Untrained neural network priors for inverse imaging problems: A survey

A Qayyum, I Ilahi, F Shamshad… - … on Pattern Analysis …, 2022‏ - ieeexplore.ieee.org
In recent years, advancements in machine learning (ML) techniques, in particular, deep
learning (DL) methods have gained a lot of momentum in solving inverse imaging problems …

Towards data-centric graph machine learning: Review and outlook

X Zheng, Y Liu, Z Bao, M Fang, X Hu, AWC Liew… - arxiv preprint arxiv …, 2023‏ - arxiv.org
Data-centric AI, with its primary focus on the collection, management, and utilization of data
to drive AI models and applications, has attracted increasing attention in recent years. In this …

Learning to denoise unreliable interactions for graph collaborative filtering

C Tian, Y **e, Y Li, N Yang, WX Zhao - Proceedings of the 45th …, 2022‏ - dl.acm.org
Recently, graph neural networks (GNN) have been successfully applied to recommender
systems as an effective collaborative filtering (CF) approach. However, existing GNN-based …

Madm: A model-agnostic denoising module for graph-based social recommendation

W Ma, Y Wang, Y Zhu, Z Wang, M **g, X Zhao… - Proceedings of the 17th …, 2024‏ - dl.acm.org
Graph-based social recommendation improves the prediction accuracy of recommendation
by leveraging high-order neighboring information contained in social relations. However …

Theoretical perspectives on deep learning methods in inverse problems

J Scarlett, R Heckel, MRD Rodrigues… - IEEE journal on …, 2022‏ - ieeexplore.ieee.org
In recent years, there have been significant advances in the use of deep learning methods in
inverse problems such as denoising, compressive sensing, inpainting, and super-resolution …

Radar‐based human activity recognition using denoising techniques to enhance classification accuracy

R Yu, Y Du, J Li, A Napolitano… - IET Radar, Sonar & …, 2024‏ - Wiley Online Library
Radar‐based human activity recognition is considered as a competitive solution for the
elderly care health monitoring problem, compared to alternative techniques such as …

Convolutional learning on directed acyclic graphs

S Rey, H Ajorlou, G Mateos - arxiv preprint arxiv:2405.03056, 2024‏ - arxiv.org
We develop a novel convolutional architecture tailored for learning from data defined over
directed acyclic graphs (DAGs). DAGs can be used to model causal relationships among …

Redesigning graph filter-based GNNs to relax the homophily assumption

S Rey, M Navarro, VM Tenorio, S Segarra… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Graph neural networks (GNNs) have become a workhorse approach for learning from data
defined over irregular domains, typically by implicitly assuming that the data structure is …

FedPnP: Personalized graph-structured federated learning

A Rasti-Meymandi, A Sajedi, KN Plataniotis - Pattern Recognition, 2025‏ - Elsevier
Abstract In Personalized Federated Learning (PFL), current methods often fail to consider
the fine-grained relationships between clients and their local datasets, hindering effective …

MRI reconstruction with enhanced self-similarity using graph convolutional network

Q Ma, Z Lai, Z Wang, Y Qiu, H Zhang, X Qu - BMC Medical Imaging, 2024‏ - Springer
Abstract Background Recent Convolutional Neural Networks (CNNs) perform low-error
reconstruction in fast Magnetic Resonance Imaging (MRI). Most of them convolve the image …