A5030468877- Complex Network Analysis Techniques
- Advanced Graph Neural Networks
- Recommender Systems and Techniques
- Neural Networks and Applications
- Intellectual Property and Patents
- Machine Learning and ELM
- Multimodal Machine Learning Applications
- Corrosion Behavior and Inhibition
- Microstructure and mechanical properties
- Aluminum Alloy Microstructure Properties
- Topic Modeling
- Human Motion and Animation
- Computational and Text Analysis Methods
- Land Rights and Reforms
- Metal and Thin Film Mechanics
- Adversarial Robustness in Machine Learning
- High Temperature Alloys and Creep
- Regional Development and Environment
- Bone Tissue Engineering Materials
- Innovation Policy and R&D
- Machine Learning in Materials Science
- Video Analysis and Summarization
- Brain Tumor Detection and Classification
- Digital Humanities and Scholarship
- China's Ethnic Minorities and Relations
Fudan University
2024
Puyang Vocational and Technical College
2019-2023
Tencent (China)
2018-2019
Anhui University
2018
University of Science and Technology of China
2017-2018
Northwest Normal University
2008
Recently, the Network Representation Learning (NRL) techniques, which represent graph structure via low-dimension vectors to support social-oriented application, have attracted wide attention. Though large efforts been made, they may fail describe multiple aspects of similarity between social users, as only a single vector for one unique aspect has represented each node. To that end, in this paper, we propose novel end-to-end framework named MCNE learn conditional network representations, so...
Recently, the Network Representation Learning (NRL) techniques, which target at learning low-dimension vector representation of graph structures, have attracted wide attention due to effectiveness on various social-oriented application. Though large efforts been made joint analysis combining node attributes with network structure, they may usually fail summarize weighted correlations within nodes and attributes, especially when suffer extremely sparse attributes. To that end, in this paper,...
With the recent advances of neural models and natural language processing, automatic generation classical Chinese poetry has drawn significant attention due to its artistic cultural value. Previous works mainly focus on generating given keywords or other text information, while visual inspirations for have been rarely explored. Generating from images is much more challenging than text, since contain very rich information which cannot be described completely using several keywords, a good...
Patent litigation is an expensive legal process faced by many companies. To reduce the cost of patent litigation, one effective approach proactive management based on predictive analysis. However, automatic prediction still open problem due to complexity lawsuits. In this paper, we propose a data-driven framework, Convolutional Tensor Factorization (CTF), identify patents that may cause litigations between two Specifically, CTF hybrid modeling approach, where content features from are...
In this paper, we study the link-oriented tasks in signed network, i.e., labeling link signs and predicting new links. Usually, prior arts directly focus on signs, while their intrinsic structural regularities have been largely ignored. Furthermore, these techniques suffer sensitiveness to high dimension sparsity of networks. To deal with tasks, verifying effect second-order distance propose a novel Link-oriented Signed Network Embedding (LSNE) model, which network embedding technique is...
Artificial neural networks (ANNs) were established for the homogenization and recrystallization heat treatment processes of 5182-Sc-Zr alloy. Microhardness conductivity testing utilized to determine precipitation state Al3(ScxZr1-x) dispersoids during treatment, while electron backscatter diffraction (EBSD) transmission microscopy (TEM) used observe microstructure evolution Tensile experiments performed test mechanical properties alloy after annealing. The two-stage parameters determined by...
With the recent advances of neural models and natural language processing, automatic generation classical Chinese poetry has drawn significant attention due to its artistic cultural value. Previous works mainly focus on generating given keywords or other text information, while visual inspirations for have been rarely explored. Generating from images is much more challenging than text, since contain very rich information which cannot be described completely using several keywords, a good...
Context: Recently, there has been a proposal for Adaptive Multi-Exit Neural Networks (AMENNs) aimed at achieving energy savings and faster inference. This innovation the potential to enable deployment of DNNs on devices with limited resources. To ensure an AMENN satisfies performance requirements resource-constrained applications, it is essential conduct systematic evaluation investigate robustness AMENNs. Recent works have focused attacks against models in both white-box black-box...
Micro/nano-structured coatings with antibacterial function were prepared by microarc oxidation (MAO) treatment on Ti6Al4V alloy in a silicate/phosphate electrolyte NaF additive. The microstructure, phase composition, and corrosion resistance of the modified adding (0.15–0.5 M) examined using scanning/transmission electron microscopy, energy dispersive spectroscopy, atomic force X-ray diffraction, potentiodynamic polarization. results showed that incorporation F ion reduced threshold voltage...