Liang Sun

AAAI Conference 2026 Conference Paper

MoCast: Learning Turbulent Motions Under Physical Guidance for Precipitation Nowcasting

• Binqing Wu
• Weiqi Chen
• Shiyu Liu
• Zongjiang Shang
• Haiou Wang
• Liang Sun
• Ling Chen

Precipitation nowcasting, a critical task for weather-sensitive applications, is highly challenging owing to the chaotic nature of atmospheric dynamics. Despite recent progress in deep learning, existing methods are limited in their capacity to model turbulent motions, one of the key drivers of precipitation evolution. Thus, we propose MoCast, the first work that incorporates turbulence knowledge to decompose turbulent motions into solvable components for precipitation nowcasting. Specifically, inspired by the continuity equation, MoCast introduces two core innovations: (1) a physics-guided motion module that learns turbulent motions from physically interpretable mean and fluctuating components based on Reynolds, Helmholtz, and Wavelet decomposition techniques, and (2) a motion-guided source-sink module that learns source-sink features considering the multi-scale impact from motions based on a mixture-of-experts architecture. Extensive experiments on three real-world datasets demonstrate that MoCast achieves the state-of-the-art performance. MoCast and its diffusion-based variant MoCast+ reduce CSI error by an average of 4.9% and 4.5% compared to the best deterministic and probabilistic baselines, respectively.

AIIM Journal 2025 Journal Article

A prior knowledge-supervised fusion network predicts survival after radiotherapy in patients with advanced gastric cancer

• Liang Sun
• Yongxin Lan
• Jian Sun
• Pengfei Ji
• Hongwei Ge
• Ming Cui
• Xin Yuan

BACKGROUND AND OBJECTIVE: Predicting overall survival (OS) for advanced gastric cancer patients after radiotherapy is critical for developing an individualized treatment plan. However, existing studies have focused on gastric cancer CT images with a large amount of redundant information, neglecting the role of physicians' prior knowledge in guiding gastric cancer CT image information. We propose a multimodal fusion method based on prior knowledge to predict OS after radiotherapy in advanced gastric cancer patients to assist physicians in clinical diagnosis and treatment. METHODS: A prior knowledge supervised fusion network (PKSFnet) is proposed. Firstly, PKSFnet uses a novel sampling strategy, which enables the input model data to obtain a complete feature space by analyzing the entire patient data space. Afterwards, under the guidance of the multi-domain feature fusion module (MdFF), multimodal information of patients is adaptively fused and mined to improve the prediction performance. RESULTS: The results of the proposed model are superior to those of other unimodal and multimodal state-of-the-art methods. For the segmented survival time classification task, the AUC, specificity, sensitivity, precision of the proposed model are 0.8397, 0.875, 0.7556, and 0.875, respectively. For the survival risk regression task, the C-index and HR of the proposed model are 0.8574 and 4.658 respectively. Ablation experimental results further demonstrate the impact of each module of the proposed model. Finally, we apply the novel sampling strategy to other deep learning models and achieve significant improvement. CONCLUSION: The experimental results have demonstrated that the proposed model can effectively predict OS after radiotherapy in patients with advanced gastric cancer, which demonstrate that the proposed model can facilitate the development and application of robust clinical treatment strategies.

EAAI Journal 2025 Journal Article

An evolutionary multitasking algorithm for multi-objective feature selection using dual-perspective reduction

• Mengyue Wang
• Hongwei Ge
• Xia Wang
• Liang Sun
• Yaqing Hou
• Bin Li

Feature selection inherently involves two conflicting objectives: minimizing the number of selected features and maximizing the classification accuracy. The exponential growth of the search space and complex interactions between features make high-dimensional feature selection challenging. Existing multi-objective methods suffer from slow convergence and limited search capabilities. Moreover, there is a lack of efficient methods for identifying feature subsets with equivalent objective values, which could offer diverse options. To address these issues, this paper proposes an evolutionary multitasking algorithm for multi-objective feature selection using dual-perspective reduction, called DREA-FS. First, a dual-perspective dimensionality reduction strategy is designed to generate simplified and complementary tasks through improved filter-based and group-based methods, facilitating the rapid identification of promising regions. To enable effective information sharing, a dual-archive multitasking optimization mechanism is proposed, which incorporates a diversity archive to preserve feature subsets with equivalent performance and maintain diversity. Coupled with an elite archive that offers convergence guidance, this mechanism achieves a balance between convergence and diversity across tasks, thereby enhancing the ability to search for equivalent feature subsets. Experimental results on 21 datasets demonstrate that the proposed method outperforms state-of-the-art multi-objective algorithms in classification performance. Besides, DREA-FS can identify different feature subsets with equivalent objective values, supporting decision-makers with diverse options and better interpretability.

ICLR Conference 2025 Conference Paper

DeeperForward: Enhanced Forward-Forward Training for Deeper and Better Performance

• Liang Sun
• Yang Zhang 0012
• Weizhao He
• Jiajun Wen 0001
• LinLin Shen
• Weicheng Xie 0001

While backpropagation effectively trains models, it presents challenges related to bio-plausibility, resulting in high memory demands and limited parallelism. Recently, Hinton (2022) proposed the Forward-Forward (FF) algorithm for high-parallel local updates. FF leverages squared sums as the local update target, termed goodness, and decouples goodness by normalizing the vector length to extract new features. However, this design encounters issues with feature scaling and deactivated neurons, limiting its application mainly to shallow networks. This paper proposes a novel goodness design utilizing **layer normalization** and **mean goodness** to overcome these challenges, demonstrating performance improvements even in 17-layer CNNs. Experiments on CIFAR-10, MNIST, and Fashion-MNIST show significant advantages over existing FF-based algorithms, highlighting the potential of FF in deep models. Furthermore, the model parallel strategy is proposed to achieve highly efficient training based on the property of local updates.

IJCAI Conference 2025 Conference Paper

Integrating Neurosymbolic AI in Advanced Air Mobility: A Comprehensive Survey

• Kamal Acharya
• Iman Sharifi
• Mehul Lad
• Liang Sun
• Houbing Song

Neurosymbolic AI combines neural network adaptability with symbolic reasoning, promising an approach to address the complex regulatory, operational, and safety challenges in Advanced Air Mobility (AAM). This survey reviews its applications across key AAM domains such as demand forecasting, aircraft design, and real-time air traffic management. Our analysis reveals a fragmented research landscape where methodologies, including Neurosymbolic Reinforcement Learning, have shown potential for dynamic optimization but still face hurdles in scalability, robustness, and compliance with aviation standards. We classify current advancements, present relevant case studies, and outline future research directions aimed at integrating these approaches into reliable, transparent AAM systems. By linking advanced AI techniques with AAM’s operational demands, this work provides a concise roadmap for researchers and practitioners developing next-generation air mobility solutions.

IJCAI Conference 2025 Conference Paper

Learning to Extrapolate and Adjust: Two-Stage Meta-Learning for Concept Drift in Online Time Series Forecasting

• Weiqi Chen
• Zhaoyang Zhu
• Yifan Zhang
• Lefei Shen
• Linxiao Yang
• Qingsong Wen
• Liang Sun

The inherent non-stationarity of time series in practical applications poses significant challenges for accurate forecasting. This paper tackles the concept drift problem where the underlying distribution or environment of time series changes. To better describe the characteristics and effectively model concept drifts, we first classify them into macro-drift (stable, long-term changes) and micro-drift (sudden, short-term fluctuations). Next, we propose a unified meta-learning framework called LEAF (Learning to Extrapolate and Adjust for Forecasting), where an extrapolation module is first introduced to track and extrapolate the prediction model in latent space considering macro-drift, and then an adjustment module incorporates meta-learnable surrogate loss to capture sample-specific micro-drift patterns. LEAF’s dual-stage approach effectively addresses diverse concept drifts and is model-agnostic which can be compatible with any deep prediction model. We further provide theoretical analysis to justify why the proposed framework can handle macro-drift and micro-drift. To facilitate further research in this field, we release three electric load time series datasets collected from real-world scenarios, exhibiting diverse and typical concept drifts. Extensive experiments on multiple datasets demonstrate the effectiveness of LEAF.

YNIMG Journal 2025 Journal Article

Local structural–functional coupling with counterfactual explanations for epilepsy prediction

• Jiashuang Huang
• Shaolong Wei
• Zhen Gao
• Shu Jiang
• Mingliang Wang
• Liang Sun
• Weiping Ding
• Daoqiang Zhang

The structural-functional brain connections coupling (SC-FC coupling) describes the relationship between white matter structural connections (SC) and the corresponding functional activation or functional connections (FC). It has been widely used to identify brain disorders. However, the existing research on SC-FC coupling focuses on global and regional scales, and few studies have investigated the impact of brain disorders on this relationship from the perspective of multi-brain region cooperation (i.e., local scale). Here, we propose the local SC-FC coupling pattern for brain disorders prediction. Compared with previous methods, the proposed patterns quantify the relationship between SC and FC in terms of subgraphs rather than whole connections or single brain regions. Specifically, we first construct structural and functional connections using diffusion tensor imaging (DTI) and resting-state functional magnetic resonance imaging (rs-fMRI) data, subsequently organizing them into a multimodal brain network. Then, we extract subgraphs from these multimodal brain networks and select them based on their frequencies to generate local SC-FC coupling patterns. Finally, we employ these patterns to identify brain disorders while refining abnormal patterns to generate counterfactual explanations. Results on a real epilepsy dataset suggest that the proposed method not only outperforms existing methods in accuracy but also provides insights into the local SC-FC coupling pattern and their changes in brain disorders. Code available at https://github.com/UAIBC-Brain/Local-SC-FC-coupling-pattern.

IJCAI Conference 2025 Conference Paper

SCNNs: Spike-based Coupling Neural Networks for Understanding Structural-Functional Relationships in the Human Brain

• Shaolong Wei
• Shu Jiang
• Mingliang Wang
• Liang Sun
• Haonan Rao
• Weiping Ding
• Jiashuang Huang

Structural-functional coupling (SC-FC coupling) offers an effective approach for analyzing structural-functional relationships, capable of revealing the dependency of functional activity on the underlying white matter architecture. However, extant SC-FC coupling analysis methods primarily center on disclosing the statistical association between the topological patterns of structural connectivity (SC) and functional connectivity (FC), while often neglecting the neurobiological mechanisms by which the brain typically transmits and processes information in the form of spikes. To address this, we propose a biologically inspired deep-learning model called spike-based coupling neural networks (SCNNs). It can simulate spiking neural activity to more realistically reproduce the interaction between brain regions and the dynamic behavior of neuronal networks. Specifically, we first use spike neurons to capture the FC temporal characteristics of the original functional magnetic resonance imaging (fMRI) time series and the SC spatial characteristics of the structural brain network. Then, we use synaptic and neuronal filter effects to simulate the coupling mechanism of SC and FC in the brain at different temporal and spatial scales, thereby quantifying SC-FC coupling and providing support for the identification of brain diseases. The results on real datasets show that the proposed method can identify brain diseases and provide a new perspective for understanding SC-FC relationships.

EAAI Journal 2025 Journal Article

Unsupervised multiple-target domain adaptation for bearing fault diagnosis

• Guoli Bai
• Tonghao Xing
• Wei Sun
• Huashan Chi
• Zhidan Zhong
• Qingchao Sun
• Liang Sun

Data-driven bearing fault diagnosis methods have gained significant attention due to their high accuracy and minimal reliance on expert knowledge. However, models trained on the data collected under single working conditions often assume independent and identically distributed data, limiting their generalization ability in real-world scenarios where varying working conditions introduce challenges such as domain shift and unlabeled data. Unsupervised domain adaptation is an effective method for addressing these challenges by training classifiers using labeled source domain data and unlabeled target domain data. However, current domain adaptation fault diagnosis methods are typically limited to single-source and single-target scenarios. When multiple unlabeled working conditions are involved, it becomes difficult to simultaneously ensure the domain invariance and the fault relevance of features. This paper proposes a fault diagnosis method across multiple unlabeled working conditions. The method extracts features from image data transformed from time-domain signals and ensures the correlation between the extracted features and fault labels, as well as domain invariance, through the gradient reversal mechanism and a corresponding loss function. The proposed method achieves an average accuracy of 99. 89 % and 95. 93 % in multi-target domain fault diagnosis tasks on two public benchmark bearing datasets, which illustrates its effectiveness and advantages compared with the existing representative methods. The source code is available at https: //github. com/WhiteGL/DA_IRP/tree/master.

AIIM Journal 2024 Journal Article

MSEF-Net: Multi-scale edge fusion network for lumbosacral plexus segmentation with MR image

• Junyong Zhao
• Liang Sun
• Zhi Sun
• Xin Zhou
• Haipeng Si
• Daoqiang Zhang

Nerve damage of spine areas is a common cause of disability and paralysis. The lumbosacral plexus segmentation from magnetic resonance imaging (MRI) scans plays an important role in many computer-aided diagnoses and surgery of spinal nerve lesions. Due to the complex structure and low contrast of the lumbosacral plexus, it is difficult to delineate the regions of edges accurately. To address this issue, we propose a Multi-Scale Edge Fusion Network (MSEF-Net) to fully enhance the edge feature in the encoder and adaptively fuse multi-scale features in the decoder. Specifically, to highlight the edge structure feature, we propose an edge feature fusion module (EFFM) by combining the Sobel operator edge detection and the edge-guided attention module (EAM), respectively. To adaptively fuse the multi-scale feature map in the decoder, we introduce an adaptive multi-scale fusion module (AMSF). Our proposed MSEF-Net method was evaluated on the collected spinal MRI dataset with 89 patients (a total of 2848 MR images). Experimental results demonstrate that our MSEF-Net is effective for lumbosacral plexus segmentation with MR images, when compared with several state-of-the-art segmentation methods.

NeurIPS Conference 2024 Conference Paper

Task-oriented Time Series Imputation Evaluation via Generalized Representers

• Zhixian Wang
• Linxiao Yang
• Liang Sun
• Qingsong Wen
• Yi Wang

Time series analysis is widely used in many fields such as power energy, economics, and transportation, including different tasks such as forecasting, anomaly detection, classification, etc. Missing values are widely observed in these tasks, and often leading to unpredictable negative effects on existing methods, hindering their further application. In response to this situation, existing time series imputation methods mainly focus on restoring sequences based on their data characteristics, while ignoring the performance of the restored sequences in downstream tasks. Considering different requirements of downstream tasks (e. g. , forecasting), this paper proposes an efficient downstream task-oriented time series imputation evaluation approach. By combining time series imputation with neural network models used for downstream tasks, the gain of different imputation strategies on downstream tasks is estimated without retraining, and the most favorable imputation value for downstream tasks is given by combining different imputation strategies according to the estimated gain.

IJCAI Conference 2024 Conference Paper

WeatherGNN: Exploiting Meteo- and Spatial-Dependencies for Local Numerical Weather Prediction Bias-Correction

• Binqing Wu
• Weiqi Chen
• Wengwei Wang
• Bingqing Peng
• Liang Sun
• Ling Chen

Due to insufficient local area information, numerical weather prediction (NWP) may yield biases for specific areas. Previous studies correct biases mainly by employing handcrafted features or applying data-driven methods intuitively, overlooking the complicated dependencies between weather factors and between areas. To address this issue, we propose WeatherGNN, a local NWP bias-correction method that utilizes Graph Neural Networks (GNNs) to exploit meteorological dependencies and spatial dependencies under the guidance of domain knowledge. Specifically, we introduce a factor GNN to capture area-specific meteorological dependencies adaptively based on spatial heterogeneity and a fast hierarchical GNN to capture dynamic spatial dependencies efficiently guided by Tobler's first and second laws of geography. Our experimental results on two real-world datasets demonstrate that WeatherGNN achieves the state-of-the-art performance, outperforming the best baseline with an average of 4. 75 % on RMSE.

NeurIPS Conference 2023 Conference Paper

One Fits All: Power General Time Series Analysis by Pretrained LM

• Tian Zhou
• Peisong Niu
• Xue Wang
• Liang Sun
• Rong Jin

Although we have witnessed great success of pre-trained models in natural language processing (NLP) and computer vision (CV), limited progress has been made for general time series analysis. Unlike NLP and CV where a unified model can be used to perform different tasks, specially designed approach still dominates in each time series analysis task such as classification, anomaly detection, forecasting, and few-shot learning. The main challenge that blocks the development of pre-trained model for time series analysis is the lack of a large amount of data for training. In this work, we address this challenge by leveraging language or CV models, pre-trained from billions of tokens, for time series analysis. Specifically, we refrain from altering the self-attention and feedforward layers of the residual blocks in the pre-trained language or image model. This model, known as the Frozen Pretrained Transformer (FPT), is evaluated through fine-tuning on all major types of tasks involving time series. Our results demonstrate that pre-trained models on natural language or images can lead to a comparable or state-of-the-art performance in all main time series analysis tasks, as illustrated in Figure1. We also found both theoretically and empirically that the self-attention module behaviors similarly to principle component analysis (PCA), an observation that helps explains how transformer bridges the domain gap and a crucial step towards understanding the universality of a pre-trained transformer. The code is publicly available at https: //anonymous. 4open. science/r/Pretrained-LM-for-TSForcasting-C561.

NeurIPS Conference 2023 Conference Paper

OneNet: Enhancing Time Series Forecasting Models under Concept Drift by Online Ensembling

• Yifan Zhang
• Qingsong Wen
• Xue Wang
• Weiqi Chen
• Liang Sun
• Zhang Zhang
• Liang Wang
• Rong Jin

Online updating of time series forecasting models aims to address the concept drifting problem by efficiently updating forecasting models based on streaming data. Many algorithms are designed for online time series forecasting, with some exploiting cross-variable dependency while others assume independence among variables. Given every data assumption has its own pros and cons in online time series modeling, we propose **On**line **e**nsembling **Net**work (**OneNet**). It dynamically updates and combines two models, with one focusing on modeling the dependency across the time dimension and the other on cross-variate dependency. Our method incorporates a reinforcement learning-based approach into the traditional online convex programming framework, allowing for the linear combination of the two models with dynamically adjusted weights. OneNet addresses the main shortcoming of classical online learning methods that tend to be slow in adapting to the concept drift. Empirical results show that OneNet reduces online forecasting error by more than $\mathbf{50}\\%$ compared to the State-Of-The-Art (SOTA) method.

IJCAI Conference 2023 Conference Paper

Transformers in Time Series: A Survey

• Qingsong Wen
• Tian Zhou
• Chaoli Zhang
• Weiqi Chen
• Ziqing Ma
• Junchi Yan
• Liang Sun

Transformers have achieved superior performances in many tasks in natural language processing and computer vision, which also triggered great interest in the time series community. Among multiple advantages of Transformers, the ability to capture long-range dependencies and interactions is especially attractive for time series modeling, leading to exciting progress in various time series applications. In this paper, we systematically review Transformer schemes for time series modeling by highlighting their strengths as well as limitations. In particular, we examine the development of time series Transformers in two perspectives. From the perspective of network structure, we summarize the adaptations and modifications that have been made to Transformers in order to accommodate the challenges in time series analysis. From the perspective of applications, we categorize time series Transformers based on common tasks including forecasting, anomaly detection, and classification. Empirically, we perform robust analysis, model size analysis, and seasonal-trend decomposition analysis to study how Transformers perform in time series. Finally, we discuss and suggest future directions to provide useful research guidance.

AAAI Conference 2022 Conference Paper

A Hybrid Causal Structure Learning Algorithm for Mixed-Type Data

• Yan Li
• Rui Xia
• Chunchen Liu
• Liang Sun

Inferring the causal structure of a set of random variables is a crucial problem in many disciplines of science. Over the past two decades, various approaches have been proposed for causal discovery from observational data. However, most of the existing methods are designed for either purely discrete or continuous data, which limit their practical usage. In this paper, we target the problem of causal structure learning from observational mixed-type data. Although there are a few methods that are able to handle mixed-type data, they suffer from restrictions, such as linear assumption and poor scalability. To overcome these weaknesses, we formulate the causal mechanisms via mixed structure equation model and prove its identifiability under mild conditions. A novel locally consistent score, named CVMIC, is proposed for causal directed acyclic graph (DAG) structure learning. Moreover, we propose an efficient conditional independence test, named MRCIT, for mixed-type data, which is used in causal skeleton learning and final pruning to further improve the computational efficiency and precision of our model. Experimental results on both synthetic and real-world data demonstrate that our proposed hybrid model outperforms the other state-of-the-art methods. Our source code is available at https: //github. com/DAMO-DI-ML/AAAI2022-HCM.

JBHI Journal 2022 Journal Article

An Explainable 3D Residual Self-Attention Deep Neural Network for Joint Atrophy Localization and Alzheimer’s Disease Diagnosis Using Structural MRI

• Xin Zhang
• Liangxiu Han
• Wenyong Zhu
• Liang Sun
• Daoqiang Zhang

Computer-aided early diagnosis of Alzheimer’s disease (AD) and its prodromal form mild cognitive impairment (MCI) based on structure Magnetic Resonance Imaging (sMRI) has provided a cost-effective and objective way for early prevention and treatment of disease progression, leading to improved patient care. In this work, we have proposed a novel computer-aided approach for early diagnosis of AD by introducing an explainable 3D Residual Attention Deep Neural Network (3D ResAttNet) for end-to-end learning from sMRI scans. Different from the existing approaches, the novelty of our approach is three-fold: 1) A Residual Self-Attention Deep Neural Network has been proposed to capture local, global and spatial information of MR images to improve diagnostic performance; 2) An explainable method using Gradient-based Localization Class Activation mapping (Grad-CAM) has been introduced to improve the interpretability of the proposed method; 3) This work has provided a full end-to-end learning solution for automated disease diagnosis. Our proposed 3D ResAttNet method has been evaluated on a large cohort of subjects from real datasets for two changeling classification tasks (i. e. Alzheimer’s disease (AD) vs. Normal cohort (NC) and progressive MCI (pMCI) vs. stable MCI (sMCI)). The experimental results show that the proposed approach has a competitive advantage over the state-of-the-art models in terms of accuracy performance and generalizability. The explainable mechanism in our approach is able to identify and highlight the contribution of the important brain parts (e. g. , hippocampus, lateral ventricle and most parts of the cortex) for transparent decisions

NeurIPS Conference 2022 Conference Paper

FiLM: Frequency improved Legendre Memory Model for Long-term Time Series Forecasting

• Tian Zhou
• Ziqing Ma
• Xue Wang
• Qingsong Wen
• Liang Sun
• Tao Yao
• Wotao Yin
• Rong Jin

Recent studies have shown that deep learning models such as RNNs and Transformers have brought significant performance gains for long-term forecasting of time series because they effectively utilize historical information. We found, however, that there is still great room for improvement in how to preserve historical information in neural networks while avoiding overfitting to noise present in the history. Addressing this allows better utilization of the capabilities of deep learning models. To this end, we design a Frequency improved Legendre Memory model, or FiLM: it applies Legendre polynomial projections to approximate historical information, uses Fourier projection to remove noise, and adds a low-rank approximation to speed up computation. Our empirical studies show that the proposed FiLM significantly improves the accuracy of state-of-the-art models in multivariate and univariate long-term forecasting by (19. 2%, 22. 6%), respectively. We also demonstrate that the representation module developed in this work can be used as a general plugin to improve the long-term prediction performance of other deep learning modules. Code is available at https: //github. com/tianzhou2011/FiLM/.

NeurIPS Conference 2022 Conference Paper

Towards Out-of-Distribution Sequential Event Prediction: A Causal Treatment

• Chenxiao Yang
• Qitian Wu
• Qingsong Wen
• Zhiqiang Zhou
• Liang Sun
• Junchi Yan

The goal of sequential event prediction is to estimate the next event based on a sequence of historical events, with applications to sequential recommendation, user behavior analysis and clinical treatment. In practice, the next-event prediction models are trained with sequential data collected at one time and need to generalize to newly arrived sequences in remote future, which requires models to handle temporal distribution shift from training to testing. In this paper, we first take a data-generating perspective to reveal a negative result that existing approaches with maximum likelihood estimation would fail for distribution shift due to the latent context confounder, i. e. , the common cause for the historical events and the next event. Then we devise a new learning objective based on backdoor adjustment and further harness variational inference to make it tractable for sequence learning problems. On top of that, we propose a framework with hierarchical branching structures for learning context-specific representations. Comprehensive experiments on diverse tasks (e. g. , sequential recommendation) demonstrate the effectiveness, applicability and scalability of our method with various off-the-shelf models as backbones.

NeurIPS Conference 2021 Conference Paper

Learning Interpretable Decision Rule Sets: A Submodular Optimization Approach

• Fan Yang
• Kai He
• Linxiao Yang
• Hongxia Du
• Jingbang Yang
• Bo Yang
• Liang Sun

Rule sets are highly interpretable logical models in which the predicates for decision are expressed in disjunctive normal form (DNF, OR-of-ANDs), or, equivalently, the overall model comprises an unordered collection of if-then decision rules. In this paper, we consider a submodular optimization based approach for learning rule sets. The learning problem is framed as a subset selection task in which a subset of all possible rules needs to be selected to form an accurate and interpretable rule set. We employ an objective function that exhibits submodularity and thus is amenable to submodular optimization techniques. To overcome the difficulty arose from dealing with the exponential-sized ground set of rules, the subproblem of searching a rule is casted as another subset selection task that asks for a subset of features. We show it is possible to write the induced objective function for the subproblem as a difference of two submodular (DS) functions to make it approximately solvable by DS optimization algorithms. Overall, the proposed approach is simple, scalable, and likely to be benefited from further research on submodular optimization. Experiments on real datasets demonstrate the effectiveness of our method.

IJCAI Conference 2021 Conference Paper

Time Series Data Augmentation for Deep Learning: A Survey

• Qingsong Wen
• Liang Sun
• Fan Yang
• Xiaomin Song
• Jingkun Gao
• Xue Wang
• Huan Xu

Deep learning performs remarkably well on many time series analysis tasks recently. The superior performance of deep neural networks relies heavily on a large number of training data to avoid overfitting. However, the labeled data of many real-world time series applications may be limited such as classification in medical time series and anomaly detection in AIOps. As an effective way to enhance the size and quality of the training data, data augmentation is crucial to the successful application of deep learning models on time series data. In this paper, we systematically review different data augmentation methods for time series. We propose a taxonomy for the reviewed methods, and then provide a structured review for these methods by highlighting their strengths and limitations. We also empirically compare different data augmentation methods for different tasks including time series classification, anomaly detection, and forecasting. Finally, we discuss and highlight five future directions to provide useful research guidance.

JBHI Journal 2020 Journal Article

Adaptive Feature Selection Guided Deep Forest for COVID-19 Classification With Chest CT

• Liang Sun
• Zhanhao Mo
• Fuhua Yan
• Liming Xia
• Fei Shan
• Zhongxiang Ding
• Bin Song
• Wanchun Gao

Chest computed tomography (CT) becomes an effective tool to assist the diagnosis of coronavirus disease-19 (COVID-19). Due to the outbreak of COVID-19 worldwide, using the computed-aided diagnosis technique for COVID-19 classification based on CT images could largely alleviate the burden of clinicians. In this paper, we propose an A daptive F eature S election guided D eep F orest (AFS-DF) for COVID-19 classification based on chest CT images. Specifically, we first extract location-specific features from CT images. Then, in order to capture the high-level representation of these features with the relatively small-scale data, we leverage a deep forest model to learn high-level representation of the features. Moreover, we propose a feature selection method based on the trained deep forest model to reduce the redundancy of features, where the feature selection could be adaptively incorporated with the COVID-19 classification model. We evaluated our proposed AFS-DF on COVID-19 dataset with 1495 patients of COVID-19 and 1027 patients of community acquired pneumonia (CAP). The accuracy (ACC), sensitivity (SEN), specificity (SPE), AUC, precision and F1-score achieved by our method are 91. 79%, 93. 05%, 89. 95%, 96. 35%, 93. 10% and 93. 07%, respectively. Experimental results on the COVID-19 dataset suggest that the proposed AFS-DF achieves superior performance in COVID-19 vs. CAP classification, compared with 4 widely used machine learning methods.

AIIM Journal 2019 Journal Article

Reliability-based robust multi-atlas label fusion for brain MRI segmentation

• Liang Sun
• Chen Zu
• WEI SHAO
• Junye Guang
• Daoqiang Zhang
• Mingxia Liu

Label fusion is one of the key steps in multi-atlas based segmentation of structural magnetic resonance (MR) images. Although a number of label fusion methods have been developed in literature, most of those existing methods fail to address two important problems, i. e. , (1) compared with boundary voxels, inner voxels usually have higher probability (or reliability) to be correctly segmented, and (2) voxels with high segmentation reliability (after initial segmentation) can help refine the segmentation of voxels with low segmentation reliability in the target image. To this end, we propose a general reliability-based robust label fusion framework for multi-atlas based MR image segmentation. Specifically, in the first step, we perform initial segmentation for MR images using a conventional multi-atlas label fusion method. In the second step, for each voxel in the target image, we define two kinds of reliability, including the label reliability and spatial reliability that are estimated based on the soft label and spatial information from the initial segmentation, respectively. Finally, we employ voxels with high label-spatial reliability to help refine the label fusion process of those with low reliability in the target image. We incorporate our proposed framework into four well-known label fusion methods, including locally-weighted voting (LWV), non-local mean patch-based method (PBM), joint label fusion (JLF) and sparse patch-based method (SPBM), and obtain four novel label-spatial reliability-based label fusion approaches (called ls-LWV, ls-PBM, ls-JLF, and ls-SPBM). We validate the proposed methods in segmenting ROIs of brain MR images from the NIREP, LONI-LPBA40 and ADNI datasets. The experimental results demonstrate that our label-spatial reliability-based label fusion methods outperform the state-of-the-art methods in multi-atlas image segmentation.

AAAI Conference 2019 Conference Paper

RobustSTL: A Robust Seasonal-Trend Decomposition Algorithm for Long Time Series

• Qingsong Wen
• Jingkun Gao
• Xiaomin Song
• Liang Sun
• Huan Xu
• Shenghuo Zhu

Decomposing complex time series into trend, seasonality, and remainder components is an important task to facilitate time series anomaly detection and forecasting. Although numerous methods have been proposed, there are still many time series characteristics exhibiting in real-world data which are not addressed properly, including 1) ability to handle seasonality fluctuation and shift, and abrupt change in trend and reminder; 2) robustness on data with anomalies; 3) applicability on time series with long seasonality period. In the paper, we propose a novel and generic time series decomposition algorithm to address these challenges. Specifically, we extract the trend component robustly by solving a regression problem using the least absolute deviations loss with sparse regularization. Based on the extracted trend, we apply the the non-local seasonal filtering to extract the seasonality component. This process is repeated until accurate decomposition is obtained. Experiments on different synthetic and real-world time series datasets demonstrate that our method outperforms existing solutions.

IJCAI Conference 2019 Conference Paper

RobustTrend: A Huber Loss with a Combined First and Second Order Difference Regularization for Time Series Trend Filtering

• Qingsong Wen
• Jingkun Gao
• Xiaomin Song
• Liang Sun
• Jian Tan

Extracting the underlying trend signal is a crucial step to facilitate time series analysis like forecasting and anomaly detection. Besides noise signal, time series can contain not only outliers but also abrupt trend changes in real-world scenarios. To deal with these challenges, we propose a robust trend filtering algorithm based on robust statistics and sparse learning. Specifically, we adopt the Huber loss to suppress outliers, and utilize a combination of the first order and second order difference on the trend component as regularization to capture both slow and abrupt trend changes. Furthermore, an efficient method is designed to solve the proposed robust trend filtering based on majorization minimization (MM) and alternative direction method of multipliers (ADMM). We compared our proposed robust trend filter with other nine state-of-the-art trend filtering algorithms on both synthetic and real-world datasets. The experiments demonstrate that our algorithm outperforms existing methods.

YNIMG Journal 2019 Journal Article

Topological correction of infant white matter surfaces using anatomically constrained convolutional neural network

• Liang Sun
• Daoqiang Zhang
• Chunfeng Lian
• Li Wang
• Zhengwang Wu
• WEI SHAO
• Weili Lin
• Dinggang Shen

Reconstruction of accurate cortical surfaces without topological errors (i. e. , handles and holes) from infant brain MR images is very important in early brain development studies. However, infant brain MR images typically suffer extremely low tissue contrast and dynamic imaging appearance patterns. Thus, it is inevitable to have large amounts of topological errors in the segmented infant brain tissue images, which lead to inaccurately reconstructed cortical surfaces with topological errors. To address this issue, inspired by recent advances in deep learning, we propose an anatomically constrained network for topological correction on infant cortical surfaces. Specifically, in our method, we first locate regions of potential topological defects by leveraging a topology-preserving level set method. Then, we propose an anatomically constrained network to correct those candidate voxels in the located regions. Since infant cortical surfaces often contain large and complex handles or holes, it is difficult to completely correct all errors using one-shot correction. Therefore, we further enroll these two steps into an iterative framework to gradually correct large topological errors. To the best of our knowledge, this is the first work to introduce deep learning approach for topological correction of infant cortical surfaces. We compare our method with the state-of-the-art methods on both simulated topological errors and real topological errors in human infant brain MR images. Moreover, we also validate our method on the infant brain MR images of macaques. All experimental results show the superior performance of the proposed method.

AAAI Conference 2019 Conference Paper

Which Factorization Machine Modeling Is Better: A Theoretical Answer with Optimal Guarantee

• Ming Lin
• Shuang Qiu
• Jieping Ye
• Xiaomin Song
• Qi Qian
• Liang Sun
• Shenghuo Zhu
• Rong Jin

Factorization machine (FM) is a popular machine learning model to capture the second order feature interactions. The optimal learning guarantee of FM and its generalized version is not yet developed. For a rank k generalized FM of d dimensional input, the previous best known sampling complexity is O[k3 d · polylog(kd)] under Gaussian distribution. This bound is sub-optimal comparing to the information theoretical lower bound O(kd). In this work, we aim to tighten this bound towards optimal and generalize the analysis to sub-gaussian distribution. We prove that when the input data satisfies the so-called τ-Moment Invertible Property, the sampling complexity of generalized FM can be improved to O[k2 d · polylog(kd)/τ2 ]. When the second order self-interaction terms are excluded in the generalized FM, the bound can be improved to the optimal O[kd · polylog(kd)] up to the logarithmic factors. Our analysis also suggests that the positive semi-definite constraint in the conventional FM is redundant as it does not improve the sampling complexity while making the model difficult to optimize. We evaluate our improved FM model in real-time high precision GPS signal calibration task to validate its superiority.

NeurIPS Conference 2011 Conference Paper

Projection onto A Nonnegative Max-Heap

• Jun Liu
• Liang Sun
• Jieping Ye

We consider the problem of computing the Euclidean projection of a vector of length $p$ onto a non-negative max-heap---an ordered tree where the values of the nodes are all nonnegative and the value of any parent node is no less than the value(s) of its child node(s). This Euclidean projection plays a building block role in the optimization problem with a non-negative max-heap constraint. Such a constraint is desirable when the features follow an ordered tree structure, that is, a given feature is selected for the given regression/classification task only if its parent node is selected. In this paper, we show that such Euclidean projection problem admits an analytical solution and we develop a top-down algorithm where the key operation is to find the so-called \emph{maximal root-tree} of the subtree rooted at each node. A naive approach for finding the maximal root-tree is to enumerate all the possible root-trees, which, however, does not scale well. We reveal several important properties of the maximal root-tree, based on which we design a bottom-up algorithm with merge for efficiently finding the maximal root-tree. The proposed algorithm has a (worst-case) linear time complexity for a sequential list, and $O(p^2)$ for a general tree. We report simulation results showing the effectiveness of the max-heap for regression with an ordered tree structure. Empirical results show that the proposed algorithm has an expected linear time complexity for many special cases including a sequential list, a full binary tree, and a tree with depth 1.

YNIMG Journal 2010 Journal Article

Learning brain connectivity of Alzheimer's disease by sparse inverse covariance estimation

• Shuai Huang
• Jing Li
• Liang Sun
• Jieping Ye
• Adam Fleisher
• Teresa Wu
• Kewei Chen
• Eric Reiman

Rapid advances in neuroimaging techniques provide great potentials for study of Alzheimer's disease (AD). Existing findings have shown that AD is closely related to alteration in the functional brain network, i. e. , the functional connectivity between different brain regions. In this paper, we propose a method based on sparse inverse covariance estimation (SICE) to identify functional brain connectivity networks from PET data. Our method is able to identify both the connectivity network structure and strength for a large number of brain regions with small sample sizes. We apply the proposed method to the PET data of AD, mild cognitive impairment (MCI), and normal control (NC) subjects. Compared with NC, AD shows decrease in the amount of inter-region functional connectivity within the temporal lobe especially between the area around hippocampus and other regions and increase in the amount of connectivity within the frontal lobe as well as between the parietal and occipital lobes. Also, AD shows weaker between-lobe connectivity than within-lobe connectivity and weaker between-hemisphere connectivity, compared with NC. In addition to being a method for knowledge discovery about AD, the proposed SICE method can also be used for classifying new subjects, which makes it a suitable approach for novel connectivity-based AD biomarker identification. Our experiments show that the best sensitivity and specificity our method can achieve in AD vs. NC classification are 88% and 88%, respectively.

IJCAI Conference 2009 Conference Paper

• Liang Sun
• Shuiwang Ji
• Shipeng Yu
• Jieping Ye

Canonical correlation analysis (CCA) and partial least squares (PLS) are well-known techniques for feature extraction from two sets of multidimensional variables. The fundamental difference between CCA and PLS is that CCA maximizes the correlation while PLS maximizes the covariance. Although both CCA and PLS have been applied successfully in various applications, the intrinsic relationship between them remains unclear. In this paper, we attempt to address this issue by showing the equivalence relationship between CCA and orthonormalized partial least squares (OPLS), a variant of PLS. We further extend the equivalence relationship to the case when regularization is employed for both sets of variables. In addition, we show that the CCA projection for one set of variables is independent of the regularization on the other set of variables. We have performed experimental studies using both synthetic and real data sets and our results confirm the established equivalence relationship. The presented analysis provides novel insights into the connection between these two existing algorithms as well as the effect of the regularization.

IJCAI Conference 2009 Conference Paper

• Zheng Zhao
• Liang Sun
• Shipeng Yu
• Huan Liu
• Jieping Ye

Kernel discriminant analysis (KDA) is an effective approach for supervised nonlinear dimensionality reduction. Probabilistic models can be used with KDA to improve its robustness. However, the state of the art of such models could only handle binary class problems, which confines their application in many real world problems. To overcome this limitation, we propose a novel nonparametric probabilistic model based on Gaussian Process for KDA to handle multiclass problems. The model provides a novel Bayesian interpretation for KDA, which allows its parameters to be automatically tuned through the optimization of the marginal loglikelihood of the data. Empirical study demonstrates the efficacy of the proposed model.

NeurIPS Conference 2009 Conference Paper

Efficient Recovery of Jointly Sparse Vectors

• Liang Sun
• Jun Liu
• Jianhui Chen
• Jieping Ye

We consider the reconstruction of sparse signals in the multiple measurement vector (MMV) model, in which the signal, represented as a matrix, consists of a set of jointly sparse vectors. MMV is an extension of the single measurement vector (SMV) model employed in standard compressive sensing (CS). Recent theoretical studies focus on the convex relaxation of the MMV problem based on the $(2, 1)$-norm minimization, which is an extension of the well-known $1$-norm minimization employed in SMV. However, the resulting convex optimization problem in MMV is significantly much more difficult to solve than the one in SMV. Existing algorithms reformulate it as a second-order cone programming (SOCP) or semidefinite programming (SDP), which is computationally expensive to solve for problems of moderate size. In this paper, we propose a new (dual) reformulation of the convex optimization problem in MMV and develop an efficient algorithm based on the prox-method. Interestingly, our theoretical analysis reveals the close connection between the proposed reformulation and multiple kernel learning. Our simulation studies demonstrate the scalability of the proposed algorithm.

NeurIPS Conference 2009 Conference Paper

Learning Brain Connectivity of Alzheimer's Disease from Neuroimaging Data

• Shuai Huang
• Jing Li
• Liang Sun
• Jun Liu
• Teresa Wu
• Kewei Chen
• Adam Fleisher
• Eric Reiman

Recent advances in neuroimaging techniques provide great potentials for effective diagnosis of Alzheimer’s disease (AD), the most common form of dementia. Previous studies have shown that AD is closely related to alternation in the functional brain network, i. e. , the functional connectivity among different brain regions. In this paper, we consider the problem of learning functional brain connectivity from neuroimaging, which holds great promise for identifying image-based markers used to distinguish Normal Controls (NC), patients with Mild Cognitive Impairment (MCI), and patients with AD. More specifically, we study sparse inverse covariance estimation (SICE), also known as exploratory Gaussian graphical models, for brain connectivity modeling. In particular, we apply SICE to learn and analyze functional brain connectivity patterns from different subject groups, based on a key property of SICE, called the “monotone property” we established in this paper. Our experimental results on neuroimaging PET data of 42 AD, 116 MCI, and 67 NC subjects reveal several interesting connectivity patterns consistent with literature findings, and also some new patterns that can help the knowledge discovery of AD.

NeurIPS Conference 2008 Conference Paper

Multi-label Multiple Kernel Learning

• Shuiwang Ji
• Liang Sun
• Rong Jin
• Jieping Ye

We present a multi-label multiple kernel learning (MKL) formulation, in which the data are embedded into a low-dimensional space directed by the instance-label correlations encoded into a hypergraph. We formulate the problem in the kernel-induced feature space and propose to learn the kernel matrix as a linear combination of a given collection of kernel matrices in the MKL framework. The proposed learning formulation leads to a non-smooth min-max problem, and it can be cast into a semi-infinite linear program (SILP). We further propose an approximate formulation with a guaranteed error bound which involves an unconstrained and convex optimization problem. In addition, we show that the objective function of the approximate formulation is continuously differentiable with Lipschitz gradient, and hence existing methods can be employed to compute the optimal solution efficiently. We apply the proposed formulation to the automated annotation of Drosophila gene expression pattern images, and promising results have been reported in comparison with representative algorithms.