Results 161 to 170 of about 4,261,155 (305)
Graph Neural Networks for Bipartite Graphs
Bipartite graphs are a special type of graph data structure where vertices can be divided into two disjoint and independent sets, and each edge connects a vertex from one set to a vertex in the other set. They can be used to model many real-world applications such as user-item interaction networks, authorship networks, and product-customer networks ...
openaire +2 more sources
Graph Databases and Graph Neural Networks [PDF]
Purpose - Nowadays, social networks, online media sharing and e-commerce platforms generate a vast amount of data, which, among other information, capture the interactions among the users.
Tsolakidis, Stratos +4 more
core
Multimodal Engagement Assessment in Children During Invented Story Paradigm With a Social Robot
A multimodal framework is proposed to assess children's engagement during storytelling interactions with a social robot. Gaze, physiological, and behavioral data are combined and validated against observer ratings. An automated gaze‐labeling strategy is introduced, and supervised classifiers achieve high accuracy. The study supports scalable engagement
Laura Fiorini +7 more
wiley +1 more source
This study explores how information processing is distributed between brains and bodies through a codesign approach. Using the “backpropagation through soft body” framework, brain–body coupling agents are developed and analyzed across several tasks in which output is generated through the agents’ physical dynamics.
Hiroki Tomioka +3 more
wiley +1 more source
Efficient Screening of Organic Singlet Fission Molecules Using Graph Neural Networks. [PDF]
A high‐throughput screening framework based on graph neural networks (GNNs) and multi‐level validation facilitates the identification of singlet fission (SF) candidates. By efficiently predicting excitation energies across 20 million molecules, and integrating TDDFT calculations, synthetic accessibility assessments, and GW+BSE calculations, this ...
Fu L +5 more
europepmc +2 more sources
An enhanced universal gripper combining rigid mechanics with self‐adaptable fingers is presented for industrial automation. The novel six‐bar linkage with integrated compliant pad eliminates mechanical interference while enabling passive shape adaptation.
Muhammad Usman Khalid +7 more
wiley +1 more source
Graph Structure Reshaping Against Adversarial Attacks on Graph Neural Networks
Graph Neural Networks (GNNs) have achieved impressive performance in many tasks on graph data. Recent studies show that they are vulnerable to adversarial attacks.
Wang, H +7 more
core +1 more source
Here, we present a textile, wearable capacitive interface enabling multidirectional remote control by dynamically modulating electrode overlap and spacing via a freely gliding upper electrode. A forearm‐mounted prototype drives robotic and media tasks with 12–15 ms latency, maintains < 0.8% drift after 500 cycles, and remains stably functional at 90 ...
Cagatay Gumus +8 more
wiley +1 more source
Graph Neural Networks for the Prediction of Protein–Protein Interfaces
Binding site identification allows to determine the functionality and the quaternary structure of protein–protein complexes. Various approaches to this problem have been proposed without reaching a viable solution.
Pancino, Niccolò +8 more
core +1 more source
Memorization in Graph Neural Networks
Deep neural networks (DNNs) have been shown to memorize their training data, but similar analyses for graph neural networks (GNNs) remain under-explored. We introduce NCMemo (Node Classification Memorization), the first framework to quantify label memorization in semi-supervised node classification.
Adarsh Jamadandi +3 more
openaire +2 more sources

