A5022061281- Natural Language Processing Techniques
- Topic Modeling
- Advanced Graph Neural Networks
- Adversarial Robustness in Machine Learning
- Text Readability and Simplification
- Data Quality and Management
- Cardiac Arrest and Resuscitation
- Software Engineering Research
- Cognitive Computing and Networks
- Rough Sets and Fuzzy Logic
- Graph Theory and Algorithms
- Radiation Detection and Scintillator Technologies
Zhejiang University
2021-2022
Zhejiang University of Science and Technology
2021
While the celebrated graph neural networks (GNNs) yield effective representations for individual nodes of a graph, there has been relatively less success in extending to task similarity learning. Recent work on learning considered either global-level graph–graph interactions or low-level node–node interactions, however, ignoring rich cross-level (e.g., between each node one and other whole graph). In this article, we propose multilevel matching network (MGMN) framework computing any pair...
Although large language models (LLMs) have achieved significant success in various tasks, they often struggle with hallucination problems, especially scenarios requiring deep and responsible reasoning. These issues could be partially addressed by introducing external knowledge graphs (KG) LLM In this paper, we propose a new LLM-KG integrating paradigm ``$\hbox{LLM}\otimes\hbox{KG}$'' which treats the as an agent to interactively explore related entities relations on KGs perform reasoning...
Code retrieval is to find the code snippet from a large corpus of source repositories that highly matches query natural language description. Recent work mainly uses processing techniques process both texts (i.e., human language) and snippets machine programming language), however neglecting deep structured features codes, which contain rich semantic information. In this paper, we propose an end-to-end graph matching searching (DGMS) model based on neural networks for task retrieval. To end,...
One intriguing property of adversarial attacks is their "transferability" – an example crafted with respect to one deep neural network (DNN) model often found effective against other DNNs as well. Intensive research has been conducted on this phenomenon under simplistic controlled conditions. Yet, thus far there still a lack comprehensive understanding about transferability-based ("transfer attacks") in real-world environments.To bridge critical gap, we conduct the first large-scale...
Knowledge graphs (KGs) are structured representations of diversified knowledge. They widely used in various intelligent applications. In this article, we provide a comprehensive survey on the evolution types knowledge (i.e., static KGs, dynamic temporal and event KGs) techniques for extraction reasoning. Furthermore, introduce practical applications different including case study financial analysis. Finally, propose our perspective future directions engineering, potential combining power...
Large Language Models (LLMs) are versatile, yet they often falter in tasks requiring deep and reliable reasoning due to issues like hallucinations, limiting their applicability critical scenarios. This paper introduces a rigorously designed framework for creating LLMs that effectively anchor knowledge employ closed-loop process, enhancing capability in-depth analysis. We dissect the illustrate contribution of each component LLMs' performance, offering theoretical assurance improved under...
One intriguing property of adversarial attacks is their "transferability" -- an example crafted with respect to one deep neural network (DNN) model often found effective against other DNNs as well. Intensive research has been conducted on this phenomenon under simplistic controlled conditions. Yet, thus far, there still a lack comprehensive understanding about transferability-based ("transfer attacks") in real-world environments. To bridge critical gap, we conduct the first large-scale...