A5101568954- Recommender Systems and Techniques
- Advanced Graph Neural Networks
- Topic Modeling
- Caching and Content Delivery
- Electrocatalysts for Energy Conversion
- Advanced Bandit Algorithms Research
- Human Mobility and Location-Based Analysis
- Advanced battery technologies research
- Fuel Cells and Related Materials
- IoT and Edge/Fog Computing
- Hybrid Renewable Energy Systems
- Image Retrieval and Classification Techniques
- Advanced Photocatalysis Techniques
- Privacy-Preserving Technologies in Data
- Data Management and Algorithms
- Complex Network Analysis Techniques
- Sentiment Analysis and Opinion Mining
- Combustion and Detonation Processes
- Spam and Phishing Detection
- Cloud Computing and Resource Management
- Cloud Data Security Solutions
- E-commerce and Technology Innovations
- Service-Oriented Architecture and Web Services
- Network Security and Intrusion Detection
- Blockchain Technology Applications and Security
Chongqing University
2016-2025
Linyi University
2025
Southwest University
2023-2025
Qingdao University
2025
South China University of Technology
2022-2024
Energy Research Institute
2024
Chongqing Medical University
2024
Chongqing Cancer Hospital
2022-2024
Kunming University of Science and Technology
2024
Changzhou University
2023-2024
Device-to-device (D2D) communication is a promising technology for wireless in the near future. Since D2D usually reuses resource of cellular users, interference management key element. However, when secrecy capacity taken into consideration, caused by could be advantage as kind help against eavesdroppers. In this paper, we novelly introduce problem capacity, such that pair achieve its own transmission while requirement still satisfied. Moreover, utilize outage probability to better depict...
Recently, explainable recommendation has attracted increasing attentions, which can make the recommender system more transparent and improve user satisfactions by recommending products with useful explanations. However, existing methods trend to trade-off between accuracy interpretability of results. In this manuscript, we propose Knowledge Enhanced Graph Neural Networks (KEGNN) for recommendation. Semantic knowledge from external base is leveraged into representation learning three sides,...
Affinity prediction between molecule and protein is an important step of virtual screening, which usually called drug-target affinity (DTA) prediction. Its accuracy directly influences the progress drug development. Sequence-based can predict according to sequence, fast be applied large datasets. However, due lack structure information, needs improved.The proposed model WGNN-DTA competent in compound-protein interaction (CPI) tasks. Various experiments are designed verify performance method...
The increasing use of biodegradable plastic mulch like polybutylene adipate terephthalate (PBAT) has raised concerns about its long-term environmental impact. In this study, we investigated the effects multiyear PBAT application on bacterial and fungal communities, assembly mechanisms, key ecological functions. microbial community diversity composition were significantly altered after mulching. We observed that treatment enriched specific genera, such as Pantoea, potentially involved in...
The d-band state of materials is an important descriptor for activity oxygen evolution reaction (OER). For NiO materials, there rarely concern about tuning their states to tailor the OER behaviors. Herein, nanocrystals with doping small amount La3+ were used regulate promoting activity. Density calculations based on density functional theory revealed that produced upper shift center, which would induce stronger electronic interaction between surface Ni atoms and species intermediates....
Recommender systems are vulnerable to shilling attacks. Forged user-generated content data, such as user ratings and reviews, used by attackers manipulate recommendation rankings. Shilling attack detection in recommender is of great significance maintain the fairness sustainability systems. The current studies have problems terms poor universality algorithms, difficulty selection profile attributes, lack an optimization mechanism. In this paper, a behaviour structure based on abnormal group...
Next point-of-interest (POI) recommendation optimizes user travel experiences and enhances platform revenues by providing users with potentially appealing next location choices. In recent research, scholars have successfully mined users' general tastes varying interests modeling long-term short-term check-in sequences. However, conventional methods for long predominantly employ distinct encoders to process interaction data independently, disparities in limiting the ultimate performance of...
Recommender systems using Collaborative Filtering techniques are capable of make personalized predictions. However, these highly vulnerable to profile injection attacks. Group attacks that target a group items instead one, and there common attributes among items. Such profiles will have good probability being similar large number user profiles, making them hard detect. We propose novel technique for identifying attack which uses an improved metric based on Degree Similarity with Top...
Recommender systems are highly vulnerable to shilling attacks, both by individuals and groups. Attackers who introduce biased ratings in order affect recommendations, have been shown negatively collaborative filtering (CF) algorithms. Previous research focuses only on the differences between genuine profiles attack profiles, ignoring group characteristics profiles. In this paper, we study use of statistical metrics detect rating patterns attackers Another question is that most existing...