Author name cluster

Kun Yue

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

12 papers

2 author rows

AAAI Conference 2026 Conference Paper

Dual-Kernel Graph Community Contrastive Learning

Xiang Chen
Kun Yue
Wenjie Liu
Zhenyu Zhang
Liang Duan

Graph Contrastive Learning (GCL) has emerged as a powerful paradigm for training Graph Neural Networks (GNNs) in the absence of task-specific labels. However, its scalability on large-scale graphs is hindered by the intensive message passing mechanism of GNN and the quadratic computational complexity of contrastive loss over positive and negative node pairs. To address these issues, we propose an efficient GCL framework that transforms the input graph into a compact network of interconnected node sets while preserving structural information across communities. We firstly introduce a kernelized graph community contrastive loss with linear complexity, enabling effective information transfer among node sets to capture hierarchical structural information of the graph. We then incorporate a knowledge distillation technique into the decoupled GNN architecture to accelerate inference while maintaining strong generalization performance. Extensive experiments on sixteen real-world datasets of varying scales demonstrate that our method outperforms state-of-the-art GCL baselines in both effectiveness and scalability.

PDF Details DOI

IJCAI Conference 2025 Conference Paper

Conditional Information Bottleneck-Based Multivariate Time Series Forecasting

Xinhui Li
Liang Duan
Lixing Yu
Kun Yue
Yuehua Li

Multivariate time series (MTS) forecasting endeavors to anticipate the forthcoming sequence of interdependent variables through the utilization of past observations. The prevailing methodologies, relying on deep neural networks, Transformer, or information bottleneck frameworks, persist in confronting challenges such as overlooking or inadequately capturing the inter / intra-series correlations evident in practical MTS datasets. In response to these challenges, we introduce a conditional information bottleneck-based strategy for MTS forecasting, grounded in information theory. Initially, we establish a conditional information bottleneck principle to capture the inter-series correlations via conditioning on non-target variables. Subsequently, a conditional mutual information-based technique is introduced to extract intra-series correlations by conditioning historical data, ensuring temporal consistency within each variable. Lastly, we devise a unified optimization objective and propose a training algorithm to collectively capture inter / intra-series correlations. Empirical investigations on authentic datasets underscore the superiority of our proposed approach over other cutting-edge competitors. Our code is available at https: //github. com/Xinhui-Lee/CIB-MTSF.

PDF Details DOI

UAI Conference 2025 Conference Paper

Improving Graph Contrastive Learning with Community Structure

Xiang Chen
Kun Yue
Liang Duan
Lixing Yu

Graph contrastive learning (GCL) has demonstrated remarkable success in training graph neural networks (GNNs) by distinguishing positive and negative node pairs without human labeling. However, existing GCL methods often suffer from two limitations: the repetitive message-passing mechanism in GNNs and the quadratic computational complexity of exhaustive node pair sampling in loss function. To address these issues, we propose an efficient and effective GCL framework that leverages community structure rather than relying on the intricate node-to-node adjacency information. Inspired by the concept of sparse low-rank approximation of graph diffusion matrices, our model delivers node messages to the corresponding communities instead of individual neighbors. By exploiting community structures, our method significantly improves GCL efficiency by reducing the number of node pairs needed for contrastive loss calculation. Furthermore, we theoretically prove that our model effectively captures essential structure information for downstream tasks. Extensive experiments conducted on real-world datasets illustrate that our method not only achieves the state-of-the-art performance but also substantially reduces time and memory consumption compared with other GCL methods. Our code is available at [https: //github. com/chenx-hi/IGCL-CS](https: //github. com/chenx-hi/IGCL-CS).

Details

EAAI Journal 2025 Journal Article

Physics-informed dual guidance method using physical envelope harmonic distribution and transfer learning for few-shot gear fault classification

Kun Yue
Liming Wang
Xiaoxi Ding
Wennian Yu
Zaigang Chen
Wenbin Huang

Recent years have seen artificial intelligence algorithms gain considerable popularity in gear fault classification, yet their performance remains hindered by the scarcity of labeled fault data, often leading to suboptimal classification results. Several state-of-the-art studies have demonstrated that incorporating physical information can improve classification accuracy. However, the differences between simulated and measured signals pose a significant challenge in enhancing the performance of physics-informed methods. In order to fill this gap, this paper introduces a novel physics-informed dual guidance (PI-DG) method using physical envelope harmonic distribution (PEHD) and transfer learning (TL) for few-shot gear fault classification. Within the proposed method, we introduce a new concept of PEHD, which is defined as the distribution feature of the shaft frequency and its harmonics in envelope spectrum. A physics-informed parameter optimization model (PI-POM) is developed to minimize the difference between the simulation and measured signals in terms of PEHD, enabling the accurate identification of detailed parameters within the dynamic model. Subsequently, a TL guidance framework is established for the fine-tuning and adaptation of a Long Short-Term Memory-aided Different Kolmogorov-Arnold network (LSTM-DKAN), with the aim of improving classification accuracy. Validation on a constructed back-to-back gear test rig with induced crack and spalling faults demonstrates the PI-DG method's effectiveness in reducing physics-simulation discrepancies, exhibiting superior classification performance especially in few-shot cases.

Details DOI

UAI Conference 2025 Conference Paper

Probabilistic Semantics Guided Discovery of Approximate Functional Dependencies

Liang Duan
Xinran Wu
Xinhui Li
Lixing Yu
Kun Yue

As the general description of relationships between attributes, approximate functional dependencies (AFDs) almost hold for a given dataset with a few violations. Most of existing methods for AFD discover are insufficient to balance the efficiency and accuracy due to the massive search space and permission of violations. To address these issues, we propose an efficient method of probabilistic semantics guided discovery of AFDs based on Bayesian network (BN). Firstly, we learn a BN structure and conduct conditional independence tests on the learned structure rather than the entire search space, such that candidate AFDs could be obtained. Secondly, we fulfill search space reduction and structure pruning by making use of probabilistic semantics of graphical models in terms of BN. Consequently, we provide a branch-and-bound algorithm to discover the AFDs with the highest smoothed mutual information scores. Experimental results illustrate that our proposed method is more effective and efficient than the comparison methods. Our code is available at [https: //github. com/DKE-Code/BNAFD](https: //github. com/DKE-Code/BNAFD).

Details

NeurIPS Conference 2025 Conference Paper

SYMPHONY: Synergistic Multi-agent Planning with Heterogeneous Language Model Assembly

Wei Zhu
Zhiwen Tang
Kun Yue

Recent advancements have increasingly focused on leveraging large language models (LLMs) to construct autonomous agents for complex problem-solving tasks. However, existing approaches predominantly employ a single-agent framework to generate search branches and estimate rewards during Monte Carlo Tree Search (MCTS) planning. This single-agent paradigm inherently limits exploration capabilities, often resulting in insufficient diversity among generated branches and suboptimal planning performance. To overcome these limitations, we propose $\textbf{SY}$nergistic $\textbf{M}$ulti-agent $\textbf{P}$lanning with $\textbf{H}$eter$\textbf{O}$geneous la$\textbf{N}$gauge model assembl$\textbf{Y}$ ($\textbf{SYMPHONY}$), a novel multi-agent planning framework that integrates a pool of heterogeneous language model-based agents. By leveraging diverse reasoning patterns across agents, SYMPHONY enhances rollout diversity and facilitates more effective exploration. Empirical results across multiple benchmark tasks show that SYMPHONY achieves strong performance even when instantiated with open-source LLMs deployable on consumer-grade hardware. When enhanced with cloud-based LLMs accessible via API, SYMPHONY demonstrates further improvements, outperforming existing state-of-the-art baselines and underscoring the effectiveness of heterogeneous multi-agent coordination in planning tasks.

PDF Details

EAAI Journal 2024 Journal Article

Detection method for weld defects in time-of-flight diffraction images based on multi-image fusion and feature hybrid enhancement

Deyan Yang
Hongquan Jiang
Song Ai
Tianlun Yang
Zelin Zhi
Deqiang Jing
Jianmin Gao
Kun Yue

The accurate recognition of defects in the time-of-flight diffraction (TOFD) images of welds is important to improve the capability and efficiency of defect detection. The existing deep learning-based defect detection methods take a single image as input, without considering the fact that technicians need to observe the image “dynamically” during its evaluation, resulting in low accuracy and credibility of the defect detection results. To address these issues, combining deep learning techniques with TOFD inspection domain knowledge, this article proposes a multi-image fusion and feature hybrid enhancement-based weld defect detection method for TOFD images, comprising three parts: a single-to-multiple image decomposition module based on gain preprocessing, multi-image feature extraction module, and weld defect detection module based on feature hybrid enhancement. The developed method can realize a “dynamically changing” feature extraction and target detection of weld defects in TOFD images. The proposed method was experimentally verified using TOFD images of welds in large-scale spherical pressure tanks. This method greatly surpassed the current state-of-the-art approaches, including You Only Look Once (YOLO) v9, YOLOv10, and Real-Time DEtection TRansformer (RT-DETR), achieving a mean average precision of 82. 0%, average precision for small-size targets of 45. 2%, and average recall for small-size targets of 70. 9%. The detection time for a single TOFD image with a resolution of 500 × 1350 pixels is 0. 1287 s, satisfying the real-time requirements for weld TOFD inspection in practical engineering applications. The proposed method can also be extended to engineering applications such as intelligent detection of weld defects based on X-ray images.

Details DOI

AAAI Conference 2024 Conference Paper

Structural Entropy Based Graph Structure Learning for Node Classification

Liang Duan
Xiang Chen
Wenjie Liu
Daliang Liu
Kun Yue
Angsheng Li

As one of the most common tasks in graph data analysis, node classification is frequently solved by using graph structure learning (GSL) techniques to optimize graph structures and learn suitable graph neural networks. Most of the existing GSL methods focus on fusing different structural features (basic views) extracted from the graph, but very little graph semantics, like hierarchical communities, has been incorporated. Thus, they might be insufficient when dealing with the graphs containing noises from real-world complex systems. To address this issue, we propose a novel and effective GSL framework for node classification based on the structural information theory. Specifically, we first prove that an encoding tree with the minimal structural entropy could contain sufficient information for node classification and eliminate redundant noise via the graph's hierarchical abstraction. Then, we provide an efficient algorithm for constructing the encoding tree to enhance the basic views. Combining the community influence deduced from the encoding tree and the prediction confidence of each view, we further fuse the enhanced views to generate the optimal structure. Finally, we conduct extensive experiments on a variety of datasets. The results demonstrate that our method outperforms the state-of-the-art competitors on effectiveness and robustness.

PDF Details DOI

TIST Journal 2022 Journal Article

Algorithms for Trajectory Points Clustering in Location-based Social Networks

Nan Han
Shaojie Qiao
Kun Yue
Jianbin Huang
Qiang He
Tingting Tang
Faliang Huang
Chunlin He

Recent advances in localization techniques have fundamentally enhanced social networking services, allowing users to share their locations and location-related contents. This has further increased the popularity of location-based social networks (LBSNs) and produces a huge amount of trajectories composed of continuous and complex spatio-temporal points from people’s daily lives. How to accurately aggregate large-scale trajectories is an important and challenging task. Conventional clustering algorithms (e.g., k -means or k -mediods) cannot be directly employed to process trajectory data due to their serialization, triviality and redundancy. Aiming to overcome the drawbacks of traditional k -means algorithm and k -mediods, including their sensitivity to the selection of the initial k value, the cluster centers and easy convergence to a locally optimal solution, we first propose an optimized k -means algorithm (namely OKM ) to obtain k optimal initial clustering centers based on the density of trajectory points. Second, because k -means is sensitive to noisy points, we propose an improved k -mediods algorithm called IKMD based on an acceptable radius r by considering users’ geographic location in LBSNs. The value of k can be calculated based on r, and the optimal k points are selected as the initial clustering centers with high densities to reduce the cost of distance calculation. Thirdly, we thoroughly analyze the advantages of IKMD by comparing it with the commonly used clustering approaches through illustrative examples. Last, we conduct extensive experiments to evaluate the performance of IKMD against seven clustering approaches including the proposed optimized k -means algorithm, k -mediods algorithm, traditional density-based k -mediods algorithm and the state-of-the-arts trajectory clustering methods. The results demonstrate that IKMD significantly outperforms existing algorithms in the cost of distance calculation and the convergence speed. The methods proposed is proved to contribute to a larger effort targeted at advancing the study of intelligent trajectory data analytics.

Details DOI

UAI Conference 2022 Conference Paper

Mutual information based Bayesian graph neural network for few-shot learning

Kaiyu Song
Kun Yue
Liang Duan
Mingze Yang
Angsheng Li

In the deep neural network based few-shot learning, the limited training data may make the neural network extract ineffective features, which leads to inaccurate results. By Bayesian graph neural network (BGNN), the probability distributions on hidden layers imply useful features, and the few-shot learning could improved by establishing the correlation among features. Thus, in this paper, we incorporate mutual information (MI) into BGNN to describe the correlation, and propose an innovative framework by adopting the Bayesian network with continuous variables (BNCV) for effective calculation of MI. First, we build the BNCV simultaneously when calculating the probability distributions of features from the Dropout in hidden layers of BGNN. Then, we approximate the MI values efficiently by probabilistic inferences over BNCV. Finally, we give the correlation based loss function and training algorithm of our BGNN model. Experimental results show that our MI based BGNN framework is effective for few-shot learning and outperforms some state-of-the-art competitors by large margins on accuracy.

Details

TIST Journal 2021 Journal Article

A Dynamic Convolutional Neural Network Based Shared-Bike Demand Forecasting Model

Shaojie Qiao
Nan Han
Jianbin Huang
Kun Yue
Rui Mao
Hongping Shu
Qiang He
Xindong Wu

Bike-sharing systems are becoming popular and generate a large volume of trajectory data. In a bike-sharing system, users can borrow and return bikes at different stations. In particular, a bike-sharing system will be affected by weather, the time period, and other dynamic factors, which challenges the scheduling of shared bikes. In this article, a new shared-bike demand forecasting model based on dynamic convolutional neural networks, called SDF, is proposed to predict the demand of shared bikes. SDF chooses the most relevant weather features from real weather data by using the Pearson correlation coefficient and transforms them into a two-dimensional dynamic feature matrix, taking into account the states of stations from historical data. The feature information in the matrix is extracted, learned, and trained with a newly proposed dynamic convolutional neural network to predict the demand of shared bikes in a dynamical and intelligent fashion. The phase of parameter update is optimized from three aspects: the loss function, optimization algorithm, and learning rate. Then, an accurate shared-bike demand forecasting model is designed based on the basic idea of minimizing the loss value. By comparing with classical machine learning models, the weight sharing strategy employed by SDF reduces the complexity of the network. It allows a high prediction accuracy to be achieved within a relatively short period of time. Extensive experiments are conducted on real-world bike-sharing datasets to evaluate SDF. The results show that SDF significantly outperforms classical machine learning models in prediction accuracy and efficiency.

Details DOI

AIIM Journal 2019 Journal Article

A novel Chinese herbal medicine clustering algorithm via artificial bee colony optimization

Nan Han
Shaojie Qiao
Guan Yuan
Ping Huang
Dingxiang Liu
Kun Yue

Traditional Chinese medicine (TCM) has become popular and been viewed as an effective clinical treatment across the world. Accordingly, there is an ever-increasing interest in performing data analysis over TCM data. Aiming to cope with the problem of excessively depending on empirical values when selecting cluster centers by traditional clustering algorithms, an improved artificial bee colony algorithm is proposed by which to automatically select cluster centers and apply it to aggregate Chinese herbal medicines. The proposed method integrates the following new techniques: (1) improving the artificial bee colony algorithm by applying a new searching strategy of neighbour nectar, (2) employing the improved artificial bee colony algorithm to optimize the parameters of the cutoff distance d c, the local density ρ i and the minimum distance δ i between the element i and any other element with higher density in the cluster algorithm by fast search and finding of density peaks (called DP algorithm) to find the optimal cluster centers, in order to clustering herbal medicines in an accurate fashion with the guarantee of runtime performance. Extensive experiments were conducted on the UCI benchmark datasets and the TCM datasets and the results verify the effectiveness of the proposed method by comparing it with classical clustering algorithms including K-means, K-mediods and DBSCAN in multiple evaluation metrics, that is, Silhouette Coefficient, Entropy, Purity, Precision, Recall and F1-Measure. The results show that the IABC-DP algorithm outperforms other approaches with good clustering quality and accuracy on the UCI and the TCM datasets as well. In addition, it can be found that the improved artificial bee colony algorithm can effectively reduce the number of iterations when compared to the traditional bee colony algorithm. In particular, the IABC-DP algorithm is applied to cluster multi-dimensional Chinese herbal medicines and the result shows that it outperforms other clustering algorithms in clustering Chinese herbal medicines, which can contribute to a larger effort targeted at advancing the study of discovering composition rules of traditional Chinese prescriptions.

Details DOI