Neural networks : the official journal of the International Neural Network Society
Sep 1, 2025
Effective molecular representation learning (MRL) is essential for advancing molecular property prediction. In recent years, graph-based MRL methods have made significant progress by effectively utilizing the topology structure of molecules. Research...
Neural networks : the official journal of the International Neural Network Society
Sep 1, 2025
Current adversarial defenses for graph neural networks (GNNs) face critical limitations that hinder their real-world application: (1) inadequate adaptability to graph heterophily, (2) lack of generalizability to early GNNs like Graph SAmple and aggre...
Interdisciplinary sciences, computational life sciences
Sep 1, 2025
In top-down proteomics, the accurate identification and characterization of proteoform through mass spectrometry represents a critical objective. As a result, achieving accuracy in identification results is essential. Multiple primary structure alter...
Neural networks : the official journal of the International Neural Network Society
Sep 1, 2025
Uncertainties are the main obstacle to improving the control performance of nonlinear systems. To address this challenge, this paper proposes a fixed-time adaptive neural network compensation control method for a class of high-order nonlinear systems...
Neural networks : the official journal of the International Neural Network Society
Sep 1, 2025
Deep learning models are vulnerable to adversarial attacks. Transfer-based adversarial examples are crafted against surrogate models and transferred to victim models. However, under the black-box settings, most adversaries have poor transferability o...
Neural networks : the official journal of the International Neural Network Society
Sep 1, 2025
Domain generalized semantic segmentation is an essential computer vision task, for which models only leverage source data to learn semantic segmentation towards generalizing to the unseen target domains. Previous works typically address this challeng...
Neural networks : the official journal of the International Neural Network Society
Sep 1, 2025
Given an arbitrary content and style image, arbitrary style transfer aims to render a new stylized image which preserves the content image's structure and possesses the style image's style. Existing arbitrary style transfer methods are based on eithe...
Neural networks : the official journal of the International Neural Network Society
Sep 1, 2025
This paper is concerned with the fixed-time containment control problem for high-order MIMO nonlinear multi-agent systems with external disturbances and actuator faults. First, in the backstepping framework, a neuroadaptive fixed-time containment con...
Magnetic resonance imaging
Sep 1, 2025
OBJECTIVES: This study aims to evaluate the feasibility and effectiveness of deep learning-based super-resolution techniques to reduce scan time while preserving image quality in high-resolution prostate diffusion-weighted imaging (DWI) with readout-...
Neural networks : the official journal of the International Neural Network Society
Sep 1, 2025
Phase information has a significant impact on speech perceptual quality and intelligibility. However, existing speech enhancement methods encounter limitations in explicit phase estimation due to the non-structural nature and wrapping characteristics...