activity
20152020
most citedLearnable Bernoulli Dropout for Bayesian Deep Learning

20 citations · 82 across the 11 of their papers we have counts for

collaborators

14 papers

cs.LG202017 cited

Bayesian Graph Neural Networks with Adaptive Connection Sampling

Arman Hasanzadeh, Ehsan Hajiramezanali, Shahin Boluki +4

We propose a unified framework for adaptive connection sampling in graph neural networks (GNNs) that generalizes existing stochastic regularization methods for training GNNs. The p…

cs.LG202010 cited

NADS: Neural Architecture Distribution Search for Uncertainty Awareness

Randy Ardywibowo, Shahin Boluki, Xinyu Gong +2

Machine learning (ML) systems often encounter Out-of-Distribution (OoD) errors when dealing with testing data coming from a distribution different from training data. It becomes im…

cs.LG202011 cited

Pairwise Supervised Hashing with Bernoulli Variational Auto-Encoder and Self-Control Gradient Estimator

Siamak Zamani Dadaneh, Shahin Boluki, Mingzhang Yin +2

Semantic hashing has become a crucial component of fast similarity search in many large-scale information retrieval systems, in particular, for text data. Variational auto-encoders…

cs.LG20205 cited

Uncertainty Quantification for Deep Context-Aware Mobile Activity Recognition and Unknown Context Discovery

Zepeng Huo, Arash PakBin, Xiaohan Chen +6

Activity recognition in wearable computing faces two key challenges: i) activity characteristics may be context-dependent and change under different contexts or situations; ii) unk…

cs.LG202020 cited

Learnable Bernoulli Dropout for Bayesian Deep Learning

Shahin Boluki, Randy Ardywibowo, Siamak Zamani Dadaneh +2

In this work, we propose learnable Bernoulli dropout (LBD), a new model-agnostic dropout scheme that considers the dropout rates as parameters jointly optimized with other model pa…

cs.LG2019

ARSM Gradient Estimator for Supervised Learning to Rank

Siamak Zamani Dadaneh, Shahin Boluki, Mingyuan Zhou +1

We propose a new model for supervised learning to rank. In our model, the relevance labels are assumed to follow a categorical distribution whose probabilities are constructed base…