Home /
Research
Showing 439 - 444 / 904
Gradient Starvation: A Learning Proclivity in Neural Networks
MohammadPezeshki, Sékou-OumarKaba, YoshuaBengio....
Published date-11/18/2020
We identify and formalize a fundamental gradient descent phenomenon resulting in a learning proclivity in over-parameterized neural networks. Gradient Starvation arises when cross-entropy loss is minimized by capturing only a …
FixBi: Bridging Domain Spaces for Unsupervised Domain Adaptation
JaeminNa, HeechulJung, HyungJinChang....
Published date-11/18/2020
DomainAdaptation, UnsupervisedDomainAdaptation
Unsupervised domain adaptation (UDA) methods for learning domain invariant representations have achieved remarkable progress. However, few studies have been conducted on the case of large domain discrepancies between a source …
Distributed Scheduling using Graph Neural Networks
ZhongyuanZhao, GunjanVerma, ChiragRao....
Published date-11/18/2020
A fundamental problem in the design of wireless networks is to efficiently schedule transmission in a distributed manner. The main challenge stems from the fact that optimal link scheduling involves …
Adaptive Contention Window Design using Deep Q-learning
AbhishekKumar, GunjanVerma, ChiragRao....
Published date-11/18/2020
Q-Learning
We study the problem of adaptive contention window (CW) design for random-access wireless networks. More precisely, our goal is to design an intelligent node that can dynamically adapt its minimum …
FROST: Faster and more Robust One-shot Semi-supervised Training
HelenaE.Liu, LeslieN.Smith....
Published date-11/18/2020
Recent advances in one-shot semi-supervised learning have lowered the barrier for deep learning of new applications. However, the state-of-the-art for semi-supervised learning is slow to train and the performance is …
EasyTransfer -- A Simple and Scalable Deep Transfer Learning Platform for NLP Applications
MinghuiQiu, PengLi, HanjiePan....
Published date-11/18/2020
QuestionAnswering, TransferLearning
The literature has witnessed the success of applying deep Transfer Learning (TL) algorithms to many NLP applications, yet it is not easy to build a simple and scalable TL toolkit …