Results 71 to 80 of about 30,335 (256)

Study on Graph Collaborative Filtering Model Based on FeatureNet Contrastive Learning [PDF]

Jisuanji kexue
Graph-based collaborative filtering recommendation techniques have gained significant attention for their ability to efficiently process large-scale interaction data.However,the effectiveness of these techniques is limited by the sparsity of data in real-
WU Pengyuan, FANG Wei
doaj   +1 more source

Graph Contrastive Learning With Personalized Augmentation

IEEE Transactions on Knowledge and Data Engineering
Graph contrastive learning (GCL) has emerged as an effective tool for learning unsupervised representations of graphs. The key idea is to maximize the agreement between two augmented views of each graph via data augmentation. Existing GCL models mainly focus on applying \textit{identical augmentation strategies} for all graphs within a given scenario ...
Xin Zhang, Qiaoyu Tan, Xiao Huang, Bo Li
openaire   +2 more sources

Predicting Atomic Charges in MOFs by Topological Charge Equilibration

Advanced Functional Materials, EarlyView.
An atomic charge prediction method is presented that is able to accurately reproduce ab‐initio‐derived reference charges for a large number of metal–organic frameworks. Based on a topological charge equilibration scheme, static charges that fulfill overall neutrality are quickly generated.
Babak Farhadi Jahromi, Sumukh Shankar Sharadaprasad, Rochus Schmid   +2 more
wiley   +1 more source

Contrastive Graph Few-Shot Learning

, 2022
Prevailing deep graph learning models often suffer from label sparsity issue. Although many graph few-shot learning (GFL) methods have been developed to avoid performance degradation in face of limited annotated data, they excessively rely on labeled data, where the distribution shift in the test phase might result in impaired generalization ability ...
Zhang, Chunhui, Liu, Hongfu, Li, Jundong, Ye, Yanfang, Zhang, Chuxu   +4 more
openaire   +2 more sources

In Situ 3D Bioprinting: Impact of Cross‐Linking on the Adhesive Properties of Hydrogels

Advanced Functional Materials, EarlyView.
In situ 3D bioprinting enables the direct deposition of cell‐laden, adhesive biomaterials for on‐site tissue regeneration. This review provides a comprehensive overview of how cross‐linking influences the bioadhesive properties of hydrogels used in 3D bioprinting, highlighting cross‐linking triggers, bioadhesion mechanisms, polymer interpenetration ...
Odile Romero Fernandez, Mulazim Hussain Asim, Shumaila Arshad, Gergely Kali, Andreas Bernkop‐Schnürch   +4 more
wiley   +1 more source

Noise-augmented contrastive learning with attention for knowledge-aware collaborative recommendation

Scientific Reports
Knowledge graph (KG) plays an increasingly important role in recommender systems. Recently, Graph Convolutional Network (GCN) and Graph Attention Network (GAT) based model has gradually become the theme of Collaborative Knowledge Graph (CKG).
Wanyi Gu, Hua Xu, Xiang Peng, Ning Rao, Huali Zhu   +4 more
doaj   +1 more source

Learning in Markov Random Fields with Contrastive Free Energies [PDF]

, 2005
Learning Markov random field (MRF) models is notoriously hard due to the presence of a global normalization factor. In this paper we present a new framework for learning MRF models based on the contrastive free energy (CF) objective function.
Sutton, Charles, Welling, Max
core   +1 more source

Molecularly Engineered Highly Stable Memristors with Ultra‐Low Operational Voltage: Integrating Synthetic DNA with Quasi‐2D Perovskites

Advanced Functional Materials, EarlyView.
Molecularly engineered memristors integrating Ag nanoparticle–embedded synthetic DNA with quasi‐2D halide perovskites enable ultra‐low‐operational voltage, forming‐free resistive switching, and record‐low power density. This synergistic integration of customized DNA and 2D OHP in bio‐hybrid architecture enhances charge transport, reduces variability ...
Kavya S. Keremane, Abhinav Gorthy, Luyao Zheng, Chiranth C Ravi, Haodong Wu, Jiamao Zheng, Neela H. Yennawar, Shashank Priya, Rashmi Jha, Bed Poudel   +9 more
wiley   +1 more source

The Cuttlebone Blueprint for Multifunctional Metamaterials: Design Taxonomy, Functional Decoupling, and Future Horizons

Advanced Functional Materials, EarlyView.
Cuttlebone‐inspired metamaterials exploit a septum‐wall architecture to achieve excellent mechanical and functional properties. This review classifies existing designs into direct biomimetic, honeycomb‐type, and strut‐type architectures, summarizes governing design principles, and presents a decoupled design framework for interpreting multiphysical ...
Xinwei Li, Zhendong Li
wiley   +1 more source

Multi-Level Graph Contrastive Learning

, 2021
Graph representation learning has attracted a surge of interest recently, whose target at learning discriminant embedding for each node in the graph. Most of these representation methods focus on supervised learning and heavily depend on label information.
Shao, Pengpeng, Liu, Tong, Zhang, Dawei, Tao, Jianhua, Che, Feihu, Yang, Guohua   +5 more
openaire   +2 more sources