A5102761357- Advanced Graph Neural Networks
- Explainable Artificial Intelligence (XAI)
- Complex Network Analysis Techniques
- Time Series Analysis and Forecasting
- Topic Modeling
- Machine Learning in Healthcare
- Machine Learning in Materials Science
- Recommender Systems and Techniques
- Neural Networks and Applications
- Bioinformatics and Genomic Networks
- Human Mobility and Location-Based Analysis
- Data Quality and Management
- Adversarial Robustness in Machine Learning
- Artificial Intelligence in Healthcare
- Traffic Prediction and Management Techniques
- Biomedical Text Mining and Ontologies
- Natural Language Processing Techniques
- Data Stream Mining Techniques
- Anomaly Detection Techniques and Applications
- Epigenetics and DNA Methylation
- Advanced Computing and Algorithms
- Advanced Photocatalysis Techniques
- Machine Learning and Algorithms
- Privacy-Preserving Technologies in Data
- Web Data Mining and Analysis
Florida International University
2022-2025
Zunyi Normal College
2024
Hubei University of Science and Technology
2022-2023
Henan Agricultural University
2022
Pennsylvania State University
2018-2021
South China University of Technology
2017-2019
Beihang University
2018
Zhejiang University
2012
Beijing Institute of Technology
2005
Despite recent progress in Graph Neural Networks (GNNs), explaining predictions made by GNNs remains a challenging open problem. The leading method independently addresses the local explanations (i.e., important subgraph structure and node features) to interpret why GNN model makes prediction for single instance, e.g. or graph. As result, explanation generated is painstakingly customized each instance. unique interpreting instance not sufficient provide global understanding of learned model,...
Graph Neural Networks (GNNs) have shown to be powerful tools for graph analytics. The key idea is recursively propagate and aggregate information along the edges of given graph. Despite their success, however, existing GNNs are usually sensitive quality input Real-world graphs often noisy contain task-irrelevant edges, which may lead suboptimal generalization performance in learned GNN models. In this paper, we propose PTDNet, a parameterized topological denoising network, improve robustness...
Various graph contrastive learning models have been proposed to improve the performance of tasks on datasets in recent years. While effective and prevalent, these are usually carefully customized. In particular, although all researches create two views, they differ greatly view augmentations, architectures, objectives. It remains an open question how build your model from scratch for particular datasets. this work, we aim fill gap by studying information is transformed transferred during...
Various contrastive learning approaches have been proposed in recent years and achieve significant empirical success. While effective prevalent, has less explored for time series data. A key component of is to select appropriate augmentations imposing some priors construct feasible positive samples, such that an encoder can be trained learn robust discriminative representations. Unlike image language domains where "desired'' augmented samples generated with the rule thumb guided by...
Accurate cancer subtype prediction is crucial for personalized medicine. Integrating multi-omics data represents a viable approach to comprehending the intricate pathophysiology of complex diseases like cancer. Conventional machine learning techniques are not ideal analyzing interrelationships among different categories omics data. Numerous models have been suggested using graph-based uncover veiled representations and network formations unique distinct types heighten predictions regarding...
Node classification in graph-structured data aims to classify the nodes where labels are only available for a subset of nodes. This problem has attracted considerable research efforts recent years. In real-world applications, both graph topology and node attributes evolve over time. Existing techniques, however, mainly focus on static graphs lack capability simultaneously learn temporal spatial/structural features. attributed is challenging two major aspects. First, effectively modeling...
Graph Neural Networks (GNNs) resurge as a trending research subject owing to their impressive ability capture representations from graph-structured data. However, the black-box nature of GNNs presents significant challenge in terms comprehending and trusting these models, thereby limiting practical applications mission-critical scenarios. Although there has been substantial progress field explaining recent years, majority studies are centered on static graphs, leaving explanation dynamic...
Local community detection aims to find a set of densely-connected nodes containing given query nodes. Most existing local methods are designed for single network. However, network can be noisy and incomplete. Multiple networks more informative in real-world applications. There multiple types node proximities. Complementary information from different helps improve accuracy. In this paper, we propose novel RWM (Random Walk networks) model relevant communities all one sends random walker each...
Despite recent progress in Graph Neural Networks (GNNs), explaining predictions made by GNNs remains a challenging and nascent problem. The leading method mainly considers the local explanations, i.e., important subgraph structure node features, to interpret why GNN model makes prediction for single instance, e.g. or graph. As result, explanation generated is painstakingly customized at instance level. unique interpreting each independently not sufficient provide global understanding of...
Given a network with the labels for subset of nodes, transductive node classification targets to predict remaining nodes in network. This technique has been used variety applications such as voxel functionality detection brain and group label prediction social Most existing approaches are performed static networks. However, many real-world networks dynamic evolve over time. The dynamics both attributes topology jointly determine labels. In this paper, we study problem classifying task is...
Detecting local graph clusters is an important problem in big analysis. Given seed nodes a graph, clustering aims at finding subgraphs around the nodes, which consist of highly relevant to nodes. However, existing methods either allow only single node, or assume all are from same cluster, not true many real applications. Moreover, assumption that cluster fails use crucial information relations between In this paper, we propose method take advantage such relationship. With prior knowledge...
Multi-graph clustering aims to improve accuracy by leveraging information from different domains, which has been shown be extremely effective for achieving better results than single graph based algorithms. Despite the previous success, existing multi-graph methods mostly use shallow models, are incapable capture highly non-linear structures and complex cluster associations in multi-graph, thus result sub-optimal results. Inspired powerful representation learning capability of neural...
Vibrio parahaemolyticus is a widespread foodborne pathogen that causes serious seafood-borne gastrointestinal infections. Biofilm and quorum sensing (QS) are critical in regulating these In this study, first, the ability of Lactiplantibacillus plantarum Z057 to compete, exclude, displace V. biofilm was evaluated. Then, inhibitory effects L. extract (Z057-E) on QS were explored from aspects biomass, metabolic activity, physicochemical properties, extracellular polymer matrix content, signal...
Uncovering rationales behind predictions of graph neural networks (GNNs) has received increasing attention over recent years. Instance-level GNN explanation aims to discover critical input elements, like nodes or edges, that the target relies upon for making predictions. Though various algorithms are proposed, most them formalize this task by searching minimal subgraph which can preserve original However, an inductive bias is deep-rooted in framework: several subgraphs result same similar...
Time series analysis has witnessed the inspiring development from traditional autoregressive models, deep learning to recent Transformers and Large Language Models (LLMs). Efforts in leveraging vision models for time have also been made along way but are less visible community due predominant research on sequence modeling this domain. However, discrepancy between continuous discrete token space of LLMs, challenges explicitly correlations variates multivariate shifted some attentions equally...
Local community detection, which aims to find a target containing set of query nodes, has recently drawn intense research interest. The existing local detection methods usually assume all nodes are from the same and only single community. This is strict requirement does not allow much flexibility. In many real-world applications, however, we may have any prior knowledge about memberships different be communities. To address this limitation methods, propose novel memory-based random walk...
Unintended pregnancies (UIP) among unmarried sexually active college students in mainland China have emerged as a major reproductive health issue with detrimental personal and socioeconomic consequences. This cross-sectional study aimed to determine the prevalence factors associated UIP undergraduates China.Between September 8, 2019 January 17, 2020, total of 48,660 participants were recruited across Chinese complete self-administered, structured, online questionnaire. analysis was...
The improved AdaBoost-SVM algorithm is used to classify the safety and risk from Peers-to-Peers net loan platforms. Since SVM hard deal with rare samples its training slow, rule sampling reduce noise. Then, combinations of learning machine, P2P risks can be identified. result shows that IAdaBoost improve platform classification accuracy. And error controlled in 5%.
Abstract Integration of multi-omics data holds great promise for understanding the complex biology diseases, particularly Alzheimer’s, Parkinson’s, and cancer. However, integration is challenging due to high dimensionality complexity data. Traditional machine learning methods are not well-suited handling relationships between different types omics Many models were proposed that utilize graph-based extract hidden representations network structures from enhance cancer prediction, patient...
Graph Neural Networks (GNNs) have received increasing attention due to their ability learn from graph-structured data. However, predictions are often not interpretable. Post-hoc instance-level explanation methods been proposed understand GNN predictions. These seek discover substructures that explain the prediction behavior of a trained GNN. In this paper, we shed light on existence distribution shifting issue in existing methods, which affects quality, particularly applications real-life...
Uncovering rationales behind predictions of graph neural networks (GNNs) has received increasing attention over recent years. Instance-level GNN explanation aims to discover critical input elements, such as nodes or edges, that the target relies upon for making predictions. Though various algorithms are proposed, most them formalize this task by searching minimal subgraph, which can preserve original However, an inductive bias is deep-rooted in framework: Several subgraphs result same...