Jiye Liang
YOU?
Author Swipe
View article: Physiological, Biochemical and Gene Expression Analyses of Halimodendron halodendron Responding to Drought Stress
Physiological, Biochemical and Gene Expression Analyses of Halimodendron halodendron Responding to Drought Stress Open
Background: As a typical xerophyte, H. halodendron can not only grow in desert sandy areas but also serves as an excellent nectar source and ornamental plant. However, research on its molecular and physiological mechanisms underlying droug…
View article: Prompting Large Language Models with Partial Knowledge for Answering Questions with Unseen Entities
Prompting Large Language Models with Partial Knowledge for Answering Questions with Unseen Entities Open
Retrieval-Augmented Generation (RAG) shows impressive performance by supplementing and substituting parametric knowledge in Large Language Models (LLMs). Retrieved knowledge can be divided into three types: explicit answer evidence, implic…
View article: A Survey of Continual Reinforcement Learning
A Survey of Continual Reinforcement Learning Open
Reinforcement Learning (RL) is an important machine learning paradigm for solving sequential decision-making problems. Recent years have witnessed remarkable progress in this field due to the rapid development of deep neural networks. Howe…
View article: Experimentally Certifying Kochen-Specker Set with the Maximally Mixed State
Experimentally Certifying Kochen-Specker Set with the Maximally Mixed State Open
Certifying Kochen-Specker (KS) set is a task of certifying a set of uncharacterized projectors as desired KS set. This work demonstrates an improved scheme that enables this certification using only a maximally mixed state, rather than tra…
View article: GNN-Transformer Cooperative Architecture for Trustworthy Graph Contrastive Learning
GNN-Transformer Cooperative Architecture for Trustworthy Graph Contrastive Learning Open
Graph contrastive learning (GCL) has become a hot topic in the field of graph representaion learning. In contrast to traditional supervised learning relying on a large number of labels, GCL exploits augmentation techniques to generate mult…
View article: Improving Generalization in Offline Reinforcement Learning via Latent Distribution Representation Learning
Improving Generalization in Offline Reinforcement Learning via Latent Distribution Representation Learning Open
Dealing with the distribution shift is a significant challenge when building offline reinforcement learning (RL) models that can generalize from a static dataset to out-of-distribution (OOD) scenarios. Previous approaches have employed pes…
View article: Progressive Local Alignment for Medical Multimodal Pre-training
Progressive Local Alignment for Medical Multimodal Pre-training Open
Local alignment between medical images and text is essential for accurate diagnosis, though it remains challenging due to the absence of natural local pairings and the limitations of rigid region recognition methods. Traditional approaches…
View article: C-LoRA: Continual Low-Rank Adaptation for Pre-trained Models
C-LoRA: Continual Low-Rank Adaptation for Pre-trained Models Open
Low-Rank Adaptation (LoRA) is an efficient fine-tuning method that has been extensively applied in areas such as natural language processing and computer vision. Existing LoRA fine-tuning approaches excel in static environments but struggl…
View article: Graph Contrastive Learning for Fusion of Graph Structure and Attribute Information
Graph Contrastive Learning for Fusion of Graph Structure and Attribute Information Open
Graph Contrastive Learning (GCL) plays a crucial role in multimedia applications due to its effectiveness in analyzing graph-structured data. Existing GCL methods focus on maximizing the agreement of node representations across different a…
View article: GNN-Transformer Cooperative Architecture for Trustworthy Graph Contrastive Learning
GNN-Transformer Cooperative Architecture for Trustworthy Graph Contrastive Learning Open
Graph contrastive learning (GCL) has become a hot topic in the field of graph representation learning. In contrast to traditional supervised learning relying on a large number of labels, GCL exploits augmentation strategies to generate mul…
View article: Towards Effective Graph Rationalization via Boosting Environment Diversity
Towards Effective Graph Rationalization via Boosting Environment Diversity Open
Graph Neural Networks (GNNs) perform effectively when training and testing graphs are drawn from the same distribution, but struggle to generalize well in the face of distribution shifts. To address this issue, existing mainstreaming graph…
View article: Contrastive Learning With Enhancing Detailed Information for Pre-Training Vision Transformer
Contrastive Learning With Enhancing Detailed Information for Pre-Training Vision Transformer Open
Contrastive Learning (CL) is an effective self-supervised learning method. It performs instance-level contrastiveness based on the image representations, which enables the model to extract abstract information from images. However, when tr…
View article: Linear active disturbance rejection control for large onshore wind turbines in full wind speed range
Linear active disturbance rejection control for large onshore wind turbines in full wind speed range Open
To achieve real-time estimation and compensation of total system disturbances and improve the control performance of wind turbines under complex turbulent wind conditions, three one-order LADRCs were used to reconstruct the wind turbine co…
View article: Graph External Attention Enhanced Transformer
Graph External Attention Enhanced Transformer Open
The Transformer architecture has recently gained considerable attention in the field of graph representation learning, as it naturally overcomes several limitations of Graph Neural Networks (GNNs) with customized attention mechanisms or po…
View article: Achieving eco-innovative smart glass design with the integration of opinion mining, QFD and TRIZ
Achieving eco-innovative smart glass design with the integration of opinion mining, QFD and TRIZ Open
Modern consumption patterns lead to massive waste, which poses challenges in storage and highlights the urgent need for more sustainable product development. Customer feedback on products plays a crucial role in product design, yet previou…
View article: Enhancing Drug Recommendations Via Heterogeneous Graph Representation Learning in EHR Networks
Enhancing Drug Recommendations Via Heterogeneous Graph Representation Learning in EHR Networks Open
Electronic health records (EHRs) contain vast medical information like diagnosis, medication, and procedures, enabling personalized drug recommendations and treatment adjustments. However, current drug recommendation methods only model pat…
View article: A Bibliometric Analysis of the Research Progress and Trends during 2002–2022 on the Carbon Stocks in Terrestrial Ecosystems
A Bibliometric Analysis of the Research Progress and Trends during 2002–2022 on the Carbon Stocks in Terrestrial Ecosystems Open
Improving the carbon storage in terrestrial ecosystems can effectively reduce atmospheric CO2, which is one of the important ways of mitigating global climate change. The knowledge on terrestrial carbon stock research is relatively mature …
View article: Nitrogen Preference of Dominant Species during Hailuogou Glacier Retreat Succession on the Eastern Tibetan Plateau
Nitrogen Preference of Dominant Species during Hailuogou Glacier Retreat Succession on the Eastern Tibetan Plateau Open
Plant nitrogen (N) uptake preference is a key factor affecting plant nutrient acquisition, vegetation composition and ecosystem function. However, few studies have investigated the contribution of different N sources to plant N strategies,…