Results 111 to 120 of about 6,993,713 (204)

Large Language Model Semantic-Guided Counterfactual Data Augmentation for Cross-Domain Sequential Recommendation

IEEE Access
Cross-domain sequential recommendation leverages source-domain interactions to alleviate target-domain sparsity, yet existing methods struggle with semantic gaps, insufficient training signals under extreme sparsity, and negative transfer caused by user ...
Ning Liu, Jianhua Zhao, Ronghua Zhao
doaj   +1 more source

Transparent Perovskite Light‐Emitting Diodes with Conductive Oxide Top Electrodes

Advanced Materials, EarlyView.
Transparent perovskite light‐emitting diodes (TrPeLEDs) enable simultaneous display and transparency, expanding application possibilities. Using a metal oxide buffer layer and pulsed laser deposition, TrPeLEDs with diverse compositions and architectures are demonstrated.
Michele Forzatti, Sergio Martínez‐Saiz, Morena Cervino, Edoardo Stanzani, Sandra Jenatsch, Qingsen Zeng, Joo Sung Kim, Dong‐Hyeok Kim, Eojin Yoon, Tae‐Woo Lee, Daniel Tordera, Henk J. Bolink   +11 more
wiley   +1 more source

Thermodynamic Limits to Molecular Doping in Conjugated Polymers: A Perspective on Phase Behavior and Miscibility

Advanced Materials, EarlyView.
Molecular doping of conjugated polymers is fundamentally constrained by thermodynamic phase behavior. This Perspective reframes doping efficiency and stability in terms of miscibility limits, binodals, and solvus boundaries, highlighting the role of effective interaction parameters and charge transfer.
Somayeh Kashani, Justin Neu, Sung‐Joo Kwon, Runqio Song, Zixuan Chen, Tajah Trapier, Paschalis Gkoupidenis, David Ginger, Wei You, Jasper J. Michels, Harald Ade   +10 more
wiley   +1 more source

Cross-domain information fusion and personalized recommendation in artificial intelligence recommendation system based on mathematical matrix decomposition

Scientific Reports
Given the challenges of inter-domain information fusion and data sparsity in collaborative filtering algorithms, this paper proposes a cross-domain information fusion matrix decomposition algorithm to enhance the accuracy of personalized recommendations ...
Xiaoyan Meng
doaj   +1 more source

Multitask Features Mapping Network Model for Cross-domain Recommendation

Journal of Harbin University of Science and Technology
The key to cross-domain recommendation is how to effectively map user features from source domain to target domain. Previous studies focused more on mapping user features, ignored the similarity between user features and actual features after mapping and
AN Qiuyu, YU Yan, XIONG Xi
doaj   +1 more source

When Poor Exciton Dissociation Limits Photocurrents in Organic Solar Cells: Why Low Offset Non‐Fullerene Acceptor Blends Can't Be Efficient

Advanced Materials, EarlyView.
The energetic offset between the donor and the acceptor components in organic photoactive layers is central to the tradeoff between photovoltage and photocurrent losses. This Perspective covers the most important issues surrounding this topic in non‐fullerene acceptor blends, from the difficulty of accurately determining state energies and driving ...
Dieter Neher, Manasi Pranav
wiley   +1 more source

Graph Signal Processing for Cross-Domain Recommendation [PDF]

Cross-domain recommendation (CDR) extends conventional recommender systems by leveraging user-item interactions from dense domains to mitigate data sparsity and the cold start problem.
Shin, Won-Yong, Choi, Jeongwhan, Kang, Seongku, Lee, Jeongeun, Park, Noseong, Lee, Dongha   +5 more
core  

FedSCOPE: Federated cross-domain sequential recommendation with decoupled contrastive learning and privacy-preserving semantic enhancement

Scientific Reports
Cross-domain sequential recommendation (CDSR) models users’ dynamic preferences by exploiting behavioral signals from multiple domains, but it faces challenges in data sparsity, domain heterogeneity, and privacy protection.
Lujin Zhao, Yi Lin, Sujuan Qin, Wenmin Li, Fei Gao, Yijie Shi, Zhengping Jin   +6 more
doaj   +1 more source

Organic Materials of Tomorrow: Horizons of Artificial Intelligence

Advanced Materials, EarlyView.
This review examines machine learning techniques accelerating the discovery of organic semiconductors by linking molecular structure to properties. Key methods include graph neural networks, generative models, and active learning. Applications to organic photovoltaics demonstrate practical impact.
Harold Mena, J. Terence Blaskovits, Kun‐Han Lin, Denis Andrienko   +3 more
wiley   +1 more source

Hierarchical Hyperbolic Embeddings for Review-Driven Cross-Domain Recommendation

IEEE Access
Recommender systems are now ubiquitous in e-commerce and review platforms, yet they often struggle when interaction data is extremely sparse (the so-called cold-start problem).
Yoonhyuk Choi, Chong-Kwon Kim
doaj   +1 more source