paper-with-me

Papers

An Underparametrized Deep Decoder Architecture for Graph Signals

2019-08-02 · Samuel Rey, Antonio G. Marques, Santiago Segarra

While deep convolutional architectures have achieved remarkable results in a gamut of supervised applications dealing with images and speech, recent works show that deep untrained non-convolutional architectures can also outperform state-of-the-art methods in several tasks such as image compression and denoising. Motivated by the fact that many contemporary datasets have an irregular structure different from a 1D/2D grid, this paper generalizes untrained and underparametrized non-convolutional architectures to signals defined over irregular domains represented by graphs. The proposed architecture consists of a succession of layers, each of them implementing an upsampling operator, a linear feature combination, and a scalar nonlinearity. A novel element is the incorporation of upsampling operators accounting for the structure of the supporting graph, which is achieved by considering a systematic graph coarsening approach based on hierarchical clustering. The numerical results carried out in synthetic and real-world datasets showcase that the reconstruction performance can improve drastically if the information of the supporting graph topology is taken into account.

📄 PDF Abstract BibTeX arXiv:1908.00878

Code (1)

reysam93/Graph_Deep_Decoder 공식 구현 pytorch

Tasks

ClusteringDecoderDenoisingImage Compression

Similar Papers 제목 키워드 기반

Time-varying Signals Recovery via Graph Neural Networks

2023-02-22 · Jhon A. Castro-Correa, Jhony H. Giraldo, Anindya Mondal, Mohsen Badiey 외

The recovery of time-varying graph signals is a fundamental problem with numerous applications in sensor networks and forecasting in time series. Effectively capturing the spatio-temporal information in these signals is …

DecoderGraph LearningGraph Neural NetworkTime Series+1

THInImg: Cross-modal Steganography for Presenting Talking Heads in Images

2023-11-28 · Lin Zhao, Hongxuan Li, Xuefei Ning, Xinru Jiang

Cross-modal Steganography is the practice of concealing secret signals in publicly available cover signals (distinct from the modality of the secret signals) unobtrusively. While previous approaches primarily concentrate…

Decoder

Generative Diffusion Models of Stochastic Graph Signals

2026-07-07 · Yiğit Berkay Uslu, Samar Hadou, Sergio Rozada, Shirin Saeedi Bidokhti 외 arxiv

Sampling stochastic signals supported on a graph underlies many graph machine learning tasks, including recommender systems, forecasting in financial markets, and wireless network optimization. In these settings, the tar…

Graph Neural Network

Encoding Robust Representation for Graph Generation

2018-09-28 · Dongmian Zou, Gilad Lerman

Generative networks have made it possible to generate meaningful signals such as images and texts from simple noise. Recently, generative methods based on GAN and VAE were developed for graphs and graph signals. However,…

DecoderGraph GenerationLink Prediction

Geometric structure of Deep Learning networks and construction of global ${\mathcal L}^2$ minimizers

2023-09-19 · Thomas Chen, Patricia Muñoz Ewald

In this paper, we explicitly determine local and global minimizers of the $\mathcal{L}^2$ cost function in underparametrized Deep Learning (DL) networks; our main goal is to shed light on their geometric structure and pr…