62 citations · 350 across the 33 of their papers we have counts for
12 papers · 1 filter
Learned Gradient Compression for Distributed Deep Learning
Lusine Abrahamyan, Yiming Chen, Giannis Bekoulis +1
Training deep neural networks on large datasets containing high-dimensional data requires a large amount of computation. A solution to this problem is data-parallel distributed tra…
A Deep-Unfolded Reference-Based RPCA Network For Video Foreground-Background Separation
Huynh Van Luong, Boris Joukovsky, Yonina C. Eldar +1
Deep unfolded neural networks are designed by unrolling the iterations of optimization algorithms. They can be shown to achieve faster convergence and higher accuracy than their op…
Graph Convolutional Neural Networks with Node Transition Probability-based Message Passing and DropNode Regularization
Tien Huu Do, Duc Minh Nguyen, Giannis Bekoulis +2
Graph convolutional neural networks (GCNNs) have received much attention recently, owing to their capability in handling graph-structured data. Among the existing GCNNs, many metho…
Interpretable Deep Recurrent Neural Networks via Unfolding Reweighted - Minimization: Architecture Design and Generalization Analysis
Huynh Van Luong, Boris Joukovsky, Nikos Deligiannis
Deep unfolding methods---for example, the learned iterative shrinkage thresholding algorithm (LISTA)---design deep neural networks as learned variations of optimization methods. Th…
DeepFPC: Deep Unfolding of a Fixed-Point Continuation Algorithm for Sparse Signal Recovery from Quantized Measurements
Peng Xiao, Bin Liao, Nikos Deligiannis
We present DeepFPC, a novel deep neural network designed by unfolding the iterations of the fixed-point continuation algorithm with one-sided l1-norm (FPC-l1), which has been propo…
Deep Coupled-Representation Learning for Sparse Linear Inverse Problems with Side Information
Evaggelia Tsiligianni, Nikos Deligiannis
In linear inverse problems, the goal is to recover a target signal from undersampled, incomplete or noisy linear measurements. Typically, the recovery relies on complex numerical o…
Designing recurrent neural networks by unfolding an l1-l1 minimization algorithm
Hung Duy Le, Huynh Van Luong, Nikos Deligiannis
We propose a new deep recurrent neural network (RNN) architecture for sequential signal reconstruction. Our network is designed by unfolding the iterations of the proximal gradient…
Geometric Matrix Completion with Deep Conditional Random Fields
Duc Minh Nguyen, Robert Calderbank, Nikos Deligiannis
The problem of completing high-dimensional matrices from a limited set of observations arises in many big data applications, especially, recommender systems. Existing matrix comple…
Matrix Factorization via Deep Learning
Duc Minh Nguyen, Evaggelia Tsiligianni, Nikos Deligiannis
Matrix completion is one of the key problems in signal processing and machine learning. In recent years, deep-learning-based models have achieved state-of-the-art results in matrix…
Matrix Completion With Variational Graph Autoencoders: Application in Hyperlocal Air Quality Inference
Tien Huu Do, Duc Minh Nguyen, Evaggelia Tsiligianni +5
Inferring air quality from a limited number of observations is an essential task for monitoring and controlling air pollution. Existing inference methods typically use low spatial…
Regularizing Autoencoder-Based Matrix Completion Models via Manifold Learning
Duc Minh Nguyen, Evaggelia Tsiligianni, Robert Calderbank +1
Autoencoders are popular among neural-network-based matrix completion models due to their ability to retrieve potential latent factors from the partially observed matrices. Neverth…
Multiview Deep Learning for Predicting Twitter Users' Location
Tien Huu Do, Duc Minh Nguyen, Evaggelia Tsiligianni +2
The problem of predicting the location of users on large social networks like Twitter has emerged from real-life applications such as social unrest detection and online marketing.…