270 citations · 1.4k across the 97 of their papers we have counts for
8 papers · 1 filter
Discovery and Separation of Features for Invariant Representation Learning
Ayush Jaiswal, Rob Brekelmans, Daniel Moyer +3
Supervised machine learning models often associate irrelevant nuisance factors with the prediction target, which hurts generalization. We propose a framework for training robust ne…
Invariant Representations through Adversarial Forgetting
Ayush Jaiswal, Daniel Moyer, Greg Ver Steeg +2
We propose a novel approach to achieving invariance for deep neural networks in the form of inducing amnesia to unwanted factors of data through a new adversarial forgetting mechan…
Nearly-Unsupervised Hashcode Representations for Relation Extraction
Sahil Garg, Aram Galstyan, Greg Ver Steeg +1
Recently, kernelized locality sensitive hashcodes have been successfully employed as representations of natural language text, especially showing high relevance to biomedical relat…
MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing
Sami Abu-El-Haija, Bryan Perozzi, Amol Kapoor +5
Existing popular methods for semi-supervised learning with Graph Neural Networks (such as the Graph Convolutional Network) provably cannot learn a general class of neighborhood mix…
Efficient Covariance Estimation from Temporal Data
Hrayr Harutyunyan, Daniel Moyer, Hrant Khachatrian +2
Estimating the covariance structure of multivariate time series is a fundamental problem with a wide-range of real-world applications -- from financial modeling to fMRI analysis. D…
Exact Rate-Distortion in Autoencoders via Echo Noise
Rob Brekelmans, Daniel Moyer, Aram Galstyan +1
Compression is at the heart of effective representation learning. However, lossy compression is typically achieved through simple parametric models like Gaussian noise to preserve…