Author name cluster

Hong Yu

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.

25 papers

1 author row

AAAI Conference 2026 Conference Paper

ChatCLIDS: Simulating Persuasive AI Dialogues to Promote Closed-Loop Insulin Adoption in Type 1 Diabetes Care

Zonghai Yao
Talha Chafekar
Junda Wang
Shuo Han
Feiyun Ouyang
Junhui Qian
Lingxi Li
Hong Yu

Real-world adoption of closed-loop insulin delivery systems (CLIDS) in type 1 diabetes remains low, driven not by technical failure, but by diverse behavioral, psychosocial, and social barriers. We introduce ChatCLIDS, the first benchmark to rigorously evaluate LLM–driven persuasive dialogue for health behavior change. Our framework features a library of expert-validated virtual patients, each with clinically grounded, heterogeneous profiles and realistic adoption barriers, and simulates multi-turn interactions with nurse agents equipped with a diverse set of evidence-based persuasive strategies. ChatCLIDS uniquely supports longitudinal counseling and adversarial social influence scenarios, enabling robust, multi-dimensional evaluation. Our findings reveal that while larger and more reflective LLMs adapt strategies over time, all models struggle to overcome resistance, especially under realistic social pressure. These results highlight critical limitations of current LLMs for behavior change, and offer a high-fidelity, scalable testbed for advancing trustworthy persuasive AI in healthcare and beyond.

PDF Details DOI

EAAI Journal 2026 Journal Article

Exploring semantic dependency for reasoning over temporal knowledge graph

Hong Yu
Meiqi Chen
Ronghua Tian
Yongfang Xie

Temporal knowledge graph reasoning aims to predict future facts based on given historical ones. When two entities that have had no historical interaction interact with each other, we call a new event occurs. Most existing methods suffer from limitations in predicting new events, as they only focus on direct historical interaction. To this end, we propose a temporal knowledge graph reasoning method by exploring semantic dependencies, abbreviated as SdTKG. It enriches the characterization of entities by capturing and representing potential semantic dependencies between entities with limited historical interactions. First, a potential semantic dependency graph and its encoder are constructed based on temporal path analysis to capture potential dependencies beyond direct historical interactions. Second, the entities with the similar stance to the target entity, which are mined by the potential semantic dependency graph, are used as positive samples; and then, self-supervised negative-free contrastive learning is employed on the positive samples to enhance the representation of potential semantic dependencies. Extensive experiments fully demonstrate that SdTKG is more competitive than ten state-of-the-art models. The mean reciprocal rank (MRR) values of SdTKG for relation prediction and new event prediction exceed those of the best baseline method 6. 47% and 5. 46% on average, respectively. The code is available at: https: //github. com/yuhongcqupt/SdTKG.

Details DOI

AAAI Conference 2026 Conference Paper

PRIME: Planning and Retrieval-Integrated Memory for Enhanced Reasoning

Hieu Tran
Zonghai Yao
Nguyen Luong Tran
Zhichao Yang
Feiyun Ouyang
Shuo Han
Razieh Rahimi
Hong Yu

Inspired by the dual-process theory of human cognition from Thinking, Fast and Slow, we introduce PRIME (Planning and Retrieval-Integrated Memory for Enhanced Reasoning), a multi-agent reasoning framework that dynamically integrates System 1 (fast, intuitive thinking) and System 2 (slow, deliberate thinking). PRIME first employs a Quick Thinking Agent to generate a rapid answer; if uncertainty is detected, it then triggers a structured System 2 reasoning pipeline composed of specialized agents for planning, hypothesis generation, retrieval, information integration, and decision-making. This multi-agent design mimics human cognitive processes faithfully and enhances both efficiency and accuracy. Experimental results with LLaMA 3 models demonstrate that PRIME enables open-source LLMs to perform competitively with state-of-the-art closed-source models like GPT-4 and GPT-4o on benchmarks requiring multi-hop and knowledge-grounded reasoning. This research establishes PRIME as a scalable solution for improving LLMs in domains requiring complex, knowledge-intensive reasoning.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Semantic-Augmented Image Clustering via Adaptive Multi-Modal Collaboration

Xiaohan Zhang
Chao Zhang
Deng Xu
Hong Yu
Chunlin Chen
Huaxiong Li

Image clustering is a fundamental task in unsupervised visual learning. While recent self-supervised methods have explored various pretext tasks to generate supervision signals for clustering, they typically depend exclusively on raw images, resulting in insufficient supervision signals that are inherently constrained by limited visual semantics. In this paper, we propose a novel Semantic-Augmented image Clustering (SAC) method, which transcends the inherent limitations of purely visual representations through the integration of external knowledge. Specifically, SAC utilizes Vision-Language pre-trained Models (VLMs) to flexibly generate textual descriptions for each image, providing external semantic cues to supplement the visual information. By integrating both visual and textual information, SAC achieves image clustering through a multi-modal learning framework. To mitigate the negative impact of inaccurate textual information, SAC designs an uncertainty-driven adaptive weighting mechanism that explores both intra-modal and inter-modal neighborhood structures, and incorporates the adaptive weights into intra-modal and inter-modal contrastive learning, which improves the robustness against noisy image-text correspondences. Experiments on several popular datasets demonstrate the superiority of SAC compared to state-of-the-art methods.

PDF Details DOI

JBHI Journal 2025 Journal Article

A Rule-Guided Community Detection Method for Identifying Subpopulations in Medical Data

Hanyue Liu
Hong Yu
Hao Wu
Guoyin Wang

Precisely identifying and explaining subpopulations in heterogeneous populations is essential to understanding the disease subtype. Using community detection to identify subpopulations is a promising way. However, there remains an issue in the existing community detection: Current methods for identifying subpopulations in medical data rely solely on separate attribute values, ignoring the important association rules between attribute values. Association rules are crucial in medical diagnosis to determine disease subtypes. Thus, We propose a rule-guided community detection (RGCD) method for precisely identifying homogeneous subpopulations. Specifically, the RGCD incorporates association rules into the original network, thereby constructing an augmented network. It proves that decomposing the embedding vectors obtained from biased random walks on the augmented network is equivalent to decomposing the transition probability matrix. Based on this proof, we enhance the transition probability matrix through rule-guided biased random walks, resulting in the rule-augmented matrix. By performing matrix decomposition and clustering on this matrix, we achieve precise identification of subpopulations. To the best of our knowledge, this is the first work that introduces the incorporation of association rules into community detection. Extensive experiments on 10 real-world datasets from medical fields fully show that the RGCD is more competitive than six state-of-the-art community detection methods. The weighted F1 of RGCD increases by up to 22. 62%, compared to the best existing community detection methods. Furthermore, We provide a qualitative depiction of the subpopulations obtained through RGCD and acquire medically significant insights.

Details DOI

JBHI Journal 2025 Journal Article

Cross-Interaction of Chinese Characters Structures and Boundary Features for Improving Clinical Named Entity Recognition

Ye Wang
Qi Wei
Hong Yu
Guoyin Wang
Chunmeng Shi
Dajiang Lei

In the natural language processing task of clinical named entity recognition (CNER), accurately identifying the boundaries and categories of medical entities is crucial. However, traditional methods struggle to recognize a large number of clinical terms and symbols that have never been encountered before, ultimately limiting the performance of CNER. Besides, there exist some easy-to-confuse Chinese clinical entities that are semantically similar but belong to quite different categories, such as “ 肺结节 ” (pulmonary nodules, a symptom entity) and “ 肺结核 ” (pulmonary tuberculosis, a disease entity), which can lead to entity misidentification. To address these problems, we propose a novel NER model called Cross-Interaction of Chinese characters structures and Boundary Features (CCS). The proposed model leverages Chinese character structural features and boundary information to comprehensively and accurately identify confusing entities. We further design a Cross-Attention mechanism to capture dependency relationships between different entities and radicals of characters, enhancing the model's semantic understanding of specialized terms and symbols, as well as improving its ability to recognize boundaries. Our experimental results show that our proposed model outperforms other state-of-the-art models on various public medical datasets, achieving significant improvements on the CCKS2020, CMeEE, CMI, and IMCS datasets, respectively.

Details DOI

NeurIPS Conference 2025 Conference Paper

HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models

Han Liu
Jiaqi Li
Zhi Xu
Xiaotong Zhang
Xiaoming Xu
Fenglong Ma
Yuanman Li
Hong Yu

Black-box adversarial attack on vision-language pre-trained models is a practical and challenging task, as text and image perturbations need to be considered simultaneously, and only the predicted results are accessible. Research on this problem is in its infancy, and only a handful of methods are available. Nevertheless, existing methods either rely on a complex iterative cross-search strategy, which inevitably consumes numerous queries, or only consider reducing the similarity of positive image-text pairs but ignore that of negative ones, which will also be implicitly diminished, thus inevitably affecting the attack performance. To alleviate the above issues, we propose a simple yet effective framework to generate high-quality adversarial examples on vision-language pre-trained models, named HQA-VLAttack, which consists of text and image attack stages. For text perturbation generation, it leverages the counter-fitting word vector to generate the substitute word set, thus guaranteeing the semantic consistency between the substitute word and the original word. For image perturbation generation, it first initializes the image adversarial example via the layer-importance guided strategy, and then utilizes contrastive learning to optimize the image adversarial perturbation, which ensures that the similarity of positive image-text pairs is decreased while that of negative image-text pairs is increased. In this way, the optimized adversarial images and texts are more likely to retrieve negative examples, thereby enhancing the attack success rate. Experimental results on three benchmark datasets demonstrate that HQA-VLAttack significantly outperforms strong baselines in terms of attack success rate.

PDF Details

AAAI Conference 2025 Conference Paper

Multi-Label Few-Shot Image Classification via Pairwise Feature Augmentation and Flexible Prompt Learning

Han Liu
Yuanyuan Wang
Xiaotong Zhang
Feng Zhang
Wei Wang
Fenglong Ma
Hong Yu

Multi-label few-shot image classification is a crucial and challenging task due to limited annotated data and elusive category specificity. However, research on this topic is still in the rudimentary stage and few methods are available. Existing methods either leverage data augmentation to alleviate data scarcity or utilize label features as auxiliary knowledge to eliminate the negative effect caused by irrelevant categories, but they ignore the utilization of image region features for data augmentation, and overlook to learn appropriate text feature to better match the image features of specific categories. Moreover, these methods only focus on one side and do not effectively tackle the above two issues simultaneously. In this paper, we introduce a novel prototype-based multi-label few-shot learning framework that seamlessly integrates pairwise feature augmentation and flexible prompt learning. Specifically, by pairwise feature augmentation, we leverage the region features of images in the support set to generate more image features and construct image prototypes, thus alleviating the issue of data scarcity. By flexible prompt learning, we adaptively acquire class-specific prompts to build text prototypes that highly match the image features of specific classes, thereby mitigating the impact of irrelevant classes. Finally, with adaptive learnable parameters, we merge image and text prototypes to obtain the final prototypes, achieving a more powerful classifier for multi-label few-shot image classification. Extensive experimental results demonstrate that our proposed method can push the performance to a higher level.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

RADAR: Benchmarking Language Models on Imperfect Tabular Data

Ken Gu
Zhihan Zhang
Kate Lin
Yuwei Zhang
Akshay Paruchuri
Hong Yu
Mehran Kazemi
Kumar Ayush

Language models (LMs) are increasingly being deployed to perform autonomous data analyses. However, their data awareness—the ability to recognize, reason over, and appropriately handle data artifacts such as missing values, outliers, and logical inconsistencies—remains underexplored. These artifacts are especially common in real-world tabular data and, if mishandled, can significantly compromise the validity of analytical conclusions. To address this gap, we present RADAR, a benchmark for systematically evaluating data-aware reasoning on tabular data. We develop a framework to simulate data artifacts via programmatic perturbations to enable targeted evaluation of model behavior. RADAR comprises 2, 980 table-query pairs, grounded in real-world data spanning 9 domains and 5 data artifact types. In addition to evaluating artifact handling, RADAR systematically varies table size to study how reasoning performance holds when increasing table size. Our evaluation reveals that, despite decent performance on tables without data artifacts, frontier models degrade significantly when data artifacts are introduced, exposing critical gaps in their capacity for robust, data-aware analysis. Designed to be flexible and extensible, RADAR supports diverse perturbation types and controllable table sizes, offering a valuable resource for advancing tabular reasoning.

PDF Details

AAAI Conference 2024 Conference Paper

Depression Detection via Capsule Networks with Contrastive Learning

Han Liu
Changya Li
Xiaotong Zhang
Feng Zhang
Wei Wang
Fenglong Ma
Hongyang Chen
Hong Yu

Depression detection is a challenging and crucial task in psychological illness diagnosis. Utilizing online user posts to predict whether a user suffers from depression seems an effective and promising direction. However, existing methods suffer from either poor interpretability brought by the black-box models or underwhelming performance caused by the completely separate two-stage model structure. To alleviate these limitations, we propose a novel capsule network integrated with contrastive learning for depression detection (DeCapsNet). The highlights of DeCapsNet can be summarized as follows. First, it extracts symptom capsules from user posts by leveraging meticulously designed symptom descriptions, and then distills them into class-indicative depression capsules. The overall workflow is in an explicit hierarchical reasoning manner and can be well interpreted by the Patient Health Questionnaire-9 (PHQ9), which is one of the most widely adopted questionnaires for depression diagnosis. Second, it integrates with contrastive learning, which can facilitate the embeddings from the same class to be pulled closer, while simultaneously pushing the embeddings from different classes apart. In addition, by adopting the end-to-end training strategy, it does not necessitate additional data annotation, and mitigates the potential adverse effects from the upstream task to the downstream task. Extensive experiments on three widely-used datasets show that in both within-dataset and cross-dataset scenarios our proposed method outperforms other strong baselines significantly.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Liberating Seen Classes: Boosting Few-Shot and Zero-Shot Text Classification via Anchor Generation and Classification Reframing

Han Liu
Siyang Zhao
Xiaotong Zhang
Feng Zhang
Wei Wang
Fenglong Ma
Hongyang Chen
Hong Yu

Few-shot and zero-shot text classification aim to recognize samples from novel classes with limited labeled samples or no labeled samples at all. While prevailing methods have shown promising performance via transferring knowledge from seen classes to unseen classes, they are still limited by (1) Inherent dissimilarities among classes make the transformation of features learned from seen classes to unseen classes both difficult and inefficient. (2) Rare labeled novel samples usually cannot provide enough supervision signals to enable the model to adjust from the source distribution to the target distribution, especially for complicated scenarios. To alleviate the above issues, we propose a simple and effective strategy for few-shot and zero-shot text classification. We aim to liberate the model from the confines of seen classes, thereby enabling it to predict unseen categories without the necessity of training on seen classes. Specifically, for mining more related unseen category knowledge, we utilize a large pre-trained language model to generate pseudo novel samples, and select the most representative ones as category anchors. After that, we convert the multi-class classification task into a binary classification task and use the similarities of query-anchor pairs for prediction to fully leverage the limited supervision signals. Extensive experiments on six widely used public datasets show that our proposed method can outperform other strong baselines significantly in few-shot and zero-shot tasks, even without using any seen class samples.

PDF Details DOI

JBHI Journal 2024 Journal Article

MSVTNet: Multi-Scale Vision Transformer Neural Network for EEG-Based Motor Imagery Decoding

Ke Liu
Tao Yang
Zhuliang Yu
Weibo Yi
Hong Yu
Guoyin Wang
Wei Wu

Object: Transformer-based neural networks have been applied to the electroencephalography (EEG) decoding for motor imagery (MI). However, most networks focus on applying the self-attention mechanism to extract global temporal information, while the cross-frequency coupling features between different frequencies have been neglected. Additionally, effectively integrating different neural networks poses challenges for the advanced design of decoding algorithms. Methods: This study proposes a novel end-to-end Multi-Scale Vision Transformer Neural Network (MSVTNet) for MI-EEG classification. MSVTNet first extracts local spatio-temporal features at different filtered scales through convolutional neural networks (CNNs). Then, these features are concatenated along the feature dimension to form local multi-scale spatio-temporal feature tokens. Finally, Transformers are utilized to capture cross-scale interaction information and global temporal correlations, providing more distinguishable feature embeddings for classification. Moreover, auxiliary branch loss is leveraged for intermediate supervision to ensure the effective integration of CNNs and Transformers. Results: The performance of MSVTNet was assessed through subject-dependent (session-dependent and session-independent) and subject-independent experiments on three MI datasets, i. e. , the BCI competition IV 2a, 2b and OpenBMI datasets. The experimental results demonstrate that MSVTNet achieves state-of-the-art performance in all analyses. Conclusion: MSVTNet shows superiority and robustness in enhancing MI decoding performance.

Details DOI

IJCAI Conference 2023 Conference Paper

Boosting Decision-Based Black-Box Adversarial Attack with Gradient Priors

Han Liu
Xingshuo Huang
Xiaotong Zhang
Qimai Li
Fenglong Ma
Wei Wang
Hongyang Chen
Hong Yu

Decision-based methods have shown to be effective in black-box adversarial attacks, as they can obtain satisfactory performance and only require to access the final model prediction. Gradient estimation is a critical step in black-box adversarial attacks, as it will directly affect the query efficiency. Recent works have attempted to utilize gradient priors to facilitate score-based methods to obtain better results. However, these gradient priors still suffer from the edge gradient discrepancy issue and the successive iteration gradient direction issue, thus are difficult to simply extend to decision-based methods. In this paper, we propose a novel Decision-based Black-box Attack framework with Gradient Priors (DBA-GP), which seamlessly integrates the data-dependent gradient prior and time-dependent prior into the gradient estimation procedure. First, by leveraging the joint bilateral filter to deal with each random perturbation, DBA-GP can guarantee that the generated perturbations in edge locations are hardly smoothed, i. e. , alleviating the edge gradient discrepancy, thus remaining the characteristics of the original image as much as possible. Second, by utilizing a new gradient updating strategy to automatically adjust the successive iteration gradient direction, DBA-GP can accelerate the convergence speed, thus improving the query efficiency. Extensive experiments have demonstrated that the proposed method outperforms other strong baselines significantly.

PDF Details DOI

AAAI Conference 2023 Conference Paper

Boosting Few-Shot Text Classification via Distribution Estimation

Han Liu
Feng Zhang
Xiaotong Zhang
Siyang Zhao
Fenglong Ma
Xiao-ming Wu
Hongyang Chen
Hong Yu

Distribution estimation has been demonstrated as one of the most effective approaches in dealing with few-shot image classification, as the low-level patterns and underlying representations can be easily transferred across different tasks in computer vision domain. However, directly applying this approach to few-shot text classification is challenging, since leveraging the statistics of known classes with sufficient samples to calibrate the distributions of novel classes may cause negative effects due to serious category difference in text domain. To alleviate this issue, we propose two simple yet effective strategies to estimate the distributions of the novel classes by utilizing unlabeled query samples, thus avoiding the potential negative transfer issue. Specifically, we first assume a class or sample follows the Gaussian distribution, and use the original support set and the nearest few query samples to estimate the corresponding mean and covariance. Then, we augment the labeled samples by sampling from the estimated distribution, which can provide sufficient supervision for training the classification model. Extensive experiments on eight few-shot text classification datasets show that the proposed method outperforms state-of-the-art baselines significantly.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

HQA-Attack: Toward High Quality Black-Box Hard-Label Adversarial Attack on Text

Han Liu
Zhi Xu
Xiaotong Zhang
Feng Zhang
Fenglong Ma
Hongyang Chen
Hong Yu
Xianchao Zhang

Black-box hard-label adversarial attack on text is a practical and challenging task, as the text data space is inherently discrete and non-differentiable, and only the predicted label is accessible. Research on this problem is still in the embryonic stage and only a few methods are available. Nevertheless, existing methods rely on the complex heuristic algorithm or unreliable gradient estimation strategy, which probably fall into the local optimum and inevitably consume numerous queries, thus are difficult to craft satisfactory adversarial examples with high semantic similarity and low perturbation rate in a limited query budget. To alleviate above issues, we propose a simple yet effective framework to generate high quality textual adversarial examples under the black-box hard-label attack scenarios, named HQA-Attack. Specifically, after initializing an adversarial example randomly, HQA-attack first constantly substitutes original words back as many as possible, thus shrinking the perturbation rate. Then it leverages the synonym set of the remaining changed words to further optimize the adversarial example with the direction which can improve the semantic similarity and satisfy the adversarial condition simultaneously. In addition, during the optimizing procedure, it searches a transition synonym word for each changed word, thus avoiding traversing the whole synonym set and reducing the query number to some extent. Extensive experimental results on five text classification datasets, three natural language inference datasets and two real-world APIs have shown that the proposed HQA-Attack method outperforms other strong baselines significantly.

PDF Details

AAAI Conference 2023 Conference Paper

Multi-Label Few-Shot ICD Coding as Autoregressive Generation with Prompt

Zhichao Yang
Sunjae Kwon
Zonghai Yao
Hong Yu

Automatic International Classification of Diseases (ICD) coding aims to assign multiple ICD codes to a medical note with an average of 3,000+ tokens. This task is challenging due to the high-dimensional space of multi-label assignment (155,000+ ICD code candidates) and the long-tail challenge - Many ICD codes are infrequently assigned yet infrequent ICD codes are important clinically. This study addresses the long-tail challenge by transforming this multi-label classification task into an autoregressive generation task. Specifically, we first introduce a novel pretraining objective to generate free text diagnosis and procedure descriptions using the SOAP structure, the medical logic physicians use for note documentation. Second, instead of directly predicting the high dimensional space of ICD codes, our model generates the lower dimension of text descriptions, which then infer ICD codes. Third, we designed a novel prompt template for multi-label classification. We evaluate our Generation with Prompt (GP) model with the benchmark of all code assignment (MIMIC-III-full) and few shot ICD code assignment evaluation benchmark (MIMIC-III-few). Experiments on MIMIC-III-few show that our model performs with a marco F1 30.2, which substantially outperforms the previous MIMIC-III-full SOTA model (marco F1 4.3) and the model specifically designed for few/zero shot setting (marco F1 18.7). Finally, we design a novel ensemble learner, a cross attention reranker with prompts, to integrate previous SOTA and our best few-shot coding predictions. Experiments on MIMIC-III-full show that our ensemble learner substantially improves both macro and micro F1, from 10.4 to 14.6 and from 58.2 to 59.1, respectively.

PDF Details DOI

AAAI Conference 2023 Conference Paper

SSPAttack: A Simple and Sweet Paradigm for Black-Box Hard-Label Textual Adversarial Attack

Han Liu
Zhi Xu
Xiaotong Zhang
Xiaoming Xu
Feng Zhang
Fenglong Ma
Hongyang Chen
Hong Yu

Hard-label textual adversarial attack is a challenging task, as only the predicted label information is available, and the text space is discrete and non-differentiable. Relevant research work is still in fancy and just a handful of methods are proposed. However, existing methods suffer from either the high complexity of genetic algorithms or inaccurate gradient estimation, thus are arduous to obtain adversarial examples with high semantic similarity and low perturbation rate under the tight-budget scenario. In this paper, we propose a simple and sweet paradigm for hard-label textual adversarial attack, named SSPAttack. Specifically, SSPAttack first utilizes initialization to generate an adversarial example, and removes unnecessary replacement words to reduce the number of changed words. Then it determines the replacement order and searches for an anchor synonym, thus avoiding going through all the synonyms. Finally, it pushes substitution words towards original words until an appropriate adversarial example is obtained. The core idea of SSPAttack is just swapping words whose mechanism is simple. Experimental results on eight benchmark datasets and two real-world APIs have shown that the performance of SSPAttack is sweet in terms of similarity, perturbation rate and query efficiency.

PDF Details DOI

AAAI Conference 2020 Conference Paper

ICD Coding from Clinical Text Using Multi-Filter Residual Convolutional Neural Network

Fei Li
Hong Yu

Automated ICD coding, which assigns the International Classiﬁcation of Disease codes to patient visits, has attracted much research attention since it can save time and labor for billing. The previous state-of-the-art model utilized one convolutional layer to build document representations for predicting ICD codes. However, the lengths and grammar of text fragments, which are closely related to ICD coding, vary a lot in different documents. Therefore, a ﬂat and ﬁxed-length convolutional architecture may not be capable of learning good document representations. In this paper, we proposed a Multi-Filter Residual Convolutional Neural Network (MultiResCNN) for ICD coding. The innovations of our model are two-folds: it utilizes a multi-ﬁlter convolutional layer to capture various text patterns with different lengths and a residual convolutional layer to enlarge the receptive ﬁeld. We evaluated the effectiveness of our model on the widely-used MIMIC dataset. On the full code set of MIMIC-III, our model outperformed the state-of-the-art model in 4 out of 6 evaluation metrics. On the top-50 code set of MIMIC-III and the full code set of MIMIC-II, our model outperformed all the existing and state-of-the-art models in all evaluation metrics. The code is available at https: //github. com/foxlf823/Multi-Filter- Residual-Convolutional-Neural-Network.

PDF Details

AAAI Conference 2020 Conference Paper

MetaMT, a Meta Learning Method Leveraging Multiple Domain Data for Low Resource Machine Translation

Rumeng Li
Xun Wang
Hong Yu

Neural machine translation (NMT) models have achieved state-of-the-art translation quality with a large quantity of parallel corpora available. However, their performance suffers signiﬁcantly when it comes to domain-speciﬁc translations, in which training data are usually scarce. In this paper, we present a novel NMT model with a new word embedding transition technique for fast domain adaption. We propose to split parameters in the model into two groups: model parameters and meta parameters. The former are used to model the translation while the latter are used to adjust the representational space to generalize the model to different domains. We mimic the domain adaptation of the machine translation model to low-resource domains using multiple translation tasks on different domains. A new training strategy based on meta-learning is developed along with the proposed model to update the model parameters and meta parameters alternately. Experiments on datasets of different domains showed substantial improvements of NMT performances on a limited amount of data.

PDF Details

AAAI Conference 2018 Conference Paper

Weighted Multi-View Spectral Clustering Based on Spectral Perturbation

Linlin Zong
Xianchao Zhang
Xinyue Liu
Hong Yu

Considering the diversity of the views, assigning the multiviews with different weights is important to multi-view clustering. Several multi-view clustering algorithms have been proposed to assign different weights to the views. However, the existing weighting schemes do not simultaneously consider the characteristic of multi-view clustering and the characteristic of related single-view clustering. In this paper, based on the spectral perturbation theory of spectral clustering, we propose a weighted multi-view spectral clustering algorithm which employs the spectral perturbation to model the weights of the views. The proposed weighting scheme follows the two basic principles: 1) the clustering results on each view should be close to the consensus clustering result, and 2) views with similar clustering results should be assigned similar weights. According to spectral perturbation theory, the largest canonical angle is used to measure the difference between spectral clustering results. In this way, the weighting scheme can be formulated into a standard quadratic programming problem. Experimental results demonstrate the superiority of the proposed algorithm.

PDF Details

AAAI Conference 2015 Conference Paper

Constrained NMF-Based Multi-View Clustering on Unmapped Data

Xianchao Zhang
Linlin Zong
Xinyue Liu
Hong Yu

Existing multi-view clustering algorithms require that the data is completely or partially mapped between each pair of views. However, this requirement could not be satisﬁed in most practical settings. In this paper, we tackle the problem of multi-view clustering for unmapped data in the framework of NMF based clustering. With the help of inter-view constraints, we deﬁne the disagreement between each pair of views by the fact that the indicator vectors of two instances from two different views should be similar if they belong to the same cluster and dissimilar otherwise. The overall objective of our algorithm is to minimize the loss function of NMF in each view as well as the disagreement between each pair of views. Experimental results show that, with a small number of constraints, the proposed algorithm gets good performance on unmapped data, and outperforms existing algorithms on partially mapped data and completely mapped data.

PDF Details

AAMAS Conference 2012 Conference Paper

A Sequential Recommendation Approach for Interactive Personalized Story Generation

Hong Yu
Mark Riedl

In story-based games or other interactive story systems, a Drama Manager is an omniscient agent that acts to bring about a particular sequence of plot points for the user to experience. We present a Drama Manager that uses player modeling to personalize the user's story according to his or her storytelling preferences. In order to deliver personalized stories, a Drama Manager must make decisions on not only which plot points to be included into the unfolding story but also the optimal sequence of the events the user should experience. A prefix based collaborative filtering algorithm based on users' structural feedback is proposed to address the sequential selection problem. We demonstrate our system on a simple interactive story generation system based on choose-your-own-adventure stories to evaluate our algorithms. Results on human users and simulated users show that our Drama Manager is capable of capturing users' preference and generating personalized stories with high accuracy.

PDF

YNIMG Journal 2008 Journal Article

Region of interest template for the human basal ganglia: Comparing EPI and standardized space approaches

Janey Prodoehl
Hong Yu
Deborah M. Little
Ivy Abraham
David E. Vaillancourt

Identifying task-related activation in the basal ganglia (BG) is an important area of interest in normal motor systems and cognitive neuroscience. The purpose of this study was to compare changes in brain activation in the BG using results obtained from two different masking methods: a mask drawn in standardized space from a T1-weighted anatomical image and individual region of interest (ROI) masks drawn from each subject’s echo-planar image (EPI) from different tasks with reference to the high resolution fast spin echo image of each subject. Two standardized masks were used: a mask developed in Talairach space (Basal Ganglia Human Area Template (BGHAT)) and a mask developed in Montreal Neurological Institute space (MNI mask). Ten subjects produced fingertip force pulses in five separate contraction tasks during fMRI scanning. ROIs were the left caudate, putamen, external and internal portions of the globus pallidus, and subthalamic nucleus. ANOVA revealed a similar average number of voxels in the EPI mask across tasks in each BG region. The percent signal change (PSC) was consistent within each region regardless of which mask was used. Linear regression analyses between PSC in BGHAT and EPI masks and MNI and EPI masks yielded r 2 values between 0. 74–0. 99 and 0. 70–0. 99 across regions, respectively. In conclusion, PSC in different BG ROIs can be compared across studies using these different masking methods. The masking method used does not affect the overall interpretation of results with respect to the effect of task. Use of a mask drawn in standardized space is a valid and time saving method of identifying PSC in the small nuclei of the BG.

Details DOI

YNIMG Journal 2007 Journal Article

Role of hyperactive cerebellum and motor cortex in Parkinson's disease

Hong Yu
Dagmar Sternad
Daniel M. Corcos
David E. Vaillancourt

Previous neuroimaging studies have found hyperactivation in the cerebellum and motor cortex and hypoactivation in the basal ganglia in patients with Parkinson's disease (PD) but the relationship between the two has not been established. This study examined whether cerebellar and motor cortex hyperactivation is a compensatory mechanism for hypoactivation in the basal ganglia or is a pathophysiological response that is related to the signs of the disease. Using a BOLD contrast fMRI paradigm PD patients and healthy controls performed automatic and cognitively controlled thumb pressing movements. Regions of interest analysis quantified the BOLD activation in motor areas, and correlations between the hyperactive and hypoactive regions were performed, along with correlations between the severity of upper limb rigidity and BOLD activation. There were three main findings. First, the putamen, supplementary motor area (SMA) and pre-SMA were hypoactive in PD patients. The left and right cerebellum and the contralateral motor cortex were hyperactive in PD patients. Second, PD patients had a significant negative correlation between the BOLD activation in the ipsilateral cerebellum and the contralateral putamen. The correlation between the putamen and motor cortex was not significant. Third, the BOLD activation in the motor cortex was positively correlated with the severity of upper limb rigidity, but the BOLD activation in the cerebellum was not correlated with rigidity. Further, the activation in the motor cortex was not correlated with upper extremity bradykinesia. These findings provide new evidence supporting the hypothesis that hyperactivation in the ipsilateral cerebellum is a compensatory mechanism for the defective basal ganglia. Our findings also provide the first evidence from neuroimaging that hyperactivation in the contralateral primary motor cortex is not a compensatory response but is directly related to upper limb rigidity.

Details DOI

YNIMG Journal 2007 Journal Article

Role of the basal ganglia and frontal cortex in selecting and producing internally guided force pulses

David E. Vaillancourt
Hong Yu
Mary A. Mayka
Daniel M. Corcos

The basal ganglia comprise a crucial circuit involved in force production and force selection, but the specific role of each nucleus to the production of force pulses and the selection of pulses of different force amplitudes remains unknown. We conducted an fMRI study in which participants produced force using a precision grip while (a) holding a steady-state force, (b) performing a series of force pulses with similar amplitude, and (c) selecting force pulses of different amplitude. Region of interest analyses were conducted in the basal ganglia and frontal cortex to compare percent signal change during force pulse versus steady-state force production and compare force amplitude selection to force production when selection of force amplitude was not present. There were three novel findings in the basal ganglia. First, the caudate nucleus increased activation during the selection of different force amplitudes when compared to producing a series of similar force pulses. Second, GPi, STN, and posterior putamen increased activation during the production of similar force amplitudes when compared to holding a steady-state force, and maintained similar activation during the production of different force amplitudes in which force selection was required. Third, GPe and anterior putamen had increased activation during the production of similar force pulses and further increased activation during the selection of different force pulses. These findings suggest that anterior basal ganglia nuclei are involved in selecting the amplitude of force contractions and posterior basal ganglia nuclei regulate basic aspects of dynamic force pulse production.

Details DOI