Author name cluster

Changjun Wang

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.

16 papers

1 author row

JBHI Journal 2025 Journal Article

A Knowledge-Guided Multi-modal Neural Network for Breast Cancer Molecular Subtyping

Jinlin Ye
Yuhan Liu
Shangjie Ren
Changjun Wang
Yidong Zhou
Liang Yang
Wei Zhang

Precise determination of HER2 subtype is essential for selecting appropriate targeted therapies in breast cancer. However, current HER2 assessment methods remain dependent on invasive tissue biopsies, which are limited by tumor heterogeneity and sampling bias. To address these challenges, this paper proposes a knowledge-guided multi-modal neural network (KMNet) for non-invasive HER2 subtyping by integrating clinical data and ultrasound images. KMNet introduces a Graph-based Clinical Feature encoder (GCF), which constructs a causal graph among clinical indicators based on medical knowledge and extracts high-order feature relationships via the Graph Convolutional Network (GCN). Meanwhile, the Convolutional Neural Network (CNN) and Vision Transformer (ViT)-based hybrid image encoder (CVUIF) captures both local details (calcifications and blood flow) and global dependencies between intra- and peritumoral regions. In addition, the Reduced Dimensional Fusion (RDF) module integrates key information from clinical graph features, ultrasound image features, and structured clinical data to construct a unified multi-modal representation for downstream HER2 subtyping task. Experiments were conducted on the private datasets (HER2USC) and the public datasets (BCW, BCa and SIIM-ISIC). Experimental results demonstrate that KMNet outperformed other reported state-ofthe- art multi-modal algorithms in HER2 subtyping task, offering strong potential for clinical decision support in breast cancer treatment.

Details DOI

JBHI Journal 2025 Journal Article

Chaos-MLP: Chaotic Transform MLP-Like Architecture for Medical Images Multi-Label Recognition Task

Mengjian Zhang
Guihua Wen
Pei Yang
Changjun Wang
Xuhui Huang
Chuyun Chen

The theory of “three-stage prevention” in view of the body constitution is the key technology of modern Chinese medicine for “Preventive Treatment of Diseases”. In particular, automated body constitution recognition (BCR) is an integral part of intelligent Traditional Chinese Medicine (TCM), which is extremely valuable for disease prevention and diagnosis. Actually, BCR is a challenging multi-label recognition task by the TCM composite constitution theory. First, two new databases are constructed, one is a multi-label facial body constitution (MFBC), and another is a multi-label tongue body constitution (MTBC). Second, a novel MLP-like architecture, named Chaos-MLP, is designed for the BCR task, which interacts with the channel chaotic features of extracted medical images and fuses them with the width and height channel direction features, respectively. Notably, the chaotic transform can enhance the distinguishability of extracted features from the medical images. Moreover, we propose a binary center cognitive gravity loss (BCCGL) to enhance the learning ability of the Chaos-MLP for unbalanced body constitution labels. Our proposed method shows superior performance on both MFBC and MTBC datasets than other state-of-the-art (SOTA) MLP-like networks and a vision graph-based neural network (VGNN), which include Wave-MLP, Cycle-MLP, Vip, and Active-MLP.

Details DOI

JBHI Journal 2023 Journal Article

MLP-Like Model With Convolution Complex Transformation for Auxiliary Diagnosis Through Medical Images

Mengjian Zhang
Guihua Wen
Jiahui Zhong
Dongliang Chen
Changjun Wang
Xuhui Huang
Shijun Zhang

Medical images such as facial and tongue images have been widely used for intelligence-assisted diagnosis, which can be regarded as the multi-label classification task for disease location (DL) and disease nature (DN) of biomedical images. Compared with complicated convolutional neural networks and Transformers for this task, recent MLP-like architectures are not only simple and less computationally expensive, but also have stronger generalization capabilities. However, MLP-like models require better input features from the image. Thus, this study proposes a novel convolution complex transformation MLP-like (CCT-MLP) model for the multi-label DL and DN recognition task for facial and tongue images. Notably, the convolutional Tokenizer and multiple convolutional layers are first used to extract the better shallow features from input biomedical images to make up for the loss of spatial information obtained by the simple MLP structure. Subsequently, the Channel-MLP architecture with complex transformations is used to extract deep-level contextual features. In this way, multi-channel features are extracted and mixed to perform the multi-label classification of the input biomedical images. Experimental results on our constructed multi-label facial and tongue image datasets demonstrate that our method outperforms existing methods in terms of both accuracy (Acc) and mean average precision (mAP).

Details DOI

TCS Journal 2023 Journal Article

Optimally integrating ad auction into e-commerce platforms

Weian Li
Qi Qi
Changjun Wang
Changyuan Yu

Advertising becomes one of the most popular ways of monetizing an online transaction platform. Usually, sponsored advertisements are posted on the most attractive positions to enhance the number of clicks. However, multiple e-commerce platforms are aware that this action may hurt the search experience of users, even though it can bring more incomes. To balance the advertising revenue and the user experience loss caused by advertisements, most e-commerce platforms choose fixing some areas for advertisements and adopting some restrictions on the number of ads, such as a fixed number K of ads or one advertisement for every N organic searched results. Different from these common rules of treating the allocation of ads separately (from the arrangements of the organic searched items), in this work we build up an integrated system with mixed arrangements of advertisements and organic items. We focus on the design of truthful mechanisms to properly list the advertisements and organic items and optimally trade off the instant revenue and the user experience. Furthermore, for different settings and practical requirements, we extend our optimal truthful allocation mechanisms to cater for these realistic conditions. Finally, we exert several experiments to verify the improvement of our mechanism compared to the common-used advertising mechanism.

Details DOI

TCS Journal 2022 Journal Article

Mechanisms for dual-role-facility location games: Truthfulness and approximability

Xujin Chen
Minming Li
Changjun Wang
Chenhao Wang
Mengqi Zhang
Yingchao Zhao

This paper studies the dual-role-facility location game with generalized service costs, in which every agent plays a dual role of facility and customer, and is associated with a facility opening cost as his private information. The agents strategically report their opening costs to a mechanism which maps the reports to a set of selected agents and payments to them. Each selected agent opens his facility, incurs his opening cost and receives the payment the mechanism sets for him. Each unselected agent incurs a services cost that is determined by the set of selected agents in a very general way. The mechanism is truthful if under it no agent has an incentive to misreport. We provide a necessary and sufficient condition for mechanisms of the game to be truthful. This characterization particularly requires an invariant service cost for each unselected agent, which is a remarkable difference from related work in literature. As applications of this truthfulness characterization, we focus on the classic metric-space setting, in which agents' service costs equal their distances to closest open facilities. We present truthful mechanisms that minimize or approximately minimize the maximum cost among all agents and the total cost of all agents, respectively. Moreover, when the total payment cannot exceed a given budget, we prove, for both cost-minimization objectives, lower and upper bounds on approximation ratios of truthful mechanisms that satisfy the budget constraint.

Details DOI

JBHI Journal 2022 Journal Article

Task-Coupling Elastic Learning for Physical Sign-Based Medical Image Classification

Yingxue Xu
Guihua Wen
Pei Yang
Baochao Fan
Yang Hu
Mingnan Luo
Changjun Wang

Physical signs of patients indicate crucial evidence for diagnosing both location and nature of the disease, where there is a sequential relationship between the two tasks. Thus their joint learning can utilize intrinsic association by transferring related knowledge across relevant tasks. Choosing the right time to transfer is a critical problem for joint learning. However, how to dynamically adjust when tasks interact to capture the right time for transferring related knowledge is still an open issue. To this end, we propose a Task-Coupling Elastic Learning (TCEL) framework to model the task relatedness for classifying disease-location and disease-nature based on physical sign images. The main idea is to dynamically transfer relevant knowledge by progressively shifting task-coupling from loose to tight during the multi-stage training. In the early stage of training, we relax the constraints of modeling relations to focus more in learning the generic task-common features. In the later stage, the semantic guidance will be strengthened to learn the task-specific features. Specifically, a dynamic sequential module (DSM) is proposed to explicitly model the sequential relationship and enable multi-stage training. Moreover, to address the side effect of DSM, a new loss regularization is proposed. The extensive experiments on these two clinical datasets show the superiority of the proposed method over the baselines, and demonstrate the effectiveness of the proposed task-coupling elastic mechanism.

Details DOI

AIIM Journal 2021 Journal Article

Fully-channel regional attention network for disease-location recognition with tongue images

Yang Hu
Guihua Wen
Mingnan Luo
Pei Yang
Dan Dai
Zhiwen Yu
Changjun Wang
Wendy Hall

Objective Using the deep learning model to realize tongue image-based disease location recognition and focus on solving two problems: 1. The ability of the general convolution network to model detailed regional tongue features is weak; 2. Ignoring the group relationship between convolution channels, which caused the high redundancy of the model. Methods To enhance the convolutional neural networks. In this paper, a stochastic region pooling method is proposed to gain detailed regional features. Also, an inner-imaging channel relationship modeling method is proposed to model multi-region relations on all channels. Moreover, we combine it with the spatial attention mechanism. Results The tongue image dataset with the clinical disease-location label is established. Abundant experiments are carried out on it. The experimental results show that the proposed method can effectively model the regional details of tongue image and improve the performance of disease location recognition. Conclusion In this paper, we construct the tongue image dataset with disease-location labels to mine the relationship between tongue images and disease locations. A novel fully-channel regional attention network is proposed to model the local detail tongue features and improve the modeling efficiency. Significance The applications of deep learning in tongue image disease-location recognition and the proposed innovative models have guiding significance for other assistant diagnostic tasks. The proposed model provides an example of efficient modeling of detailed tongue features, which is of great guiding significance for other auxiliary diagnosis applications.

Details DOI

AIIM Journal 2019 Journal Article

Complexity perception classification method for tongue constitution recognition

Jiajiong Ma
Guihua Wen
Changjun Wang
Lijun Jiang

The body constitution is much related to the diseases and the corresponding treatment programs in Traditional Chinese Medicine. It can be recognized by the tongue image diagnosis, so that it is essentially regarded as a problem of tongue image classification, where each tongue image is classified into one of nine constitution types. This paper first presents a system framework to automatically identify the constitution through natural tongue images, where deep convolutional neural networks are carefully designed for tongue coating detection, tongue coating calibration, and constitution recognition. Under the system framework, a novel complexity perception (CP) classification method is proposed to nicely perform the constitution recognition, which can better deal with the bad influence of the variation of environmental condition and the uneven distribution of the tongue images on constitution recognition performance. CP performs the constitution recognition based on the complexity of individual tongue images by selecting the classifier with the corresponding complexity. To evaluate the performance of the proposed method, experiments are conducted on three sizes of clinic tongue images from hospitals. The experimental results illustrate that CP is effective to improve the accuracy of body constitution recognition.

Details DOI

AAMAS Conference 2019 Conference Paper

Truthful Mechanisms for Location Games of Dual-Role Facilities

Xujin Chen
Minming Li
Changjun Wang
Chenhao Wang
Yingchao Zhao

This paper is devoted to the facility location games with payments, where every agent plays a dual role of facility and customer. In this game, each selfish agent is located on a publicly known location in a metric space, and can allow a facility to be opened at his place. But the opening cost is his private information and he may strategically report this opening cost. Besides, each agent also bears a service cost equal to the distance to his nearest open facility. We are concerned with designing truthful mechanisms for the game, which, given agents’ reports, output a set of agents whose facilities could be opened, and a payment to each of these agents who opens a facility. The objective is to minimize (exactly or approximately) the social cost (the total opening and service costs) or the maximum agent cost of the outcome. We characterize the normalized truthful mechanisms for this game. Concerning the minimum social-cost objective, we give an optimal truthful mechanism without regard to time complexity, and show a small gap between the best known approximation ratio of polynomial-time truthful mechanisms for the game and that of polynomial-time approximation algorithms for the counterpart of pure optimization. For the minimum maximum-cost objective, we provide an optimal truthful mechanism which runs in polynomial time. We also investigate mechanism design for the game under a budget on the total payment.

PDF

IJCAI Conference 2017 Conference Paper

Efficient Mechanism Design for Online Scheduling (Extended Abstract)

Xujin Chen
Xiaodong Hu
Tie-Yan Liu
Weidong Ma
Tao Qin
Pingzhong Tang
Changjun Wang
Bo Zheng

This work concerns the mechanism design for online scheduling in a strategic setting. In this setting, each job is owned by a self-interested agent who may misreport the release time, deadline, length, and value of her job, while we need to determine not only the schedule of the jobs, but also the payment of each agent. We focus on the design of incentive compatible (IC) mechanisms, and study the maximization of social welfare (i. e. , the aggregated value of completed jobs) by competitive analysis. We first derive two lower bounds on the competitive ratio of any deterministic IC mechanism to characterize the landscape of our research: one bound is 5, which holds for equal-length jobs; the other bound is $\frac{\kappa}{\ln\kappa}+1-o(1)$, which holds for unequal-length jobs, where $\kappa$ is the maximum ratio between lengths of any two jobs. We then propose a deterministic IC mechanism and show that such a simple mechanism works very well for two models: (1) In the preemption-restart model, the mechanism can achieve the optimal competitive ratio of 5 for equal-length jobs and a near optimal ratio of $(\frac{1}{(1-\epsilon)^2}+o(1)) \frac{\kappa}{\ln\kappa}$ for unequal-length jobs, where $0<\epsilon<1$ is a small constant; (2) In the preemption-resume model, the mechanism can achieve the optimal competitive ratio of 5 for equal-length jobs and a near optimal competitive ratio (within factor 2) for unequal-length jobs.

PDF Details

I&C Journal 2017 Journal Article

Finding connected k -subgraphs with high density

Xujin Chen
Xiaodong Hu
Changjun Wang

Given an edge-weighted connected graph G on n vertices and a positive integer k ≤ n, a subgraph of G on k vertices is called a k-subgraph in G. We design combinatorial approximation algorithms for finding a connected k-subgraph in G such that its weighted density is at least a factor Ω ( max ⁡ { 1 / k, k 2 / n 2 } ) of the maximum weighted density among all k-subgraph in G (which are not necessarily connected), where max ⁡ { 1 / k, k 2 / n 2 } ≥ n − 2 / 3 implies an O ( n 2 / 3 ) -approximation ratio. We obtain improved O ( n 2 / 5 ) -approximation for unit weights. These particularly provide the first non-trivial approximations for the heaviest/densest connected k-subgraph problem on general graphs. We also give O ( n log ⁡ n ) -approximation for the problem on general weighted interval graphs.

Details DOI

TCS Journal 2016 Journal Article

Approximation for the minimum cost doubly resolving set problem

Xujin Chen
Xiaodong Hu
Changjun Wang

Locating source of diffusion in networks is crucial for controlling and preventing epidemic risks. It has been studied under various probabilistic models. In this paper, we study source location from a deterministic point of view by modeling it as the minimum cost doubly resolving set (DRS) problem, which is a strengthening of the well-known metric dimension problem. Let G be an undirected graph on n vertices, where each vertex has a nonnegative cost. A vertex subset S of G is a doubly resolving set (DRS) of G if for every pair of vertices u, v in G, there exist x, y ∈ S such that the difference of distances (in terms of number of edges) between u and x, y is not equal to the difference of distances between v and x, y. The minimum cost DRS problem consists of finding a DRS in G with minimum total cost. We establish Θ ( ln ⁡ n ) approximability of the minimum DRS problem on general graphs for both weighted and unweighted versions. This provides the first explicit lower and upper bounds on approximation for the minimum (cost) DRS, which are nearly tight. Moreover, we design the first known strongly polynomial time exact algorithms for the minimum cost DRS problem on general wheels and trees with additional constant k ≥ 0 edges.

Details DOI

JAIR Journal 2016 Journal Article

Efficient Mechanism Design for Online Scheduling

Xujin Chen
Xiaodong Hu
Tie-Yan Liu
Weidong Ma
Tao Qin
Pingzhong Tang
Changjun Wang
Bo Zheng

This paper concerns the mechanism design for online scheduling in a strategic setting. In this setting, each job is owned by a self-interested agent who may misreport the release time, deadline, length, and value of her job, while we need to determine not only the schedule of the jobs, but also the payment of each agent. We focus on the design of incentive compatible (IC) mechanisms, and study the maximization of social welfare (i.e., the aggregated value of completed jobs) by competitive analysis. We first derive two lower bounds on the competitive ratio of any deterministic IC mechanism to characterize the landscape of our research. We then propose a deterministic IC mechanism and show that such a simple mechanism works very well for both the preemption-restart model and the preemption-resume model. We show the mechanism can achieve the optimal competitive ratio of 5 for equal-length jobs and a near optimal competitive ratio (within a constant factor) for unequal-length jobs.

PDF Details DOI

IJCAI Conference 2015 Conference Paper

Selling Reserved Instances in Cloud Computing

Changjun Wang
Weidong Ma
Tao Qin
Xujin Chen
Xiaodong Hu
Tie-Yan Liu

In this paper, we study the problem of designing new mechanisms for selling reserved instances (also referred to as virtual machines) in cloud computing. Unlike the practice in today’s clouds in which users only have a few predefined options to reserve instances (i. e. , either 1-year reservation or 3-year reservation), we allow users to reserve resources for any length and from any time point in the future. Our goal is to maximize the social welfare. We propose two mechanisms, one for the case where all the jobs are tight (their lengths are exactly their reservation time intervals), and the other for the more general case where jobs are delayable and have some flexibility on their reservations. Both of the mechanisms are prompt in the sense that the acceptance and the payment for a job is determined at the very moment of its arrival. We use competitive analysis to evaluate the performance of our mechanisms, and show that both of the mechanisms have a competitive ratio of O(ln(kT)) under some mild assumption, where k (res. T) is the maximum ratio between per-instance-hour valuation (res. length) of any two jobs. We then prove that no algorithm can achieve a competitive ratio better than ln(2kT) under the same assumption. Therefore, our mechanisms are optimal within a constant factor.

PDF Details

TCS Journal 2014 Journal Article

Schedules for marketing products with negative externalities

Zhigang Cao
Xujin Chen
Changjun Wang

With the fast development of social network services, network marketing of products with externalities has been attracting more and more attention from both academia and business. The extensive study on network marketing mainly concerns with positive externalities. The focus of this paper is on the much less understood counterpart for negative externalities, where a consumer has lower incentive to buy a product as the product is possessed by more social network neighbors. For a seller who markets these products, it is desirable to have a good schedule which specifies an order of consumers he approaches. We design polynomial time algorithms that find marketing schedules for products with negative externalities. The goals are two-fold: maximizing the product sale and ensuring consumer regret-free decisions. We show that the maximization is NP-hard. Our algorithms achieve satisfactory performance guarantees, approximating the maximum within constant factors in most of the cases. Two of these algorithms provide regret-proof schedules, reaching an equilibrium state where no consumers regret their previous decisions. Our work is the first attempt to address these marketing problems from an algorithmic point of view.

Details DOI

TCS Journal 2013 Journal Article

Reducing price of anarchy of selfish task allocation with more selfishness

Xujin Chen
Xiaodong Hu
Weidong Ma
Changjun Wang

In this paper we consider the task allocation problem from a new game theoretic perspective. We assume that tasks and machines are both controlled by selfish agents with two distinct objectives, which stands in contrast to the passive role of machines in the traditional model of selfish task allocation. To characterize the outcome of this new game where two classes of players interact, we introduce the concept of dual equilibrium. We prove that the price of anarchy with respect to dual equilibria is 1. 4, which is considerably smaller than the counterpart 2 in the traditional model. Our study shows that activating more freedom and selfishness in a game may bring about a better global outcome.

Details DOI