A5066877556- Advanced Image and Video Retrieval Techniques
- Topic Modeling
- Advanced Graph Neural Networks
- Image Retrieval and Classification Techniques
- Recommender Systems and Techniques
- Domain Adaptation and Few-Shot Learning
- Multimodal Machine Learning Applications
- Text and Document Classification Technologies
- Sentiment Analysis and Opinion Mining
- Complex Network Analysis Techniques
- Reinforcement Learning in Robotics
- Remote-Sensing Image Classification
- Advanced Text Analysis Techniques
- Adversarial Robustness in Machine Learning
- Advanced Neural Network Applications
- Advanced Computational Techniques and Applications
- Image Processing Techniques and Applications
- Consumer Market Behavior and Pricing
- Opinion Dynamics and Social Influence
- Spam and Phishing Detection
- Machine Learning and Data Classification
- Intelligent Tutoring Systems and Adaptive Learning
- Machine Learning in Bioinformatics
- Energy Efficient Wireless Sensor Networks
- Service-Oriented Architecture and Web Services
Jining Medical University
2025
Xidian University
2016-2025
Huawei Technologies (China)
2022-2025
Stanford University
2025
Dongguan People’s Hospital
2025
Shenzhen Institutes of Advanced Technology
2024
Chongqing Cancer Hospital
2024
Chongqing University
2010-2024
Northern Jiangsu People's Hospital
2024
Yangtze University
2024
As an essential approach in many Internet of Things (IoT) applications, multiview learning synthesizes multiple features to achieve more comprehensive descriptions data items. Most the previous studies on have been dedicated increasing prediction accuracy, while ignoring reliability decision. This would limit their deployment high-risk IoT and industrial applications such as automated vehicle. Although a trusted classification model has proposed recently, it cannot well deal with highly...
Product reviews are valuable for upcoming buyers in helping them make decisions. To this end, different opinion mining techniques have been proposed, where judging a review sentence's orientation (e.g., positive or negative) is one of their key challenges. Recently, deep learning has emerged as an effective means solving sentiment classification problems. A neural network intrinsically learns useful representation automatically without human efforts. However, the success highly relies on...
Multi-view clustering aims to leverage information from multiple views improve clustering. Most previous works assumed that each view has complete data. However, in real-world datasets, it is often the case a may contain some missing data, resulting incomplete multi-view problem. Previous methods for this problem have at least one of following drawbacks: (1) employing shallow models, which cannot well handle dependence and discrepancy among different views; (2) ignoring hidden data; (3)...
With the application requirement, technique for change detection based on heterogeneous remote sensing images is paid more attention. However, detecting changes between two challenging as they cannot be compared in low-dimensional space. In this paper, we construct an approximately symmetric deep neural network with sides containing same number of coupled layers to transform into feature The are connected and transformed space, which their features discriminative difference image can...
Graph Convolutional Network (GCN) has achieved extraordinary success in learning effective task-specific representations of nodes graphs. However, regarding Heterogeneous Information (HIN), existing HIN-oriented GCN methods still suffer from two deficiencies: (1) they cannot flexibly explore all possible meta-paths and extract the most useful ones for a target object, which hinders both effectiveness interpretability; (2) often need to generate intermediate meta-path based dense graphs,...
Bidding optimization is one of the most critical problems in online advertising. Sponsored search (SS) auction, due to randomness user query behavior and platform nature, usually adopts keyword-level bidding strategies. In contrast, display advertising (DA), as a relatively simpler scenario for has taken advantage real-time (RTB) boost performance advertisers. this paper, we consider RTB problem sponsored named SS-RTB. SS-RTB much more complex dynamic environment, stochastic policies based...
Multiview representation learning (MVRL) leverages information from multiple views to obtain a common summarizing the consistency and complementarity in multiview data. Most previous matrix factorization-based MVRL methods are shallow models that neglect complex hierarchical information. The recently proposed deep factorization cannot explicitly capture We present concept (DMCL) method, which hierarchically factorizes data, tries model consistent complementary semantic structures at highest...
Nowadays, a lot of people possess accounts on multiple online social networks, e.g., Facebook and Twitter. These networks are overlapped, but the correspondences between their users not explicitly given. Mapping common across these will be beneficial for applications such as cross-network recommendation. In recent years, mapping algorithms have been proposed which exploited and/or profile relations from different networks. However, there is still lack unified framework can well exploit...
Graph Convolutional Networks (GCNs) suffer from performance degradation when models go deeper. However, earlier works only attributed the degeneration to over-smoothing. In this paper, we conduct theoretical and experimental analysis explore fundamental causes of in deep GCNs: over-smoothing gradient vanishing have a mutually reinforcing effect that deteriorate more quickly GCNs. On other hand, existing anti-over-smoothing methods all perform full convolutions up model depth. They could not...
As an essential role in smart city applications, personalized recommender systems help users to find their potentially interested items from historically generated data. Recently, researchers have started utilize the massive user-generated multimodal contents improve recommendation performance. However, previous methods at least one of following drawbacks: 1) employing shallow models, which cannot well capture high-level conceptual information; 2) failing user visual preference. In this...
Rapid eye movement (REM) sleep behavior disorder (RBD) is a parasomnia that involves involuntary, unwanted, and random movements of dreaming patient. Typically, these dreams contain violent activities. There high likelihood the patient being injured or hurting his bed-partner as result enactments. Continuous monitoring sleeping RBD patients can prevent harmful events through timely intervention. This paper presents novel method for continuous observation exploiting fine-grained amplitude...
Multi-view data is common in real-world datasets, where different views describe distinct perspectives. To better summarize the consistent and complementary information multi-view data, researchers have proposed various representation learning algorithms, typically based on factorization models. However, most previous methods were focused shallow models which cannot capture complex hierarchical information. Although a deep model has been recently, it fails to explicitly discern does not...
The remarkable progress of network embedding has led to state-of-the-art algorithms in recommendation. However, the sparsity user-item interactions (i.e., explicit preferences) on websites remains a big challenge for predicting users' behaviors. Although research efforts have been made utilizing some auxiliary information (e.g., social relations between users) solve problem, existing rich heterogeneous relationships are still not fully exploited. Moreover, previous works relied linearly...
Multi-layer networks provide an effective and efficient tool to model characterize complex systems with multiple types of interactions, which differ greatly from the traditional single-layer networks. Graph clustering in multi-layer is highly non-trivial since it difficult balance connectivity clusters connection various layers. The current algorithms for layer-specific are criticized low accuracy sensitivity perturbation To overcome these issues, a novel algorithm module based on...