Node-Adaptive Regularization for Graph Signal Reconstruction
IEEE Open Journal of Signal Processing, 2021 A critical task in graph signal processing is to estimate the true signal from noisy observations over a subset of nodes, also known as the reconstruction problem.
Maosheng Yang +3 more
doaj +2 more sources
Neural Networks Regularization With Graph-Based Local Resampling
IEEE Access, 2021 This paper presents the concept of Graph-based Local Resampling of perceptron-like neural networks with random projections (RN-ELM) which aims at regularization of the yielded model.
Alex D. Assis +4 more
doaj +2 more sources
Fusion of Radiomics and Gated Graph Attention Network for Pulmonary Nodule Malignancy Classification [PDF]
Journal of ImagingPulmonary nodule malignancy classification requires effective integration of heterogeneous imaging features and contextual information among nodules. Existing models mainly analyze nodules independently and may overlook inter-nodule relationships.
Xinying Guo, Zirong Yu, Jibin Yin
doaj +2 more sources
On the Multiplicative Regularization of Graph Laplacians on Closed and Open Structures With Applications to Spectral Partitioning [PDF]
IEEE Access, 2014 A new regularization technique for graph Laplacians arising from triangular meshes of closed and open structures is presented. The new technique is based on the analysis of graph Laplacian spectrally equivalent operators in terms of Sobolev norms and on ...
Rajendra Mitharwal +1 more
doaj +2 more sources
Structure-Aware Compound–Protein Affinity Prediction via Graph Neural Networks with Group Lasso Regularization [PDF]
Computational and Structural Biotechnology JournalHighlights • Graph neural networks (GNNs) improve drug property prediction using activity-cliff substructure signals.• Group lasso regularization enhances atom-level feature attribution in GNN models.• Sparse regularization provides stable subgraph-level
Zanyu Shi +6 more
doaj +2 more sources
Uncertainty-aware instance-wise feature selection with adaptive graph regularization [PDF]
Scientific ReportsInstance-wise feature selection aims at discovering the most relevant set of attributes for each particular sample, providing a natural direction for achieving adaptive learning on inputs of heterogeneous and high-dimensional nature.
G. Kirubavathi +2 more
doaj +2 more sources
Spectral Geometry for Structural Pattern Recognition [PDF]
, 2010 Graphs are used pervasively in computer science as representations of data with a network or relational structure, where the graph structure provides a flexible representation such that there is no fixed dimensionality for objects. However, the analysis
El Ghawalby, Hewayda
core +6 more sources
Regular colorings in regular graphs
Discussiones Mathematicae Graph Theory, 2020 zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Anton Bernshteyn +6 more
openaire +4 more sources
Catastrophic Forgetting in Deep Graph Networks: A Graph Classification Benchmark
Frontiers in Artificial Intelligence, 2022 In this work, we study the phenomenon of catastrophic forgetting in the graph representation learning scenario. The primary objective of the analysis is to understand whether classical continual learning techniques for flat and sequential data have a ...
Antonio Carta +4 more
doaj +1 more source
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2022 Although a graph-based semisupervised learning (SSL) approach can utilize limited numbers of labeled samples for hyperspectral image (HSI) classification, it is difficult to use the large amount of pixels in an HSI to construct a large-scale graph.
Longshan Yang +4 more
doaj +1 more source