Author name cluster

Miao Xu

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.

23 papers

2 author rows

NeurIPS Conference 2025 Conference Paper

ComRank: Ranking Loss for Multi-Label Complementary Label Learning

Jing-Yi Zhu
Yi Gao
Miao Xu
Min-Ling Zhang

Multi-label complementary label learning (MLCLL) is a weakly supervised paradigm that addresses multi-label learning (MLL) tasks using complementary labels (i. e. , irrelevant labels) instead of relevant labels. Existing methods typically adopt an unbiased risk estimator (URE) under the assumption that complementary labels follow a uniform distribution. However, this assumption fails in real-world scenarios due to instance-specific annotation biases, making URE-based methods ineffective under such conditions. Furthermore, existing methods underutilize label correlations inherent in MLL. To address these limitations, we propose ComRank, a ranking loss framework for MLCLL, which encourages complementary labels to be ranked lower than non-complementary ones, thereby modeling pairwise label relationships. Theoretically, our surrogate loss ensures Bayes consistency under both uniform and biased cases. Experiments demonstrate the effectiveness of our method in MLCLL tasks. The code is available at https: //github. com/JellyJamZhu/ComRank.

PDF Details

AAAI Conference 2025 Conference Paper

Toward Efficient Data-Free Unlearning

Chenhao Zhang
Shaofei Shen
Weitong Chen
Miao Xu

Machine unlearning without access to real data distribution is challenging. The existing method based on data-free distillation achieved unlearning by filtering out synthetic samples containing forgetting information but struggled to distill the retaining-related knowledge efficiently. In this work, we analyze that such a problem is due to over-filtering, which reduces the synthesized retaining-related information. We propose a novel method, Inhibited Synthetic PostFilter (ISPF), to tackle this challenge from two perspectives: First, the Inhibited Synthetic, by reducing the synthesized forgetting information; Second, the PostFilter, by fully utilizing the retaining-related information in synthesized samples. Experimental results demonstrate that the proposed ISPF effectively tackles the challenge and outperforms existing methods.

PDF Details DOI

EAAI Journal 2024 Journal Article

Ensemble learning based approach for traffic incident detection and multi-category classification

Miao Xu
Hongfei Liu
Hongbo Yang

Traffic incident is one of the important causes of road congestion. Traffic incident detection plays a crucial role in the safety application of intelligent transportation systems, which provides timely information for traffic management departments and reducing losses. Despite many researches on incident detection approach, the identification of different incident categories is not enough. In addition, traffic incident detection is still a challenging task due to the problem of data imbalance and feature selection. In this study, we propose a two-stage traffic incident detection framework based on ensemble learning. In the first stage, a binary classification algorithm based on XGBoost (eXtreme Gradient Boosting) is established to detect whether there is a traffic incident, and 24 feature variables are determined by model feature selection. In the second stage, three resampling algorithms are utilized to reconstruct and balance the dataset. Through comparative analysis, SMOTE (Synthetic Minority Over-sampling Technique)-XGBoost is the best method for incident multi-category classification with precision of 87. 27%, 78. 52% and 92. 54%, respectively. Moreover, the baseline comparison experiments are conducted to evaluate our model performance with real-word datasets. The proposed model achieves the highest average accuracy of 93. 45% in the first stage and the macro-precision of 86. 11% in the second stage. The results indicate that the proposed method outperforms baselines and the two-stage framework can accurately realize the incident detection and multi-category classification.

Details DOI

AAAI Conference 2024 Conference Paper

Inspecting Prediction Confidence for Detecting Black-Box Backdoor Attacks

Tong Wang
Yuan Yao
Feng Xu
Miao Xu
Shengwei An
Ting Wang

Backdoor attacks have been shown to be a serious security threat against deep learning models, and various defenses have been proposed to detect whether a model is backdoored or not. However, as indicated by a recent black-box attack, existing defenses can be easily bypassed by implanting the backdoor in the frequency domain. To this end, we propose a new defense DTInspector against black-box backdoor attacks, based on a new observation related to the prediction confidence of learning models. That is, to achieve a high attack success rate with a small amount of poisoned data, backdoor attacks usually render a model exhibiting statistically higher prediction confidences on the poisoned samples. We provide both theoretical and empirical evidence for the generality of this observation. DTInspector then carefully examines the prediction confidences of data samples, and decides the existence of backdoor using the shortcut nature of backdoor triggers. Extensive evaluations on six backdoor attacks, four datasets, and three advanced attacking types demonstrate the effectiveness of the proposed defense.

PDF Details DOI

IJCAI Conference 2024 Conference Paper

Machine Unlearning: Challenges in Data Quality and Access

Miao Xu

Machine unlearning aims to remove specific knowledge from a well-trained machine learning model. This topic has gained significant attention recently due to the widespread adoption of machine learning models across various applications and the accompanying privacy, legal, and ethical considerations. During the unlearning process, models are typically presented with data that specifies which information should be erased and which should be retained. Nonetheless, practical challenges arise due to prevalent issues of data quality issues and access restrictions. This paper explores these challenges and introduces strategies to address problems related to unsupervised data, weakly supervised data, and scenarios characterized by zero-shot and federated data availability. Finally, we discuss related open questions, particularly concerning evaluation metrics, how the forgetting information is represented and delivered, and the unique challenges posed by large generative models.

PDF Details DOI

TIST Journal 2024 Journal Article

Mitigating the Impact of Inaccurate Feedback in Dynamic Learning-to-Rank: A Study of Overlooked Interesting Items

Chenhao Zhang
Weitong Chen
Wei Zhang
Miao Xu

Dynamic Learning-to-Rank (DLTR) is a method of updating a ranking policy in real time based on user feedback, which may not always be accurate. Although previous DLTR work has achieved fair and unbiased DLTR under inaccurate feedback, they face the tradeoff between fairness and user utility and also have limitations in the setting of feeding items. Existing DLTR works improve ranking utility by eliminating bias from inaccurate feedback on observed items, but the impact of another pervasive form of inaccurate feedback, overlooked or ignored interesting items, remains unclear. For example, users may browse the rankings too quickly to catch interesting items or miss interesting items because the snippets are not optimized enough. This phenomenon raises two questions: (i) Will overlooked interesting items affect the ranking results? and (ii) Is it possible to improve utility without sacrificing fairness if these effects are eliminated? These questions are particularly relevant for small and medium-sized retailers who are just starting out and may have limited data, leading to the use of inaccurate feedback to update their models. In this article, we find that inaccurate feedback in the form of overlooked interesting items has a negative impact on DLTR performance in terms of utility. To address this, we treat the overlooked interesting items as noise and propose a novel DLTR method, the Co-teaching Rank (CoTeR), that has good utility and fairness performance when inaccurate feedback is present in the form of overlooked interesting items. Our solution incorporates a co-teaching-based component with a customized loss function and data sampling strategy, as well as a mean pooling strategy to further accommodate newly added products without historical data. Through experiments, we demonstrate that CoTeR not only enhances utilities but also preserves ranking fairness and can smoothly handle newly introduced items.

Details DOI

IJCAI Conference 2024 Conference Paper

Unlearning from Weakly Supervised Learning

Yi Tang
Yi Gao
Yong-gang Luo
Ju-Cheng Yang
Miao Xu
Min-Ling Zhang

Machine unlearning provides users with the right to remove their privacy data from a well-trained model. Existing approaches of machine unlearning mainly focus on exploring data removing within supervised learning (SL) tasks. However, weakly supervised learning (WSL) is more applicable to real-world scenarios since collecting WSL data is less laborious than collecting fully supervised data. In this paper, we first propose a machine unlearning approach for WSL by updating the model parameters. Motivated by the uniform distributions of untrained model predictions, we derive a formulated target to force the model's predictions of removed data to be indistinguishable. This encourages the model to forget its ability to recognize features of data slated for unlearning. Moreover, we employ formulated targets to transform the classification unlearning into the convex regression, which can significantly reduce computational cost and avoid extra information storage during the training process. Additionally, we discuss how to design a target to ensure the models' predictions of removed data being indistinguishable in different learning scenarios, e. g. , SL or WSL. As the flexibility in formulating targets, the proposed approach effectively deals with the WSL problem while still excels in SL models. Empirical studies show the superiority of the proposed approach.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

What Makes Partial-Label Learning Algorithms Effective?

Jiaqi Lv
Yangfan Liu
Shiyu Xia
Ning Xu
Miao Xu
Gang Niu
Min-Ling Zhang
Masashi Sugiyama

A partial label (PL) specifies a set of candidate labels for an instance and partial-label learning (PLL) trains multi-class classifiers with PLs. Recently, many methods that incorporate techniques from other domains have shown strong potential. The expectation that stronger techniques would enhance performance has resulted in prominent PLL methods becoming not only highly complicated but also quite different from one another, making it challenging to choose the best direction for future algorithm design. While it is exciting to see higher performance, this leaves open a fundamental question: what makes a PLL method effective? We present a comprehensive empirical analysis of this question and summarize the success of PLL so far into some minimal algorithm design principles. Our findings reveal that high accuracy on benchmark-simulated datasets with PLs can misleadingly amplify the perceived effectiveness of some general techniques, which may improve representation learning but have limited impact on addressing the inherent challenges of PLs. We further identify the common behavior among successful PLL methods as a progressive transition from uniform to one-hot pseudo-labels, highlighting the critical role of mini-batch PL purification in achieving top performance. Based on our findings, we introduce a minimal working algorithm that is surprisingly simple yet effective, and propose an improved strategy to implement the design principles, suggesting a promising direction for improvements in PLL.

PDF Details DOI

IJCAI Conference 2023 Conference Paper

Unbiased Risk Estimator to Multi-Labeled Complementary Label Learning

Yi Gao
Miao Xu
Min-Ling Zhang

Multi-label learning (MLL) usually requires assigning multiple relevant labels to each instance. While a fully supervised MLL dataset needs a large amount of labeling effort, using complementary labels can help alleviate this burden. However, current approaches to learning from complementary labels are mainly designed for multi-class learning and assume that each instance has a single relevant label. This means that these approaches cannot be easily applied to MLL when only complementary labels are provided, where the number of relevant labels is unknown and can vary across instances. In this paper, we first propose the unbiased risk estimator for the multi-labeled complementary label learning (MLCLL) problem. We also provide an estimation error bound to ensure the convergence of the empirical risk estimator. In some cases, the unbiased estimator may give unbounded gradients for certain loss functions and result in overfitting. To mitigate this problem, we improve the risk estimator by minimizing a proper loss function, which has been shown to improve gradient updates. Our experimental results demonstrate the effectiveness of the proposed approach on various datasets.

PDF Details DOI

JBHI Journal 2022 Journal Article

Personalized On-Device E-Health Analytics With Decentralized Block Coordinate Descent

Guanhua Ye
Hongzhi Yin
Tong Chen
Miao Xu
Quoc Viet Hung Nguyen
Jiangning Song

Actuated by the growing attention to personal healthcare and the pandemic, the popularity of E-health is proliferating. Nowadays, enhancement on medical diagnosis via machine learning models has been highly effective in many aspects of e-health analytics. Nevertheless, in the classic cloud-based/centralized e-health paradigms, all the data will be centrally stored on the server to facilitate model training, which inevitably incurs privacy concerns and high time delay. Distributed solutions like Decentralized Stochastic Gradient Descent (D-SGD) are proposed to provide safe and timely diagnostic results based on personal devices. However, methods like D-SGD are subject to the gradient vanishing issue and usually proceed slowly at the early training stage, thereby impeding the effectiveness and efficiency of training. In addition, existing methods are prone to learning models that are biased towards users with dense data, compromising the fairness when providing E-health analytics for minority groups. In this paper, we propose a Decentralized Block Coordinate Descent (D-BCD) learning framework that can better optimize deep neural network-based models distributed on decentralized devices for E-health analytics. As a gradient-free optimization method, Block Coordinate Descent (BCD) mitigates the gradient vanishing issue and converges faster at the early stage compared with the conventional gradient-based optimization. To overcome the potential data scarcity issues for users’ local data, we propose similarity-based model aggregation that allows each on-device model to leverage knowledge from similar neighbor models, so as to achieve both personalization and high accuracy for the learned models. Benchmarking experiments on three real-world datasets illustrate the effectiveness and practicality of our proposed D-BCD, where additional simulation study showcases the strong applicability of D-BCD in real-life E-health scenarios.

Details DOI

NeurIPS Conference 2022 Conference Paper

Positive-Unlabeled Learning using Random Forests via Recursive Greedy Risk Minimization

Jonathan Wilton
Abigail Koay
Ryan Ko
Miao Xu
Nan Ye

The need to learn from positive and unlabeled data, or PU learning, arises in many applications and has attracted increasing interest. While random forests are known to perform well on many tasks with positive and negative data, recent PU algorithms are generally based on deep neural networks, and the potential of tree-based PU learning is under-explored. In this paper, we propose new random forest algorithms for PU-learning. Key to our approach is a new interpretation of decision tree algorithms for positive and negative data as \emph{recursive greedy risk minimization algorithms}. We extend this perspective to the PU setting to develop new decision tree learning algorithms that directly minimizes PU-data based estimators for the expected risk. This allows us to develop an efficient PU random forest algorithm, PU extra trees. Our approach features three desirable properties: it is robust to the choice of the loss function in the sense that various loss functions lead to the same decision trees; it requires little hyperparameter tuning as compared to neural network based PU learning; it supports a feature importance that directly measures a feature's contribution to risk minimization. Our algorithms demonstrate strong performance on several datasets. Our code is available at \url{https: //github. com/puetpaper/PUExtraTrees}.

PDF Details

EAAI Journal 2021 Journal Article

A flexible deep learning-aware framework for travel time prediction considering traffic event

Miao Xu
Hongfei Liu

Travel time is an important signal to measure the performance of transportation systems. However, urban traffic forecasting is still a challenging task due to the complicated nonlinear nature of urban traffic and the impact of abnormal traffic event. In this study, we propose a flexible deep learning-aware framework which is composed by integrating multiple components with a sequence-to-sequence (Seq2Seq) model as the main body. Specifically, we incorporate a newly designed hybrid adjacency matrix of graph convolution network and temporal attention mechanism to flexibly capture spatio-temporal dynamics accordingly. In addition, we design a responsive algorithm to obtain the latent representation of traffic event by applying stacked denoising autoencoder. We then conduct the baseline model comparison and ablation experiments to evaluate our model performance with real-word datasets. The results indicate that our method outperforms baselines and the fusion of traffic event data can improve prediction accuracy. Moreover, the case study and sensitivity analysis also have a reference value to the practical application of traffic prediction task.

Details DOI

IJCAI Conference 2021 Conference Paper

Positive-Unlabeled Learning from Imbalanced Data

Guangxin Su
Weitong Chen
Miao Xu

Positive-unlabeled (PU) learning deals with the binary classification problem when only positive (P) and unlabeled (U) data are available, without negative (N) data. Existing PU methods perform well on the balanced dataset. However, in real applications such as financial fraud detection or medical diagnosis, data are always imbalanced. It remains unclear whether existing PU methods can perform well on imbalanced data. In this paper, we explore this problem and propose a general learning objective for PU learning targeting specially at imbalanced data. By this general learning objective, state-of-the-art PU methods based on optimizing a consistent risk can be adapted to conquer the imbalance. We theoretically show that in expectation, optimizing our learning objective is equivalent to learning a classifier on the oversampled balanced data with both P and N data available, and further provide an estimation error bound. Finally, experimental results validate the effectiveness of our proposal compared to state-of-the-art PU methods.

PDF Details DOI

IJCAI Conference 2021 Conference Paper

Self-Supervised Adversarial Distribution Regularization for Medication Recommendation

Yanda Wang
Weitong Chen
Dechang Pi
Lin Yue
Sen Wang
Miao Xu

Medication recommendation is a significant healthcare application due to its promise in effectively prescribing medications. Avoiding fatal side effects related to Drug-Drug Interaction (DDI) is among the critical challenges. Most existing methods try to mitigate the problem by providing models with extra DDI knowledge, making models complicated. While treating all patients with different DDI properties as a single cohort would put forward strict requirements on models' generalization performance. In pursuit of a valuable model for a safe recommendation, we propose the Self-Supervised Adversarial Regularization Model for Medication Recommendation (SARMR). SARMR obtains the target distribution associated with safe medication combinations from raw patient records for adversarial regularization. In this way, the model can shape distributions of patient representations to achieve DDI reduction. To obtain accurate self-supervision information, SARMR models interactions between physicians and patients by building a key-value memory neural network and carrying out multi-hop reading to obtain contextual information for patient representations. SARMR outperforms all baseline methods in the experiment on a real-world clinical dataset. This model can achieve DDI reduction when considering the different number of DDI types, which demonstrates the robustness of adversarial regularization for safe medication recommendation.

PDF Details DOI

ICML Conference 2020 Conference Paper

Dynamic Knapsack Optimization Towards Efficient Multi-Channel Sequential Advertising

Xiaotian Hao
Zhaoqing Peng
Yi Ma 0005
Guan Wang
Junqi Jin
Jianye Hao
Shan Chen
Rongquan Bai

In E-commerce, advertising is essential for merchants to reach their target users. The typical objective is to maximize the advertiser’s cumulative revenue over a period of time under a budget constraint. In real applications, an advertisement (ad) usually needs to be exposed to the same user multiple times until the user finally contributes revenue (e. g. , places an order). However, existing advertising systems mainly focus on the immediate revenue with single ad exposures, ignoring the contribution of each exposure to the final conversion, thus usually falls into suboptimal solutions. In this paper, we formulate the sequential advertising strategy optimization as a dynamic knapsack problem. We propose a theoretically guaranteed bilevel optimization framework, which significantly reduces the solution space of the original optimization space while ensuring the solution quality. To improve the exploration efficiency of reinforcement learning, we also devise an effective action space reduction approach. Extensive offline and online experiments show the superior performance of our approaches over state-of-the-art baselines in terms of cumulative revenue.

Details

NeurIPS Conference 2020 Conference Paper

Provably Consistent Partial-Label Learning

Lei Feng
Jiaqi Lv
Bo Han
Miao Xu
Gang Niu
Xin Geng
Bo An
Masashi Sugiyama

Partial-label learning (PLL) is a multi-class classification problem, where each training example is associated with a set of candidate labels. Even though many practical PLL methods have been proposed in the last two decades, there lacks a theoretical understanding of the consistency of those methods - none of the PLL methods hitherto possesses a generation process of candidate label sets, and then it is still unclear why such a method works on a specific dataset and when it may fail given a different dataset. In this paper, we propose the first generation model of candidate label sets, and develop two PLL methods that are guaranteed to be provably consistent, i. e. , one is risk-consistent and the other is classifier-consistent. Our methods are advantageous, since they are compatible with any deep network or stochastic optimizer. Furthermore, thanks to the generation model, we would be able to answer the two questions above by testing if the generation model matches given candidate label sets. Experiments on benchmark and real-world datasets validate the effectiveness of the proposed generation model and two PLL methods.

PDF Details

NeurIPS Conference 2020 Conference Paper

Trading Personalization for Accuracy: Data Debugging in Collaborative Filtering

Long Chen
Yuan Yao
Feng Xu
Miao Xu
Hanghang Tong

Collaborative filtering has been widely used in recommender systems. Existing work has primarily focused on improving the prediction accuracy mainly via either building refined models or incorporating additional side information, yet has largely ignored the inherent distribution of the input rating data. In this paper, we propose a data debugging framework to identify overly personalized ratings whose existence degrades the performance of a given collaborative filtering model. The key idea of the proposed approach is to search for a small set of ratings whose editing (e. g. , modification or deletion) would near-optimally improve the recommendation accuracy of a validation set. Experimental results demonstrate that the proposed approach can significantly improve the recommendation accuracy. Furthermore, we observe that the identified ratings significantly deviate from the average ratings of the corresponding items, and the proposed approach tends to modify them towards the average. This result sheds light on the design of future recommender systems in terms of balancing between the overall accuracy and personalization.

PDF Details

AAAI Conference 2019 Conference Paper

Clipped Matrix Completion: A Remedy for Ceiling Effects

Takeshi Teshima
Miao Xu
Issei Sato
Masashi Sugiyama

We consider the problem of recovering a low-rank matrix from its clipped observations. Clipping is conceivable in many scientific areas that obstructs statistical analyses. On the other hand, matrix completion (MC) methods can recover a low-rank matrix from various information deficits by using the principle of low-rank completion. However, the current theoretical guarantees for low-rank MC do not apply to clipped matrices, as the deficit depends on the underlying values. Therefore, the feasibility of clipped matrix completion (CMC) is not trivial. In this paper, we first provide a theoretical guarantee for the exact recovery of CMC by using a trace-norm minimization algorithm. Furthermore, we propose practical CMC algorithms by extending ordinary MC methods. Our extension is to use the squared hinge loss in place of the squared loss for reducing the penalty of overestimation on clipped entries. We also propose a novel regularization term tailored for CMC. It is a combination of two trace-norm terms, and we theoretically bound the recovery error under the regularization. We demonstrate the effectiveness of the proposed methods through experiments using both synthetic and benchmark data for recommendation systems.

PDF Details

NeurIPS Conference 2018 Conference Paper

Co-teaching: Robust training of deep neural networks with extremely noisy labels

Bo Han
Quanming Yao
Xingrui Yu
Gang Niu
Miao Xu
Weihua Hu
Ivor Tsang
Masashi Sugiyama

Deep learning with noisy labels is practically challenging, as the capacity of deep models is so high that they can totally memorize these noisy labels sooner or later during training. Nonetheless, recent studies on the memorization effects of deep neural networks show that they would first memorize training data of clean labels and then those of noisy labels. Therefore in this paper, we propose a new deep learning paradigm called ''Co-teaching'' for combating with noisy labels. Namely, we train two deep neural networks simultaneously, and let them teach each other given every mini-batch: firstly, each network feeds forward all data and selects some data of possibly clean labels; secondly, two networks communicate with each other what data in this mini-batch should be used for training; finally, each network back propagates the data selected by its peer network and updates itself. Empirical results on noisy versions of MNIST, CIFAR-10 and CIFAR-100 demonstrate that Co-teaching is much superior to the state-of-the-art methods in the robustness of trained deep models.

PDF Details

IJCAI Conference 2017 Conference Paper

Incomplete Label Distribution Learning

Miao Xu
Zhi-Hua Zhou

Label distribution learning (LDL) assumes labels can be associated to an instance to some degree, thus it can learn the relevance of a label to a particular instance. Although LDL has got successful practical applications, one problem with existing LDL methods is that they are designed for data with \emph{complete} supervised information, while in reality, annotation information may be \emph{incomplete}, because assigning each label a real value to indicate its association with a particular instance will result in large cost in labor and time. In this paper, we will solve LDL problem when given \emph{incomplete} supervised information. We propose an objective based on trace norm minimization to exploit the correlation between labels. We develop a proximal gradient descend algorithm and an algorithm based on alternating direction method of multipliers. Experiments validate the effectiveness of our proposal.

PDF Details

AAAI Conference 2013 Conference Paper

Multi-Label Learning with PRO Loss

Miao Xu
Yu-Feng Li
Zhi-Hua Zhou

Multi-label learning methods assign multiple labels to one object. In practice, in addition to differentiating relevant labels from irrelevant ones, it is often desired to rank the relevant labels for an object, whereas the rankings of irrelevant labels are not important. Such a requirement, however, cannot be met because most existing methods were designed to optimize existing criteria, yet there is no criterion which encodes the aforementioned requirement. In this paper, we present a new criterion, PRO LOSS, concerning the prediction on all labels as well as the rankings of only relevant labels. We then propose ProSVM which optimizes PRO LOSS efficiently using alternating direction method of multipliers. We further improve its efficiency with an upper approximation that reduces the number of constraints from O(T2 ) to O(T), where T is the number of labels. Experiments show that our proposals are not only superior on PRO LOSS, but also highly competitive on existing evaluation criteria.

PDF Details

NeurIPS Conference 2013 Conference Paper

Speedup Matrix Completion with Side Information: Application to Multi-Label Learning

Miao Xu
Rong Jin
Zhi-Hua Zhou

In standard matrix completion theory, it is required to have at least $O(n\ln^2 n)$ observed entries to perfectly recover a low-rank matrix $M$ of size $n\times n$, leading to a large number of observations when $n$ is large. In many real tasks, side information in addition to the observed entries is often available. In this work, we develop a novel theory of matrix completion that explicitly explore the side information to reduce the requirement on the number of observed entries. We show that, under appropriate conditions, with the assistance of side information matrices, the number of observed entries needed for a perfect recovery of matrix $M$ can be dramatically reduced to $O(\ln n)$. We demonstrate the effectiveness of the proposed approach for matrix completion in transductive incomplete multi-label learning.

PDF Details

IS Journal 2008 Journal Article

The Creation Process of Chinese Calligraphy and Emulation of Imagery Thinking

Jun Dong
Miao Xu
Xian-jun Zhang
Yan-qing Gao
Yun-he Pan

Chinese calligraphy is both an art form and the embodiment of imagery thinking. The process of calligraphy involves studying tablets or documents, remembering the contents, and creating new artwork with calligraphic images from memory. All these steps are related to simulation intelligence, thought patterns, and cognition models. Ancient tablets were damaged by human hands and eroded by the environment, thus considerably degrading their original appearance. Automated reconstruction of the characters represented in the tablets, completed in the past by an experienced expert, is a necessary preprocessing stage that simulates the imagery thinking of calligraphy creation. Following reconstruction, a stroke-reforming approach based on statistical models generates new calligraphic styles. We present the results of this approach and discuss ongoing problems. This article is part of a special issue on AI in China.

Details DOI