Explanipedia

LGAN: An Efficient High-Order Graph Neural Network via the Line Graph Aggregation Open

Lin Du, Lu Bai, Jincheng Li, Lixin Cui, Hangyuan Du , et al. · 2025

Graph Neural Networks (GNNs) have emerged as a dominant paradigm for graph classification. Specifically, most existing GNNs mainly rely on the message passing strategy between neighbor nodes, where the expressivity is limited by the 1-dime…

Pricing and coordination of product service supply chain under an industrial internet platform environment Open

Xiangdong Li, Xueyan Wu, Junli Wang, Lixin Cui · 2025

Purpose With the development and application of new-generation information technology, a wave of intelligent transformations in enterprise services has emerged. As a combination of various information technologies, industrial Internet plat…

FairWork: A Generic Framework For Evaluating Fairness In LLM-Based Job Recommender System Open

Yi Hu, Ziyu Lyu, Lu Bai, Lixin Cui · 2025

MidPO: Dual Preference Optimization for Safety and Helpfulness in Large Language Models via a Mixture of Experts Framework Open

Yupeng Qi, Ziyu Lyu, Min Yang, Yanlin Wang, Lu Bai , et al. · 2025

As large language models (LLMs) are increasingly applied across various domains, enhancing safety while maintaining the helpfulness of LLMs has become a critical challenge. Recent studies solve this problem through safety-constrained onlin…

The Risk Spillover Effect of China's Financial Market and Real Economy——Based on Network Correlation Analysis Open

Yichuan Yuan, Yan Tu, Lixin Cui, Yang Hu, Xi Wang · 2025

Financial security is crucial for the development of the Chinese economy owing to the complex interconnections between the financial market and the real economy. This study employs the generalized variance decomposition method to construct…

DHAKR: Learning Deep Hierarchical Attention-Based Kernelized Representations for Graph Classification Open

Feifei Qian, Lu Bai, Lixin Cui, Ming Li, Ziyu Lyu , et al. · 2025

Graph-based representations are powerful tools for analyzing structured data. In this paper, we propose a novel model to learn Deep Hierarchical Attention-based Kernelized Representations (DHAKR) for graph classification. To this end, we c…

Graphprobe: Knowledge Probing for Graph Representation Learning Open

Mingyu Zhao, Xingyu Huang, Anqi Liu, Ziyu Lyu, Yanlin Wang , et al. · 2025

MidPO: Dual Preference Optimization for Safety and Helpfulness in Large Language Models via a Mixture of Experts Framework Open

Yupeng Qi, Ziyu Lyu, Min Yang, Yanlin Wang, Lu Bai , et al. · 2025

Knowledge Probing for Graph Representation Learning Open

Mingyu Zhao, Xingyu Huang, Ziyu Lyu, Yanlin Wang, Lixin Cui , et al. · 2024

Graph learning methods have been extensively applied in diverse application areas. However, what kind of inherent graph properties e.g. graph proximity, graph structural information has been encoded into graph representation learning for d…

Quantum Vicsek Model for Active Matter Open

Hong Chun Yuan, Lixin Cui, Larry Chen, Che Sun · 2024

We propose a quantum analog of the Vicsek model, consisting of an ensemble of overdamped spin$-1/2$ particles with ferromagnetic couplings, driven by a uniformly polarized magnetic field. The spontaneous magnetization of the spin component…

HC-GAE: The Hierarchical Cluster-based Graph Auto-Encoder for Graph Representation Learning Open

Zhuo Xu, Lu Bai, Lixin Cui, Ming Li, Yue Wang , et al. · 2024

Graph Auto-Encoders (GAEs) are powerful tools for graph representation learning. In this paper, we develop a novel Hierarchical Cluster-based GAE (HC-GAE), that can learn effective structural characteristics for graph data analysis. To thi…

ENADPool: The Edge-Node Attention-based Differentiable Pooling for Graph Neural Networks Open

Zhehan Zhao, Lu Bai, Lixin Cui, Ming Li, Yue Wang , et al. · 2024

Graph Neural Networks (GNNs) are powerful tools for graph classification. One important operation for GNNs is the downsampling or pooling that can learn effective embeddings from the node representations. In this paper, we propose a new hi…

Dual-modal Prior Semantic Guided Infrared and Visible Image Fusion for Intelligent Transportation System Open

Jing Li, Lu Bai, Bin Yang, Chang Li, Lingfei Ma , et al. · 2024

Infrared and visible image fusion (IVF) plays an important role in intelligent transportation system (ITS). The early works predominantly focus on boosting the visual appeal of the fused result, and only several recent approaches have trie…

AKBR: Learning Adaptive Kernel-based Representations for Graph Classification Open

Feifei Qian, Lixin Cui, Yue Wang, Hangyuan Du, Lu Bai , et al. · 2024

In this paper, we propose a new model to learn Adaptive Kernel-based Representations (AKBR) for graph classification. Unlike state-of-the-art R-convolution graph kernels that are defined by merely counting any pair of isomorphic substructu…

SSHPool: The Separated Subgraph-based Hierarchical Pooling Open

Zhuo Xu, Lixin Cui, Yue Wang, Hangyuan Du, Lu Bai , et al. · 2024

In this paper, we develop a novel local graph pooling method, namely the Separated Subgraph-based Hierarchical Pooling (SSHPool), for graph classification. We commence by assigning the nodes of a sample graph into different clusters, resul…

LncRNA018392 promotes proliferation of Liaoning cashmere goat skin fibroblasts through up-regulation of CSF1R by binding to SPI1 Open

Mei Jin, Suhe Lyu, Xinyang Liu, Lixin Cui, Weiyu Fan · 2023

The Liaoning cashmere goat has been confirmed as a valuable genetic resource breed that is prohibited from genetic outflow in China, and it achieves the highest single fleece production. Hair follicle development in the cashmere goat is re…

AERK: Aligned Entropic Reproducing Kernels through Continuous-time Quantum Walks Open

Lixin Cui, Ming Li, Yue Wang, Lu Bai, Edwin R. Hancock · 2023

In this work, we develop an Aligned Entropic Reproducing Kernel (AERK) for graph classification. We commence by performing the Continuous-time Quantum Walk (CTQW) on each graph structure, and computing the Averaged Mixing Matrix (AMM) to d…

QESK: Quantum-based Entropic Subtree Kernels for Graph Classification Open

Lu Bai, Lixin Cui, Edwin R. Hancock · 2022

In this paper, we propose a novel graph kernel, namely the Quantum-based Entropic Subtree Kernel (QESK), for Graph Classification. To this end, we commence by computing the Average Mixing Matrix (AMM) of the Continuous-time Quantum Walk (C…

HAQJSK: Hierarchical-Aligned Quantum Jensen-Shannon Kernels for Graph Classification Open

Lu Bai, Lixin Cui, Yue Wang, Ming Li, Edwin R. Hancock · 2022

In this work, we propose a family of novel quantum kernels, namely the Hierarchical Aligned Quantum Jensen-Shannon Kernels (HAQJSK), for un-attributed graphs. Different from most existing classical graph kernels, the proposed HAQJSK kernel…

Collaborative Knowledge Graph Fusion by Exploiting the Open Corpus Open

Yue Wang, Yao Wan, Lu Bai, Lixin Cui, Zhuo Xu , et al. · 2022

To alleviate the challenges of building Knowledge Graphs (KG) from scratch, a more general task is to enrich a KG using triples from an open corpus, where the obtained triples contain noisy entities and relations. It is challenging to enri…

Writing Style Aware Document-level Event Extraction Open

Zhuo Xu, Yue Wang, Lu Bai, Lixin Cui · 2022

Event extraction, the technology that aims to automatically get the structural information from documents, has attracted more and more attention in many fields. Most existing works discuss this issue with the token-level multi-label classi…

Cross-Supervised Joint-Event-Extraction with Heterogeneous Information Networks Open

Yue Wang, Zhuo Xu, Lu Bai, Yao Wan, Lixin Cui , et al. · 2020

Joint-event-extraction, which extracts structural information (i.e., entities or triggers of events) from unstructured real-world corpora, has attracted more and more research attention in natural language processing. Most existing works d…

Learning Backtrackless Aligned-Spatial Graph Convolutional Networks for Graph Classification Open

Lu Bai, Lixin Cui, Yuhang Jiao, Luca Rossi, Edwin R. Hancock · 2020

In this paper, we develop a novel backtrackless aligned-spatial graph convolutional network (BASGCN) model to learn effective features for graph classification. Our idea is to transform arbitrary-sized graphs into fixed-sized backtrackless…

Entropic Dynamic Time Warping Kernels for Co-Evolving Financial Time Series Analysis Open

Lu Bai, Lixin Cui, Zhihong Zhang, Lixiang Xu, Yue Wang , et al. · 2020

Network representations are powerful tools to modeling the dynamic time-varying financial complex systems consisting of multiple co-evolving financial time series, e.g., stock prices. In this work, we develop a novel framework to compute t…

A Quantum-inspired Entropic Kernel for Multiple Financial Time Series Analysis Open

Lu Bai, Lixin Cui, Yue Wang, Yuhang Jiao, Edwin R. Hancock · 2020

Network representations are powerful tools for the analysis of time-varying financial complex systems consisting of multiple co-evolving financial time series, e.g., stock prices, etc. In this work, we develop a new kernel-based similarity…

A Hierarchical Transitive-Aligned Graph Kernel for Un-attributed Graphs Open

Lu Bai, Lixin Cui, Edwin R. Hancock · 2020

In this paper, we develop a new graph kernel, namely the Hierarchical Transitive-Aligned kernel, by transitively aligning the vertices between graphs through a family of hierarchical prototype graphs. Comparing to most existing state-of-th…

Typical Correlation Score between Economic Development Speed and Employment Rate Open

Lixin Cui, Qian Hu, Lei Wang, Xinqian Wu · 2020

In order to discuss the relationship between the employment rate and the economic development speed, the typical correlation analysis between the development speed and the employment rate is made in the past 20 years. Three indicators of d…

Generative Temporal Link Prediction via Self-tokenized Sequence Modeling Open

Yue Wang, Chenwei Zhang, Shen Wang, Philip S. Yu, Lu Bai , et al. · 2019

We formalize networks with evolving structures as temporal networks and propose a generative link prediction model, Generative Link Sequence Modeling (GLSM), to predict future links for temporal networks. GLSM captures the temporal link fo…

Entropic Dynamic Time Warping Kernels for Co-evolving Financial Time Series Analysis Open

Lu Bai, Lixin Cui, Lixiang Xu, Yue Wang, Zhihong Zhang , et al. · 2019

In this work, we develop a novel framework to measure the similarity between dynamic financial networks, i.e., time-varying financial networks. Particularly, we explore whether the proposed similarity measure can be employed to understand …

Competitive Multi-Agent Deep Reinforcement Learning with Counterfactual Thinking Open

Yue Wang, Yao Wan, Chenwei Zhang, Lixin Cui, Lu Bai , et al. · 2019

Counterfactual thinking describes a psychological phenomenon that people re-infer the possible results with different solutions about things that have already happened. It helps people to gain more experience from mistakes and thus to perf…

Lixin Cui YOU? Author Swipe