A5027301562- Advanced Graph Neural Networks
- Graph Theory and Algorithms
- Complex Network Analysis Techniques
- Color perception and design
- Artificial Intelligence in Healthcare
- 2D Materials and Applications
- Topic Modeling
- Multisensory perception and integration
- Generative Adversarial Networks and Image Synthesis
- Digital Media and Visual Art
- Domain Adaptation and Few-Shot Learning
- Machine Learning and ELM
Peking University
2020-2024
Fuzhou University
2023
Despite the recent success of Message-passing Graph Neural Networks (MP-GNNs), strong inductive bias homophily limits their ability to generalize heterophilic graphs and leads over-smoothing problem. Most existing works attempt mitigate this issue in spirit emphasizing contribution from similar neighbors reducing those dissimilar ones when performing aggregation, where dissimilarities are utilized passively positive effects ignored, leading suboptimal performances. Inspired by idea attitude...
While Graph Neural Networks (GNNs) have achieved remarkable results in a variety of applications, recent studies exposed important shortcomings their ability to capture heterogeneous structures and attributes an underlying graph. Furthermore, though many Heterogeneous GNN (HGNN) variants been proposed state-of-the-art results, there are limited theoretical understandings properties. To this end, we introduce graph kernel HGNNs develop Kernel-based (HGK-GNN). Specifically, incorporate the...
Recent works reveal that network embedding techniques enable many machine learning models to handle diverse downstream tasks on graph-structured data. However, as previous methods usually focus for a single network, they cannot learn representations transferable multiple networks. Hence, it is important design algorithm supports model transferring different networks, known domain adaptation. In this article, we propose Domain Adaptive Network Embedding framework, which applies Graph...
Large-scale "pre-train and prompt learning" paradigms have demonstrated remarkable adaptability, enabling broad applications across diverse domains such as question answering, image recognition, multimodal retrieval. This approach fully leverages the potential of large-scale pre-trained models, reducing downstream data requirements computational costs while enhancing model applicability various tasks. Graphs, versatile structures that capture relationships between entities, play pivotal...
Despite the recent success of Graph Neural Networks (GNNs), their learning pipeline is guided only by input graph and desired output certain tasks, failing to capture useful patterns when not enough data are presented. Existing attempts incorporate auxiliary knowledge mitigate this issue, most which in a unified structure or hard obtain. Noticing that nodes graphs usually form implicit hierarchical structures, we proposed integrate category taxonomies into process GNNs. A taxonomy domain...
Intelligent sweeping robots were first marketed in Europe and the US, gradually entered China as standard of living country improved.The purpose this study is to investigate influence appearance intelligent floor on consumers' perceptions preferences. The aim impact smart cleaning consumer In stage, 120 adjectives collected screened by six industrial design students find most suitable 40 adjectives, then a questionnaire survey was conducted general consumer's semantic difference method (SD...