A5018666299- Advanced Graph Neural Networks
- Organ Transplantation Techniques and Outcomes
- Recommender Systems and Techniques
- Domain Adaptation and Few-Shot Learning
- Renal Transplantation Outcomes and Treatments
- Text and Document Classification Technologies
- Complex Network Analysis Techniques
- Topic Modeling
- Machine Learning and Data Classification
- Clinical Nutrition and Gastroenterology
- Traffic Prediction and Management Techniques
- Liver Disease and Transplantation
- Hepatitis B Virus Studies
- Liver Disease Diagnosis and Treatment
- Machine Learning and Algorithms
- Transplantation: Methods and Outcomes
- Hepatitis C virus research
- Metabolism and Genetic Disorders
- Organ and Tissue Transplantation Research
- Neurological Complications and Syndromes
- Human Mobility and Location-Based Analysis
- Artificial Intelligence in Healthcare
- Advanced Image and Video Retrieval Techniques
- Organ Donation and Transplantation
- Bioinformatics and Genomic Networks
Peking University
2015-2025
Chengdu University
2024-2025
Sichuan University
2024-2025
University of California, Los Angeles
2024
Huazhong University of Science and Technology
2024
Anhui University
2022
Capital Medical University
2015-2017
Beijing Ditan Hospital
2017
Soochow University
2015-2016
Liaoning Provincial People's Hospital
2014
Sequential recommendation aims at understanding user preference by capturing successive behavior correlations, which are usually represented as the item purchasing sequences based on their past interactions. Existing efforts generally predict next via modeling sequential patterns. Despite effectiveness, there exist two natural deficiencies: (i) is dynamic in nature, and evolution of collaborative signals often ignored; (ii) observed interactions irregularly-sampled, while existing methods...
This article studies self-supervised graph representation learning, which is critical to various tasks, such as protein property prediction. Existing methods typically aggregate representations of each individual node representations, but fail comprehensively explore local substructures (i.e., motifs and subgraphs), also play important roles in many mining tasks. In this article, we propose a learning framework named cluster-enhanced Contrast (CLEAR) that models the structural semantics from...
The recently developed unsupervised graph representation learning approaches apply contrastive into graph-structured data and achieve promising performance. However, these methods mainly focus on augmentation for positive samples, while the negative mining strategies are less explored, leading to sub-optimal To tackle this issue, we propose a Graph Adversarial Contrastive Learning (GraphACL) scheme that learns bank of samples effective self-supervised whole-graph learning. Our GraphACL...
Point-of-Interest (POI) recommendation plays a vital role in various location-aware services. It has been observed that POI is driven by both sequential and geographical influences. However, since there no annotated label of the dominant influence during recommendation, existing methods tend to entangle these two influences, which may lead sub-optimal performance poor interpretability. In this paper, we address above challenge proposing DisenPOI, novel Disentangled dual-graph framework for...
This paper studies the problem of traffic flow forecasting, which aims to predict future conditions on basis road networks and in past. The is typically solved by modeling complex spatio-temporal correlations data using graph neural (GNNs). However, performance these methods still far from satisfactory since GNNs usually have limited representation capacity when it comes networks. Graphs, nature, fall short capturing non-pairwise relations. Even worse, existing follow paradigm message...
Next Point-of-Interest (POI) recommendation is a critical task in location-based services that aim to provide personalized suggestions for the user’s next destination. Previous works on POI have laid focus modeling spatial preference. However, existing leverage information are only based aggregation of users’ previous visited positions, which discourages model from recommending POIs novel areas. This trait position-based methods will harm model’s performance many situations. Additionally,...
Graph classification is a critical task in numerous multimedia applications, where graphs are employed to represent diverse types of data, including images, videos, and social networks. Nevertheless, the real world, labeled graph data always limited or scarce. To address this issue, we focus on semi-supervised task, which involves both supervised unsupervised models learning from unlabeled data. In contrast recent approaches that transfer entire knowledge model one, argue an effective should...
Graph-structured data, prevalent in domains ranging from social networks to biochemical analysis, serve as the foundation for diverse real-world systems. While graph neural demonstrate proficiency modeling this type of their success is often reliant on significant amounts labeled posing a challenge practical scenarios with limited annotation resources. To tackle problem, tremendous efforts have been devoted enhancing machine learning performance under low-resource settings by exploring...
Graph-structured data exhibits universality and widespread applicability across diverse domains, such as social network analysis, biochemistry, financial fraud detection, security. Significant strides have been made in leveraging Graph Neural Networks (GNNs) to achieve remarkable success these areas. However, real-world scenarios, the training environment for models is often far from ideal, leading substantial performance degradation of GNN due various unfavorable factors, including...
In recent years, deep learning on graphs has achieved remarkable success in various domains. However, the reliance annotated graph data remains a significant bottleneck due to its prohibitive cost and time-intensive nature. To address this challenge, self-supervised (SSL) gained increasing attention made progress. SSL enables machine models produce informative representations from unlabeled data, reducing expensive labeled data. While witnessed widespread adoption, one critical component,...
This paper studies the problem of class-imbalanced graph classification, which aims at effectively classifying categories in scenarios with imbalanced class distributions. While neural networks (GNNs) have achieved remarkable success, their modeling ability on graph-structured data remains suboptimal, typically leads to predictions biased towards majority classes. On other hand, existing learning methods vision may overlook rich semantic substructures classes and excessively emphasize from...
In this paper, we study semi-supervised graph classification, a fundamental problem in data mining and machine learning. The is typically solved by learning neural networks with pseudo-labeling or knowledge distillation to incorporate both labeled unlabeled graphs. However, these methods usually either suffer from overconfident biased pseudo-labels suboptimal caused the insufficient use of data. Inspired recent progress contrastive dual learning, propose DualGraph, principled framework...
This paper studies semi-supervised graph classification, a crucial task with wide range of applications in social network analysis and bioinformatics. Recent works typically adopt neural networks to learn graph-level representations for failing explicitly leverage features derived from topology (e.g., paths). Moreover, when labeled data is scarce, these methods are far satisfactory due their insufficient exploration unlabeled data. We address the challenge by proposing novel framework called...
Graph neural networks have pushed state-of-the-arts in graph classifications recently. Typically, these methods are studied within the context of supervised end-to-end training, which necessities copious task-specific labels. However, real-world circumstances, labeled data could be limited, and there a massive corpus unlabeled data, even from unknown classes as complementary. Towards this end, we study problem semi-supervised universal classification, not only identifies samples do belong to...
Graph clustering, which learns the node representations for effective cluster assignments, is a fundamental yet challenging task in data analysis and has received considerable attention accompanied by graph neural networks (GNNs) recent years. However, most existing methods overlook inherent relational information among nonindependent nonidentically distributed nodes graph. Due to lack of exploration attributes, semantic graph-structured fails be fully exploited leads poor clustering...
Intelligent Transportation System (ITS) is vital in improving traffic congestion, reducing accidents, optimizing urban planning, etc. However, due to the complexity of network, traditional machine learning and statistical methods are relegated background. With advent artificial intelligence era, many deep frameworks have made remarkable progress various fields now considered effective areas. As a method, Graph Neural Networks (GNNs) emerged as highly competitive method ITS field since 2019...
This paper studies semi-supervised graph classification, which is an important problem with various applications in social network analysis and bioinformatics. typically solved by using neural networks (GNNs), yet rely on a large number of labeled graphs for training are unable to leverage unlabeled graphs. We address the limitations proposing Kernel-based Graph Neural Network (KGNN). A KGNN consists GNN-based as well kernel-based parameterized memory network. The performs classification...