Author name cluster

Hui Sun

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.

11 papers

1 author row

AAAI Conference 2026 Conference Paper

ARBench: Algorithmic Reasoner or API Alchemist? Evaluating LLMs Beyond API Calls

Ren-Biao Liu
Chao-Zeng Ma
Anqi Li
Hui Sun
Xin-Ye Li
Ming Li

Large Language Models (LLMs) have demonstrated impressive capabilities in code generation. Like human programmers, LLMs tend to call high-level APIs and libraries to program efficiently. However, this shortcut may hinder LLMs from learning the essential algorithm reasoning, leading instead to rote memorization of API usage. As a result, LLMs often struggle to generalize to new or domain-specific algorithms that lack ready-made library support. In this work, we propose ARBench, a novel benchmark for evaluating LLMs’ ability to generate machine learning algorithms from scratch, beyond merely invoking high-level APIs. It emphasizes algorithmic reasoning and implementation, distinguishing genuine understanding from superficial API usage. It covers fundamental and advanced machine learning tasks, rigorously assessing current LLMs’ capacity to implement these algorithms from scratch. Our evaluation reveals the strengths and weaknesses of state-of-the-art LLMs in algorithmic reasoning and generalization, offering valuable insights to guide future research and development.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Dynamic-Static Synergistic Selection Method for Candidate Code Solutions with Generated Test Cases

Ren-Biao Liu
Jiang-Tian Xue
Chao-Zeng Ma
Hui Sun
Xin-Ye Li
Ming Li

Large language models (LLMs) show significant improvement in code generation. A common practice is sampling multiple candidate codes to increase the likelihood of producing an accurate solution. However, effectively identifying the best candidate from the pool is a significant challenge. Although existing code consensus methods attempt to solve this issue, they suffer from a critical problem: relying on test cases generated by LLMs, which can be flawed or provide incomplete coverage. This problem can result in erroneous validations, causing correct code to fail flawed tests and preventing the detection of functional differences in candidate code solutions. To address these issues, we present the Dynamic-Static Synergistic Selection Method, a novel framework that combines two complementary analytical approaches. First, it uses the abstract syntax tree (AST) to detect and filter candidate solutions and test cases. Second, the method statically analyzes the quality of the solutions and then dynamically validates functional consistency based on the execution results of the extracted inputs, thereby neutralizing the impact of faulty tests. Extensive experiments demonstrate that this synergistic approach significantly outperforms existing methods, substantially enhancing the correctness of the selected code.

PDF Details DOI

YNIMG Journal 2026 Journal Article

Multidimensional characterization of structure aberrations for biotypes of major depressive disorder

Jiang Zhang
Heng Zhang
Hui Sun
Tianwei Qin
Jun Pan
Jin Chen
Wei Li
Meiling Chen

BACKGROUND: Major depressive disorder (MDD) is a heterogeneous clinical syndrome associated with brain structural abnormalities, yet the neurobiological heterogeneity and consistent neuroimaging findings underlying these alterations remain unclear. Multilevel and multidimensional analyses are therefore needed to identify reliable structural signatures of MDD biotypes. METHODS: K-means clustering was applied to identify biotypes in 387 drug-naive MDD patients, with gray matter volume (GMV) compared to 1104 healthy controls. Causal structural covariance network (CaSCN), individual differential structural covariance network (IDSCN), and graph theory-based single-subject morphological network analyses were performed to characterize subtype-specific causal influences, individual-level covariance, and network topology. Transcriptomic and neurotransmitter association analyses were further conducted to probe the biological mechanisms underlying each subtype. RESULTS: Subtype 1 showed predominant GMV alterations in the visual network, subtype 2 in somatomotor, default mode, and limbic networks, and subtype 3 in cerebellar-limbic regions. CaSCN revealed subtype-specific directed influences, indicating differential propagation of structural abnormalities. IDSCN identified distinct altered covariance patterns, highlighting subtype-dependent thalamo-cerebellar changes and selective links to depressive severity. Graph theory showed divergent global topology, with subtype 1 exhibiting higher network integration, whereas subtypes 2 and 3 showed reduced integration and efficiency. Each biotype showed distinct neurobiological profiles, with subtype 1 enriched in cellular functions, subtype 2 in metabolic regulation, and subtype 3 in neurodevelopmental genes, alongside distinct neurotransmitter associations. CONCLUSIONS: These findings advance the understanding of structural and individual-level network alterations underlying MDD biotypes and provide novel insights into the neurobiological mechanisms of MDD heterogeneity.

Details DOI

EAAI Journal 2025 Journal Article

Coupled fault diagnosis for centrifugal pumps through Boruta-Shap feature selection and rime-enhanced stacked denoised autoencoder

Kang Hu
Hui Sun
Wei Fan
Qiaorui Si
Yu Wu
Shouqi Yuan

This study addresses the critical engineering challenges of diagnosing multi-condition cavitation and impeller erosion damage in deep sea centrifugal pumps, where traditional methods suffer from feature redundancy and poor generalization. An artificial intelligence (AI)-driven framework is proposed by integrating Boruta-Shap interpretable feature selection with a Rime-optimized Stacked Denoising Auto-Encoder (SDAE). Firstly, vibration signals undergo multi-domain feature extraction. The Boruta-Shap method quantifies feature interactions via Shapley values and shadow feature hypothesis testing, enabling physics-informed selection of cavitation energy indicators and impeller damage transient features, reducing feature dimensionality by approximately 70 %. Secondly, the Rime algorithm, inspired by ice-crystal growth dynamics, globally optimizes SDAE hyperparameters via balancing soft-rime exploration and hard-rime exploitation. Validated experimentally under variable conditions (0. 8, 1. 0 and 1. 2Q d), the framework achieves 96 % testing accuracy, outperforming other diagnostic models, with reduced cross-condition misclassification. By bridging interpretable AI with multi-physics diagnostics, this work provides a replicable solution for predictive maintenance of energy infrastructure, advancing intelligent maintenance technologies for industrial systems facing complex hydrodynamic perturbations.

Details DOI

AAAI Conference 2025 Conference Paper

Genomics Data Lossless Compression with (S, K)-Mer Encoding and Deep Neural Networks

Hui Sun
Liping Yi
Huidong Ma
Yongxia Sun
Yingfeng Zheng
Wenwen Cui
Meng Yan
Gang Wang

Learning-based compression shows competitive compression ratios for genomics data. It often includes three types of compressors: static, adaptive and semi-adaptive. However, these existing compressors suffer from inferior compression ratios or throughput, and adaptive compressors also faces model cold-start problems. To address these issues, we propose DeepGeCo, a novel genomics data lossless adaptive compression framework with (s,k)-mer encoding and deep neural networks, involving three compression modes (MINI for static, PLUS for adaptive, ULTRA for semi-adaptive) for flexible requirements of compression ratios or throughput. In DeepGeCo, (1) we develop BiGRU and Transformer as the backbone to build Warm-Start and Supporter models in terms of cold-start problems. (2) We introduce (s,k)-mer encoding to pre-process genomics data before feeding it into the DNN model for improve model throughput, and we propose a new metric - Ranking of Throughput and Compression Ratio (RTCR) for effective encoding parameters selection. (3) We design a threshold controller and a probabilistic mixer within the backbone to balance compression ratios and model throughput. Experiments on 10 real-world datasets show that DeepGeCo's three compression modes improve up to a 22.949X average throughput and up to a 31.095% average compression ratio improvement while occupying low CPU or GPU memory.

PDF Details DOI

EAAI Journal 2025 Journal Article

Probability forecasting for multivariate urban water demand using temporal convolutional network based on quantile regression and Parzen window

Jun Guo
Qingya Meng
Baigang Du
Hui Sun

Probability prediction can provide more abundant information about uncertainties in future water demand, which is gaining increasing attention in building economical and reliable water resource management plans. However, most existing literature on water demand prediction focus on provide deterministic point prediction results. To overcome this problem, a novel hybrid probability forecasting model based on quantile regression temporal convolutional network and Parzen window is proposed for the probability density forecast of multivariate urban water demand. Firstly, to address the complex coupling relationship between water demand and multiple influencing factors, a random forest-based feature selection method is employed to eliminate the redundant variables. Then, a discrete wavelet transform is deployed to decompose the original series into a variety of characteristic subseries to reduce fluctuations of the original water demand series. Secondly, a quantile regression-based temporal convolutional neural network is employed to obtain the conditional quantiles of future water demand. Moreover, a probability density prediction method based on Parzen window estimation is developed to further obtain the distribution information of prediction uncertainty. Finally, a real-world multivariate dataset from a water plant in Suzhou, China, is used for comparison experiments with state-of-the-art models. The comparison results show that the proposed model has achieved an average improvement of 15. 4 % and 53. 3 % in interval prediction and probability density prediction, respectively. It shows that the proposed model is a reliable prediction model that can assist policymakers to optimize the management of urban water demand.

Details DOI

YNIMG Journal 2024 Journal Article

Elucidating genetic and molecular basis of altered higher-order brain structure-function coupling in major depressive disorder

Haixia Long
Zihao Chen
Xinli Xu
Qianwei Zhou
Zhaolin Fang
Mingqi Lv
Xu-Hua Yang
Jie Xiao

Previous studies have shown that major depressive disorder (MDD) patients exhibit structural and functional impairments, but few studies have investigated changes in higher-order coupling between structure and function. Here, we systematically investigated the effect of MDD on higher-order coupling between structural connectivity (SC) and functional connectivity (FC). Each brain region was mapped into embedding vector by the node2vec algorithm. We used support vector machine (SVM) with the brain region embedding vector to distinguish MDD patients from health controls (HCs) and identify the most discriminative brain regions. Our study revealed that MDD patients had decreased higher-order coupling in connections between the most discriminative brain regions and local connections in rich-club organization and increased higher-order coupling in connections between the ventral attentional network and limbic network compared with HCs. Interestingly, transcriptome-neuroimaging association analysis demonstrated the correlations between regional rSC-FC coupling variations between MDD patients and HCs and α/β-hydrolase domain-containing 6 (ABHD6), β 1,3-N-acetylglucosaminyltransferase-9(β3GNT9), transmembrane protein 45B (TMEM45B), the correlation between regional dSC-FC coupling variations and retinoic acid early transcript 1E antisense RNA 1(RAET1E-AS1), and the correlations between regional iSC-FC coupling variations and ABHD6, β3GNT9, katanin-like 2 protein (KATNAL2). In addition, correlation analysis with neurotransmitter receptor/transporter maps found that the rSC-FC and iSC-FC coupling variations were both correlated with neuroendocrine transporter (NET) expression, and the dSC-FC coupling variations were correlated with metabotropic glutamate receptor 5 (mGluR5). Further mediation analysis explored the relationship between genes, neurotransmitter receptor/transporter and MDD related higher-order coupling variations. These findings indicate that specific genetic and molecular factors underpin the observed disparities in higher-order SC-FC coupling between MDD patients and HCs. Our study confirmed that higher-order coupling between SC and FC plays an important role in diagnosing MDD. The identification of new biological evidence for MDD etiology holds promise for the development of innovative antidepressant therapies.

Details DOI

AAAI Conference 2023 Conference Paper

Cooperative and Adversarial Learning: Co-enhancing Discriminability and Transferability in Domain Adaptation

Hui Sun
Zheng Xie
Xin-Ye Li
Ming Li

Discriminability and transferability are two goals of feature learning for domain adaptation (DA), as we aim to find the transferable features from the source domain that are helpful for discriminating the class label in the target domain. Modern DA approaches optimize discriminability and transferability by adopting two separate modules for the two goals upon a feature extractor, but lack fully exploiting their relationship. This paper argues that by letting the discriminative module and transfer module help each other, better DA can be achieved. We propose Cooperative and Adversarial LEarning (CALE) to combine the optimization of discriminability and transferability into a whole, provide one solution for making the discriminative module and transfer module guide each other. Specifically, CALE generates cooperative (easy) examples and adversarial (hard) examples with both discriminative module and transfer module. While the easy examples that contain the module knowledge can be used to enhance each other, the hard ones are used to enhance the robustness of the corresponding goal. Experimental results show the effectiveness of CALE for unifying the learning of discriminability and transferability, as well as its superior performance.

PDF Details DOI

AAAI Conference 2023 Conference Paper

Semi-supervised Learning with Support Isolation by Small-Paced Self-Training

Zheng Xie
Hui Sun
Ming Li

In this paper, we address a special scenario of semi-supervised learning, where the label missing is caused by a preceding filtering mechanism, i.e., an instance can enter a subsequent process in which its label is revealed if and only if it passes the filtering mechanism. The rejected instances are prohibited to enter the subsequent labeling process due to economical or ethical reasons, making the support of the labeled and unlabeled distributions isolated from each other. In this case, semi-supervised learning approaches which rely on certain coherence of the labeled and unlabeled distribution would suffer from the consequent distribution mismatch, and hence result in poor prediction performance. In this paper, we propose a Small-Paced Self-Training framework, which iteratively discovers labeled and unlabeled instance subspaces with bounded Wasserstein distance. We theoretically prove that such a framework may achieve provably low error on the pseudo labels during learning. Experiments on both benchmark and pneumonia diagnosis tasks show that our method is effective.

PDF Details DOI

JBHI Journal 2022 Journal Article

Learning COVID-19 Pneumonia Lesion Segmentation From Imperfect Annotations via Divergence-Aware Selective Training

Shuojue Yang
Guotai Wang
Hui Sun
Xiangde Luo
Peng Sun
Kang Li
Qijun Wang
Shaoting Zhang

Automatic segmentation of COVID-19 pneumonia lesions is critical for quantitative measurement for diagnosis and treatment management. For this task, deep learning is the state-of-the-art method while requires a large set of accurately annotated images for training, which is difficult to obtain due to limited access to experts and the time-consuming annotation process. To address this problem, we aim to train the segmentation network from imperfect annotations, where the training set consists of a small clean set of accurately annotated images by experts and a large noisy set of inaccurate annotations by non-experts. To avoid the labels with different qualities corrupting the segmentation model, we propose a new approach to train segmentation networks to deal with noisy labels. We introduce a dual-branch network to separately learn from the accurate and noisy annotations. To fully exploit the imperfect annotations as well as suppressing the noise, we design a Divergence-Aware Selective Training (DAST) strategy, where a divergence-aware noisiness score is used to identify severely noisy annotations and slightly noisy annotations. For severely noisy samples we use an regularization through dual-branch consistency between predictions from the two branches. We also refine slightly noisy samples and use them as supplementary data for the clean branch to avoid overfitting. Experimental results show that our method achieves a higher performance than standard training process for COVID-19 pneumonia lesion segmentation when learning from imperfect labels, and our framework outperforms the state-of-the-art noise-tolerate methods significantly with various clean label percentages.

Details DOI

JMLR Journal 2017 Journal Article

Angle-based Multicategory Distance-weighted SVM

Hui Sun
Bruce A. Craig
Lingsong Zhang

Classification is an important supervised learning technique with numerous applications. We develop an angle-based multicategory distance-weighted support vector machine (MDWSVM) classification method that is motivated from the binary distance-weighted support vector machine (DWSVM) classification method. The new method has the merits of both support vector machine (SVM) and distance-weighted discrimination (DWD) but also alleviates both the data piling issue of SVM and the imbalanced data issue of DWD. Theoretical and numerical studies demonstrate the advantages of MDWSVM method over existing angle-based methods. [abs] [ pdf ][ bib ] &copy JMLR 2017. ( edit, beta )

PDF Details