Home /
Research
Showing 121 - 126 / 904
Autoencoders that don't overfit towards the Identity
HaraldSteck....
Published date-12/01/2020
Denoising
Autoencoders (AE) aim to reproduce the output from the input. They may hence tend to overfit towards learning the identity-function between the input and output, i.e., they may predict each …
Counting People by Estimating People Flows
WeizheLiu, MathieuSalzmann, PascalFua....
Published date-12/01/2020
ActiveLearning, CrowdCounting, OpticalFlowEstimation
Modern methods for counting people in crowded scenes rely on deep networks to estimate people densities in individual images. As such, only very few take advantage of temporal consistency in …
Graph Random Neural Networks for Semi-Supervised Learning on Graphs
WenzhengFeng, JieZhang, YuxiaoDong....
Published date-12/01/2020
DataAugmentation, NodeClassification
We study the problem of semi-supervised learning on graphs, for which graph neural networks (GNNs) have been extensively explored. However, most existing GNNs inherently suffer from the limitations of over-smoothing, …
A Closer Look at the Training Strategy for Modern Meta-Learning
JiaxinChen, Xiao-MingWu, YankeLi....
Published date-12/01/2020
Few-ShotLearning, Few-shotRegression, Meta-Learning
The support/query (S/Q) episodic training strategy has been widely used in modern meta-learning algorithms and is believed to improve their generalization ability to test environments. This paper conducts a theoretical …
Evaluating Attribution for Graph Neural Networks
BenjaminSanchez-Lengeling, JenniferWei, BrianLee....
Published date-12/01/2020
Interpretability of machine learning models is critical to scientific understanding, AI safety, as well as debugging. Attribution is one approach to interpretability, which highlights input dimensions that are influential to …
Analysis of Drifting Features
FabianHinder, JonathanJakob, BarbaraHammer....
Published date-12/01/2020
FeatureSelection
The notion of concept drift refers to the phenomenon that the distribution, which is underlying the observed data, changes over time. We are interested in an identification of those features, …