A5018509620- Crystallization and Solubility Studies
- X-ray Diffraction in Crystallography
- Advanced Graph Neural Networks
- Intelligent Tutoring Systems and Adaptive Learning
- Recommender Systems and Techniques
- Online Learning and Analytics
- Privacy-Preserving Technologies in Data
- Ethics and Social Impacts of AI
- Topic Modeling
- Metal and Thin Film Mechanics
- Boron and Carbon Nanomaterials Research
- Heat Transfer and Boiling Studies
- Behavioral Health and Interventions
- Cognitive Computing and Networks
- Advanced materials and composites
- Crystallography and molecular interactions
- Face recognition and analysis
- Generative Adversarial Networks and Image Synthesis
- Brain Tumor Detection and Classification
- Surface Modification and Superhydrophobicity
- Fluid Dynamics and Heat Transfer
Hefei University of Technology
2021-2025
As a key application of artificial intelligence, recommender systems are among the most pervasive computer aided to help users find potential items interests. Recently, researchers paid considerable attention fairness issues for intelligence applications. Most these approaches assumed independence instances, and designed sophisticated models eliminate sensitive information facilitate fairness. However, differ greatly from as naturally form user-item bipartite graph, collaboratively...
Recently, the user-side fairness issue in Collaborative Filtering (CF) algorithms has gained considerable attention, arguing that results should not discriminate an individual or a sub-user group based on users’ sensitive attributes (e.g., gender). Researchers have proposed fairness-aware CF models by decreasing statistical associations between predictions and attributes. A more natural idea is to achieve model from causal perspective. The remaining challenge we no access interventions,...
Recommender systems have been widely used in recent years. By exploiting historical user-item interactions, recommender can model personalized potential interests of users and applied to a wide range scenarios. Despite their impressive performance, most them may be subject unwanted biases related sensitive attributes (e.g., race gender), leading unfairness. An intuitive idea alleviate this problem is ensure that there no mutual information between recommendation results attributes. However,...
We present an optical method of simultaneous measurement liquid surface tension, contact angle, and the curved shape, which uses light reflection from this due to wettability. When expanded collimated laser beam is incident upon surfaces vertically, special pattern, includes a dark central region bright field outside, was observed. A critical spot on found, distribution related both width incidence spot. In our experiment, different patterns were recorded when changed. The shape measured...
Cognitive Diagnosis (CD) algorithms receive growing research interest in intelligent education. Typically, these CD assist students by inferring their abilities (i.e., proficiency levels on various knowledge concepts). The can enable further targeted skill training and personalized exercise recommendations, thereby promoting students' learning efficiency online Recently, researchers have found that building incorporating a student-exercise bipartite graph is beneficial for enhancing...
Using first-principles calculations, the elastic constants, thermodynamic property and structural phase transition of rhenium diboride under pressure are investigated by means pseudopotential plane-waves method, as well effect metallic bond on its hardness. Eight candidate structures known transition-metal compounds chosen to probe for ReB2. The calculated lattice parameters consistent with experimental theoretical values. Based third order equation states, Pt between ReB2-ReB2 MoB2-ReB2...
As a key application of artificial intelligence, recommender systems are among the most pervasive computer aided to help users find potential items interests. Recently, researchers paid considerable attention fairness issues for intelligence applications. Most these approaches assumed independence instances, and designed sophisticated models eliminate sensitive information facilitate fairness. However, differ greatly from as naturally form user-item bipartite graph, collaboratively...
Predicting student performance is a fundamental task in Intelligent Tutoring Systems (ITSs), by which we can learn about students' knowledge level and provide personalized teaching strategies for them. Researchers have made plenty of efforts on this task. They either leverage educational psychology methods to predict scores according the learned proficiency, or make full use Collaborative Filtering (CF) models represent latent factors students exercises. However, most these neglect...