforms. With the capability of transferring knowledge from learned tasks, meta-learning has s…

cs.CL2020

CoCo: Controllable Counterfactuals for Evaluating Dialogue State Trackers

Shiyang Li, Semih Yavuz, Kazuma Hashimoto +6

Dialogue state trackers have made significant progress on benchmark datasets, but their generalization capability to novel and realistic scenarios beyond the held-out conversations…

cs.LG2020

Representation Learning for Sequence Data with Deep Autoencoding Predictive Components

Junwen Bai, Weiran Wang, Yingbo Zhou +1

We propose Deep Autoencoding Predictive Components (DAPC) -- a self-supervised representation learning method for sequence data, based on the intuition that useful representations…

cs.CL202013 cited

Fast and Robust Unsupervised Contextual Biasing for Speech Recognition

Young Mo Kang, Yingbo Zhou

Automatic speech recognition (ASR) system is becoming a ubiquitous technology. Although its accuracy is closing the gap with that of human level under certain settings, one area th…

cs.LG20207 cited

Differentially Private Deep Learning with Smooth Sensitivity

Lichao Sun, Yingbo Zhou, Philip S. Yu +1

Ensuring the privacy of sensitive data used to train modern machine learning models is of paramount importance in many areas of practice. One approach to study these concerns is th…

cs.CR2019

Private Deep Learning with Teacher Ensembles

Lichao Sun, Yingbo Zhou, Ji Wang +4

Privacy-preserving deep learning is crucial for deploying deep neural network based solutions, especially when the model works on data that contains sensitive information. Most pri…