Author name cluster

Ting Li

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.

27 papers

2 author rows

YNIMG Journal 2026 Journal Article

Divergent neural mechanisms of reward processing and cognitive control in non-substance and substance addiction: A meta-analytic perspective

Qi Li
Mei Du
Jing Xiao
Ting Li
Kesong Hu
Song Tu
Xun Liu
Lingxiao Wang

Addiction disorders, encompassing non-substance and substance addiction, are a prevalent and devastating class of mental illnesses. The dual-system theory of addiction posits that abnormal processing in the brain's reward and control systems underlies addictive behaviors. However, challenges in previous neuroimaging studies on addiction, including small sample sizes, subjective narrative reviews, and inconsistent findings, have limited the comprehensive clarification of the neural mechanisms underlying addiction. This meta-analysis addresses these limitations by integrating neuroimaging data from multiple studies. Here, the random-effects activation likelihood estimation (ALE) method was applied to systematically synthesize data to elucidate the neural mechanisms of reward processing and cognitive control in non-substance and substance addiction. The study revealed that individuals with non-substance addiction presented increased dorsal anterior cingulate cortex (dACC) and caudate activation during cue reactivity, enhanced putamen and globus pallidus responses to non-specific rewards, and no significant group differences in cognitive control tasks. In contrast, substance addiction was found to be characterized by heightened activation in the rostral anterior cingulate cortex (rACC), ventromedial prefrontal cortex (vmPFC) and putamen during cue reactivity, accompanied by reduced responses of the nucleus accumbens (NAc) to non-specific rewards and reduced activation in the inferior parietal lobule (IPL) during cognitive-control tasks. These findings not only reveal a potential "motivation-control equilibrium" mechanism in non-substance addiction but also support the dual-system framework for substance addiction, providing neurobiological targets for precision interventions.

EAAI Journal 2026 Journal Article

Robust adaptive-neighbor-induced optimization to nonnegative matrix factorization with regularized strategies in the framework of semi-supervised learning

Jie Guo
Ting Li
Jialu Liu
Zhong Wan
Fang Zhang

As an efficient tool in artificial intelligence, nonnegative matrix factorization (NMF) is widely used for data clustering and feature discovery, yet existing models are often sensitive to noise and outliers and lack effective mechanisms to exploit limited supervisory information in semi-supervised settings. To address these limitations, this paper proposes a novel robust NMF optimization model within a semi-supervised learning framework, introducing a reconstruction-error-based loss function to bolster robustness and an adaptive neighbor induced strategy to propagate pairwise constraints via dynamic similarity graphs, along with a dataset-adaptive mechanism to refine sample similarity weighting. For this model, we develop an efficient optimization algorithm with convergence guarantees. Extensive experiments on twelve public image and text datasets demonstrate that the proposed method outperforms state-of-the-art alternatives across multiple clustering metrics, confirming its effectiveness in noisy environments and demonstrating its capacity to leverage supervisory information for improved clustering performance.

JMLR Journal 2026 Journal Article

Two-way Node Popularity Model for Directed and Bipartite Networks

Bing-Yi Jing
Ting Li
Jiangzhou Wang
Ya Wang

There has been increasing research attention on community detection in directed and bipartite networks. However, these studies often fail to consider the popularity of nodes in different communities, which is a common phenomenon in real-world networks. To address this issue, we propose a new probabilistic framework called the Two-Way Node Popularity Model (TNPM). The TNPM also accommodates edges from different distributions within a general sub-Gaussian family. We introduce the Delete-One-Method (DOM) for model fitting and community structure identification, and provide a comprehensive theoretical analysis with novel technical skills dealing with sub-Gaussian generalization. Additionally, we propose the Two-Stage Divided Cosine Algorithm (TSDC) to handle large-scale networks more efficiently. Our proposed methods offer multi-folded advantages in terms of estimation accuracy and computational efficiency, as demonstrated through extensive numerical studies. We apply our methods to two real-world applications, uncovering interesting findings. [abs] [ pdf ][ bib ] [ code ] &copy JMLR 2026. ( edit, beta )

ICML Conference 2025 Conference Paper

Differentially Private Analysis for Binary Response Models: Optimality, Estimation, and Inference

Ce Zhang
Yixin Han
Yafei Wang
Xiaodong Yan
Linglong Kong
Ting Li
Bei Jiang

Randomized response (RR) mechanisms constitute a fundamental and effective technique for ensuring label differential privacy (LabelDP). However, existing RR methods primarily focus on the response labels while overlooking the influence of covariates and often do not fully address optimality. To address these challenges, this paper explores optimal LabelDP procedures using RR mechanisms, focusing on achieving optimal estimation and inference in binary response models. We first analyze the asymptotic behaviors of RR binary response models and then optimize the procedure by maximizing the trace of the Fisher Information Matrix within the $\varepsilon$- and $(\varepsilon, \delta)$-LabelDP constraints. Our theoretical results indicate that the proposed methods achieve optimal LabelDP guarantees while maintaining statistical accuracy in binary response models under mild conditions. Furthermore, we develop private confidence intervals with nominal coverage for statistical inference. Extensive simulation studies and real-world applications confirm that our methods outperform existing approaches in terms of precise estimation, privacy protection, and reliable inference.

JBHI Journal 2025 Journal Article

Fine-Grained Temporal Site Monitoring in EGD Streams via Visual Time-Aware Embedding and Vision-Text Asymmetric Coworking

Fang Peng
Hongkuan Shi
Shiquan He
Qiang Hu
Ting Li
Fan Huang
Xinxia Feng
Mei Liu

Esophagogastroduodenoscopy (EGD) requires inspecting plentiful upper gastrointestinal (UGI) sites completely for a precise cancer screening. Automated temporal site monitoring for EGD assistance is thus of high demand, yet often fails if directly applying the existing methods of online action detection. The key challenges are two-fold: 1) the global camera motion dominates, invalidating the temporal patterns derived from the object optical flows, and 2) the UGI sites are fine-grained, yielding highly homogenized appearances. In this paper, we propose an EGD-customized model, powered by two novel designs, i. e. , Visual Time-aware Embedding plus Vision-text Asymmetric Coworking (VTE+VAC), for real-time accurate fine-grained UGI site monitoring. Concretely, VTE learns visual embeddings by differentiating frames via classification losses, and meanwhile by reordering the sampled time-agnostic frames to be temporally coherent via a ranking loss. Such joint objective encourages VTE to capture the sequential relation without resorting to the inapplicable object optical flows, and thus to provide the time-aware frame-wise embeddings. In the subsequent analysis, VAC uses a temporal sliding window, and extracts vision-text multimodal knowledge from each frame and its corresponding textualized prediction via the learned VTE and a frozen BERT. The text embeddings help provide more representative cues, but also may cause misdirection due to prediction errors. Thus, VAC randomly drops or replaces historical predictions to increase the error tolerance to avoid collapsing onto the last few predictions. Qualitative and quantitative experiments demonstrate that the proposed method achieves superior performance compared to other state-of-the-art methods, with an average F1-score improvement of at least 7. 66%.

EAAI Journal 2025 Journal Article

Hypergraph induced semi-supervised orthogonal nonnegative matrix factorization with label and constraint propagation

Jie Guo
Ting Li
Jialu Liu
Zhong Wan

As a popular technology of artificial intelligence, nonnegative matrix factorization (NMF) aims at clustering and finding the differentially expressed features of each cluster. However, for complex high-dimensional sample data, it is still a challenge to design more appropriate NMF optimization models and develop more efficient algorithms to solve this model in view of enhanced theoretical properties and numerical performance. In this paper, a novel NMF optimization model with regularization is proposed such that the NMF is performed by a semi-supervised approach, as well as incorporating the strategies of hypergraph induced label propagation and constraint propagation. Specifically, different from existing NMF methods, the hypergraph structure underlying the data, together with the simple graph information, is employed to guide the pairwise constraint propagation in our built model. In recognition of sample similarity, a dataset-adaptive strategy is proposed to update the weight matrix of the graphs. By adding dual orthogonality on the factor matrices in the objective function, interpretability and feature independence of the built model are enhanced. Then, an algorithm is developed to efficiently solve this complicated model. Theoretically, it is proved that the developed algorithms are well defined and convergent. Numerically, extensive tests on the proposed model and algorithm are performed, which validate that they outperform the state-of-the-art ones in terms of different metrics of evaluating clustering performance when they are applied into solution of the problems from eight public datasets.

JBHI Journal 2025 Journal Article

Multi-View Fused Nonnegative Matrix Completion Methods for Drug-Target Interaction Prediction

Ting Li
Chuanqi Lao
Zhao Li
Hongyang Chen

Accurate prediction of drug-target interactions (DTIs) is crucial for accelerating drug discovery and reducing experimental costs. However, challenges such as sparse interactions and heterogeneous datasets complicate this prediction. In this study, we hypothesize that leveraging nonnegative matrix completion and integrating heterogeneous similarity information from multiple biological views can improve the accuracy, interpretability, and scalability of DTI prediction. To validate this, we propose two multi-view fused nonnegative matrix completion methods that combine three key components: (1) a nonnegative matrix completion framework that avoids heuristic rank selection and ensures biologically interpretable predictions; (2) a linear multi-view fusion mechanism, where weights over multiple drug and target similarity matrices are jointly learned through linearly constrained quadratic programming; and (3) multi-graph Laplacian regularization to preserve structural properties within each view. The optimization is performed using two efficient proximal linearization-incorporated block coordinate descent algorithms. Extensive experiments on four gold-standard datasets and a larger real-world dataset demonstrate that our models consistently outperform state-of-the-art single-view, multi-view and deep learning-based DTI prediction methods. Furthermore, ablation studies confirm the contribution of each model component, and scalability analysis highlights the computational efficiency of our approach.

ICML Conference 2025 Conference Paper

Online Differentially Private Conformal Prediction for Uncertainty Quantification

Qiangqiang Zhang
Ting Li
Xinwei Feng
Xiaodong Yan
Jinhan Xie

Traditional conformal prediction faces significant challenges with the rise of streaming data and increasing concerns over privacy. In this paper, we introduce a novel online differentially private conformal prediction framework, designed to construct dynamic, model-free private prediction sets. Unlike existing approaches that either disregard privacy or require full access to the entire dataset, our proposed method ensures individual privacy with a one-pass algorithm, ideal for real-time, privacy-preserving decision-making. Theoretically, we establish guarantees for long-run coverage at the nominal confidence level. Moreover, we extend our method to conformal quantile regression, which is fully adaptive to heteroscedasticity. We validate the effectiveness and applicability of the proposed method through comprehensive simulations and real-world studies on the ELEC2 and PAMAP2 datasets.

NeurIPS Conference 2025 Conference Paper

Online Locally Differentially Private Conformal Prediction via Binary Inquiries

Qiangqiang Zhang
Chenfei Gu
Xinwei Feng
Jinhan Xie
Ting Li

We propose an online conformal prediction framework under local differential privacy to address the emerging challenge of privacy-preserving uncertainty quantification in streaming data environments. Our method constructs dynamic, model-free prediction sets based on randomized binary inquiries, ensuring rigorous privacy protection without requiring access to raw data. Importantly, the proposed algorithm can be conducted in a one-pass online manner, leading to high computational efficiency and minimal storage requirements with $\mathcal{O}(1)$ space complexity, making it particularly suitable for real-time applications. The proposed framework is also broadly applicable to both regression and classification tasks, adapting flexibly to diverse predictive settings. We establish theoretical guarantees for long-run coverage at a target confidence level, ensuring statistical reliability under strict privacy constraints. Extensive empirical evaluations on both simulated and real-world datasets demonstrate that the proposed method delivers accurate, stable, and privacy-preserving predictions across a range of dynamic environments.

NeurIPS Conference 2025 Conference Paper

Online robust locally differentially private learning for nonparametric regression

Chenfei Gu
Qiangqiang Zhang
Ting Li
Jinhan Xie
Niansheng Tang

The growing prevalence of streaming data and increasing concerns over data privacy pose significant challenges for traditional nonparametric regression methods, which are often ill-suited for real-time, privacy-aware learning. In this paper, we tackle these issues by first proposing a novel one-pass online functional stochastic gradient descent algorithm that leverages the Huber loss (H-FSGD), to improve robustness against outliers and heavy-tailed errors in dynamic environments. To further accommodate privacy constraints, we introduce a locally differentially private extension, Private H-FSGD (PH-FSGD), designed to real-time, privacy-preserving estimation. Theoretically, we conduct a comprehensive non-asymptotic convergence analysis of the proposed estimators, establishing finite-sample guarantees and identifying optimal step size schedules that achieve optimal convergence rates. In particular, we provide practical insights into the impact of key hyperparameters, such as step size and privacy budget, on convergence behavior. Extensive experiments validate our theoretical findings, demonstrating that our methods achieve strong robustness and privacy protection without sacrificing efficiency.

NeurIPS Conference 2025 Conference Paper

Pessimistic Data Integration for Policy Evaluation

Xiangkun Wu
Ting Li
Gholamali Aminian
Armin Behnamnia
Hamid Rabiee
Chengchun Shi

This paper studies how to integrate historical control data with experimental data to enhance A/B testing, while addressing the distributional shift between historical and experimental datasets. We propose a pessimistic data integration method that combines two causal effect estimators constructed based on experimental and historical datasets. Our main idea is to conceptualize the weight function for this combination as a policy so that existing pessimistic policy learning algorithms are applicable to learn the optimal weight that minimizes the resulting weighted estimator's mean squared error. Additionally, we conduct comprehensive theoretical and empirical analyses to compare our method against various baseline estimators across five scenarios. Both our theoretical and numerical findings demonstrate that the proposed estimator achieves near-optimal performance across all scenarios.

YNIMG Journal 2024 Journal Article

Activity flow under the manipulation of cognitive load and training

Wanyun Zhao
Kaiqiang Su
Hengcheng Zhu
Marcus Kaiser
Mingxia Fan
Yong Zou
Ting Li
Dazhi Yin

Flexible cognitive functions, such as working memory (WM), usually require a balance between localized and distributed information processing. However, it is challenging to uncover how local and distributed processing specifically contributes to task-induced activity in a region. Although the recently proposed activity flow mapping approach revealed the relative contribution of distributed processing, few studies have explored the adaptive and plastic changes that underlie cognitive manipulation. In this study, we recruited 51 healthy volunteers (31 females) and investigated how the activity flow and brain activation of the frontoparietal systems was modulated by WM load and training. While the activation of both executive control network (ECN) and dorsal attention network (DAN) increased linearly with memory load at baseline, the relative contribution of distributed processing showed a linear response only in the DAN, which was prominently attributed to within-network activity flow. Importantly, adaptive training selectively induced an increase in the relative contribution of distributed processing in the ECN and also a linear response to memory load, which were predominantly due to between-network activity flow. Furthermore, we demonstrated a causal effect of activity flow prediction through training manipulation on connectivity and activity. In contrast with classic brain activation estimation, our findings suggest that the relative contribution of distributed processing revealed by activity flow prediction provides unique insights into neural processing of frontoparietal systems under the manipulation of cognitive load and training. This study offers a new methodological framework for exploring information integration versus segregation underlying cognitive processing.

YNIMG Journal 2024 Journal Article

Association between low-frequency oscillation and cognitive compensation in high-performance group: An fNIRS mapping study

Xiang Ji
Qiwei Dong
Zhanxu Liu
Jiangbo Pu
Ting Li

Brain lateralization is known to enhance cognitive efficiency by reducing redundant processing. Theories such as HAROLD and CRUNCH propose that cognitive decline with age can be compensated by the recruitment of additional bilateral brain regions. However, cognitive compensation is not always effective, and the underlying mechanisms remain unclear, particularly those not related to aging. Low-frequency oscillation (LFO) may be a potential factor in this process. This study investigated the relationship between LFO and cognitive compensation in the prefrontal cortex (PFC) of 28 young adults during a visual verbal working memory task, utilizing functional near-infrared spectroscopy (fNIRS). The participants were categorized into high- and low-performance groups. Changes in oxygenated hemoglobin (Δ[oxy-Hb]), deoxygenated hemoglobin (Δ[deoxy-Hb]), and total hemoglobin (Δ[tot-Hb]) were measured. Both groups exhibited reduced lateralization and increased PFC activation under cognitive load. The results show that only the high-performance group displayed enhanced Δ[oxy-Hb] LFO power, which correlated with behavioral performance. In conclusion, this study found that insufficient LFO is associated with a lack of cognitive resources, which may be due to a deficiency in cerebral autoregulation (CA). This deficiency results in an absence of low-frequency rhythms during cognitive processes, hindering effective coordination between distant brain regions. This provides new insights into the non-aging-related cognitive compensation mechanism.

ICML Conference 2024 Conference Paper

Bayesian Power Steering: An Effective Approach for Domain Adaptation of Diffusion Models

Ding Huang
Ting Li
Jian Huang

We propose a Bayesian framework for fine-tuning large diffusion models with a novel network structure called Bayesian Power Steering (BPS). We clarify the meaning behind adaptation from a large probability space to a small probability space and explore the task of fine-tuning pre-trained models using learnable modules from a Bayesian perspective. BPS extracts task-specific knowledge from a pre-trained model’s learned prior distribution. It efficiently leverages large diffusion models, differentially intervening different hidden features with a head-heavy and foot-light configuration. Experiments highlight the superiority of BPS over contemporary methods across a range of tasks even with limited amount of data. Notably, BPS attains an FID score of 10. 49 under the sketch condition on the COCO17 dataset.

YNIMG Journal 2024 Journal Article

Brain responses to self- and other- unfairness under resource distribution context: Meta-analysis of fMRI studies

Qi Li
Xinyu Lai
Ting Li
Kristoffer Hougaard Madsen
Jing Xiao
Kesong Hu
Chunliang Feng
Di Fu

Under resource distribution context, individuals have a strong aversion to unfair treatment not only toward themselves but also toward others. However, there is no clear consensus regarding the commonality and distinction between these two types of unfairness. Moreover, many neuroimaging studies have investigated how people evaluate and respond to unfairness in the abovementioned two contexts, but the consistency of the results remains to be investigated. To resolve these two issues, we sought to summarize existing findings regarding unfairness to self and others and to further elucidate the neural underpinnings related to distinguishing evaluation and response processes through meta-analyses of previous neuroimaging studies. Our results indicated that both types of unfairness consistently activate the affective and conflict-related anterior insula (AI) and dorsal anterior cingulate cortex/supplementary motor area (dACC/SMA), but the activations related to unfairness to self appeared stronger than those related to others, suggesting that individuals had negative reactions to both unfairness and a greater aversive response toward unfairness to self. During the evaluation process, unfairness to self activated the bilateral AI, dACC, and right dorsolateral prefrontal cortex (DLPFC), regions associated with unfairness aversion, conflict, and cognitive control, indicating reactive, emotional and automatic responses. In contrast, unfairness to others activated areas associated with theory of mind, the inferior parietal lobule and temporoparietal junction (IPL-TPJ), suggesting that making rational judgments from the perspective of others was needed. During the response, unfairness to self activated the affective-related left AI and striatum, whereas unfairness to others activated cognitive control areas, the left DLPFC and the thalamus. This indicated that the former maintained the traits of automaticity and emotionality, whereas the latter necessitated cognitive control. These findings provide a fine-grained description of the common and distinct neurocognitive mechanisms underlying unfairness to self and unfairness to others. Overall, this study not only validates the inequity aversion model but also provides direct evidence of neural mechanisms for neurobiological models of fairness.

ICML Conference 2024 Conference Paper

Combining Experimental and Historical Data for Policy Evaluation

Ting Li
Chengchun Shi
Qianglin Wen
Yang Sui
Yongli Qin
Chunbo Lai
Hongtu Zhu

This paper studies policy evaluation with multiple data sources, especially in scenarios that involve one experimental dataset with two arms, complemented by a historical dataset generated under a single control arm. We propose novel data integration methods that linearly integrate base policy value estimators constructed based on the experimental and historical data, with weights optimized to minimize the mean square error (MSE) of the resulting combined estimator. We further apply the pessimistic principle to obtain more robust estimators, and extend these developments to sequential decision making. Theoretically, we establish non-asymptotic error bounds for the MSEs of our proposed estimators, and derive their oracle, efficiency and robustness properties across a broad spectrum of reward shift scenarios. Numerical experiments and real-data-based analyses from a ridesharing company demonstrate the superior performance of the proposed estimators.

YNIMG Journal 2024 Journal Article

Common neural dysfunction of economic decision-making across psychiatric conditions

Chunliang Feng
Qingxia Liu
Chuangbing Huang
Ting Li
Li Wang
Feilong Liu
Simon B. Eickhoff
Chen Qu

Adaptive decision-making, which is often impaired in various psychiatric conditions, is essential for well-being. Recent evidence has indicated that decision-making capacity in multiple tasks could be accounted for by latent dimensions, enlightening the question of whether there is a common disruption of brain networks in economic decision-making across psychiatric conditions. Here, we addressed the issue by combining activation/lesion network mapping analyses with a transdiagnostic brain imaging meta-analysis. Our findings indicate that there were transdiagnostic alterations in the thalamus and ventral striatum during the decision or outcome stage of decision-making. The identified regions represent key nodes in a large-scale network, which is composed of multiple heterogeneous brain regions and plays a causal role in motivational functioning. The findings suggest that disturbances in the network associated with emotion- and reward-related processing play a key role in dysfunctions of decision-making observed in various psychiatric conditions. This study provides the first meta-analytic evidence of common neural alterations linked to deficits in economic decision-making.

AIJ Journal 2024 Journal Article

Functional Relation Field: A Model-Agnostic Framework for Multivariate Time Series Forecasting

Ting Li
Bing Yu
Jianguo Li
Zhanxing Zhu

In multivariate time series forecasting, the most popular strategy for modeling the relationship between multiple time series is the construction of graph, where each time series is represented as a node and related nodes are connected by edges. However, the relationship between multiple time series is typically complicated, e. g. the sum of outflows from upstream nodes may be equal to the inflows of downstream nodes. Such relations widely exist in many real-world scenarios for multivariate time series forecasting, yet are far from well studied. In these cases, graph might be insufficient for modeling the complex dependency between nodes. To this end, we explore a new framework to model the inter-node relationship in a more precise way based our proposed inductive bias, Functional Relation Field, where a group of functions parameterized by neural networks are learned to characterize the dependency between multiple time series. Essentially, these learned functions then form a “field”, i. e. a particular set of constraints, to regularize the training loss of the backbone prediction network and enforce the inference process to satisfy these constraints. Since our framework introduces the relationship bias in a data-driven manner, it is flexible and model-agnostic such that it can be applied to any existing multivariate time series prediction networks for boosting performance. The experiment is conducted on one toy dataset to show our approach can well recover the true constraint relationship between nodes. And various real-world datasets are also considered with different backbone prediction networks. Results show that the prediction error can be reduced remarkably with the aid of the proposed framework.

YNIMG Journal 2024 Journal Article

Large-scale meta-analyses and network analyses of neural substrates underlying human escalated aggression

Li Wang
Ting Li
Ruolei Gu
Chunliang Feng

Escalated aggression represents a frequent and severe form of violence, sometimes manifesting as antisocial behavior. Driven by the pressures of modern life, escalated aggression is of particular concern due to its rising prevalence and its destructive impact on both individual well-being and socioeconomic stability. However, a consistent neural circuitry underpinning it remains to be definitively identified. Here, we addressed this issue by comparing brain alterations between individuals with escalated aggression and those without such behavioral manifestations. We first conducted a meta-analysis to synthesize previous neuroimaging studies on functional and structural alterations of escalated aggression (325 experiments, 2997 foci, 16,529 subjects). Following-up network and functional decoding analyses were conducted to provide quantitative characterizations of the identified brain regions. Our results revealed that brain regions constantly involved in escalated aggression were localized in the subcortical network (amygdala and lateral orbitofrontal cortex) associated with emotion processing, the default mode network (dorsal medial prefrontal cortex and middle temporal gyrus) associated with mentalizing, and the salience network (anterior cingulate cortex and anterior insula) associated with cognitive control. These findings were further supported by additional meta-analyses on emotion processing, mentalizing, and cognitive control, all of which showed conjunction with the brain regions identified in the escalated aggression. Together, these findings advance the understanding of the risk biomarkers of escalated aggressive populations and refine theoretical models of human aggression.

EAAI Journal 2024 Journal Article

Solving distributed assembly blocking flowshop with order acceptance by knowledge-driven multiobjective algorithm

Ting Li
Jun-qing Li
Xiao-long Chen
Jia-ke Li

In the era of Industry 4. 0, industrial artificial intelligence technologies make production planning and scheduling systems more flexible. A new distributed assembly blocking flowshop problem with order acceptance and scheduling decisions (DABFSP_OAS) was investigated in this paper. Specifically, three objectives—the makespan, total energy consumption (TEC), and total profit (TP)—were addressed simultaneously. To address this problem, we established a knowledge-driven non-dominated sorting genetic algorithm-II (KDNSGAII). First, three initialization schemes based on the problem-specific property were introduced to generate diverse initial population. Then, to accelerate the convergence process, we developed multiple Pareto-based crossover and mutation operators. In addition, two novel destructive reinsertion strategies based on product and job sequence length were implemented to enhance the development ability of the algorithm. Finally, the designed strategies were evaluated. Comparisons and discussions showed that the KDNSGAII outperformed the other state-of-art multi-objective algorithms in solving DABFSP_OAS.

NeurIPS Conference 2023 Conference Paper

Neural Lad: A Neural Latent Dynamics Framework for Times Series Modeling

Ting Li
Jianguo Li
Zhanxing Zhu

Neural ordinary differential equation (Neural ODE) is an elegant yet powerful framework to learn the temporal dynamics for time series modeling. However, we observe that existing Neural ODE forecasting models suffer from two disadvantages: i) controlling the latent states only through the linear transformation over the local change of the observed signals may be inadequate; ii) lacking the ability to capture the inherent periodical property in time series forecasting tasks; To overcome the two issues, we introduce a new neural ODE framework called \textbf{Neural Lad}, a \textbf{Neural} \textbf{La}tent \textbf{d}ynamics model in which the latent representations evolve with an ODE enhanced by the change of observed signal and seasonality-trend characterization. We incorporate the local change of input signal into the latent dynamics in an attention-based manner and design a residual architecture over basis expansion to depict the periodicity in the underlying dynamics. To accommodate the multivariate time series forecasting, we extend the Neural Lad through learning an adaptive relationship between multiple time series. Experiments demonstrate that our model can achieve better or comparable performance against existing neural ODE families and transformer variants in various datasets. Remarkably, the empirical superiority of Neural Lad is consistent across short and long-horizon forecasting for both univariate, multivariate and even irregular sampled time series.

NeurIPS Conference 2023 Conference Paper

Optimal Treatment Allocation for Efficient Policy Evaluation in Sequential Decision Making

Ting Li
Chengchun Shi
Jianing Wang
Fan Zhou
Hongtu Zhu

A/B testing is critical for modern technological companies to evaluate the effectiveness of newly developed products against standard baselines. This paper studies optimal designs that aim to maximize the amount of information obtained from online experiments to estimate treatment effects accurately. We propose three optimal allocation strategies in a dynamic setting where treatments are sequentially assigned over time. These strategies are designed to minimize the variance of the treatment effect estimator when data follow a non Markov decision process or a (time-varying) Markov decision process. We further develop estimation procedures based on existing off-policy evaluation (OPE) methods and conduct extensive experiments in various environments to demonstrate the effectiveness of the proposed methodologies. In theory, we prove the optimality of the proposed treatment allocation design and establish upper bounds for the mean squared errors of the resulting treatment effect estimators.

EAAI Journal 2023 Journal Article

Robust multi-view subspace enhanced representation based on collaborative constraints and HSIC induction

Guoqing Liu
Hongwei Ge
Ting Li
Shuzhi Su
Shuangxi Wang

The design of effective multi-view subspace clustering (MSC) algorithms has recently garnered significant research attention. Herein, to effectively improve the recognition performance and anti-noise interference ability of an MSC model, we propose a novel MSC algorithm, termed as robust multi-view subspace enhancement representation, based on collaborative constraints and a Hilbert–Schmidt independence criterion (HSIC) induction method. To mine the complementary information between different views, we apply the HSIC as a diversity regularization term. Specifically, to enhance the diagonal block structure of a subspace representation, a new sparse constraint is introduced on the product of itself and the transpose of the subspace representation matrix in a multi-view subspace learning model. Furthermore, hypergraph regularization and a low-rank idea are considered to capture the local geometric structure and clean data. In addition, to optimize our model, we adopt an augmented Lagrangian multiplier method and discuss the convergence of the model. Extensive experiments on six challenging datasets reveal that the proposed method achieves a highly competent objective performance with and without noisy views, as compared with several state-of-the-art multi-view clustering methods.

IJCAI Conference 2022 Conference Paper

Regularized Graph Structure Learning with Semantic Knowledge for Multi-variates Time-Series Forecasting

Hongyuan Yu
Ting Li
Weichen Yu
Jianguo Li
Yan Huang
Liang Wang
Alex Liu

Multivariate time-series forecasting is a critical task for many applications, and graph time-series network is widely studied due to its capability to capture the spatial-temporal correlation simultaneously. However, most existing works focus more on learning with the explicit prior graph structure, while ignoring potential information from the implicit graph structure, yielding incomplete structure modeling. Some recent works attempts to learn the intrinsic or implicit graph structure directly, while lacking a way to combine explicit prior structure with implicit structure together. In this paper, we propose Regularized Graph Structure Learning (RGSL) model to incorporate both explicit prior structure and implicit structure together, and learn the forecasting deep networks along with the graph structure. RGSL consists of two innovative modules. First, we derive an implicit dense similarity matrix through node embedding, and learn the sparse graph structure using the Regularized Graph Generation (RGG) based on the Gumbel Softmax trick. Second, we propose a Laplacian Matrix Mixed-up Module (LM3) to fuse the explicit graph and implicit graph together. We conduct experiments on three real-word datasets. Results show that the proposed RGSL model outperforms existing graph forecasting algorithms with a notable margin, while learning meaningful graph structure simultaneously. Our code and models are made publicly available at https: //github. com/alipay/RGSL. git.

PDF Details DOI

AAAI Conference 2019 Conference Paper

Joint Representation Learning for Multi-Modal Transportation Recommendation

Hao Liu
Ting Li
Renjun Hu
Yanjie Fu
Jingjing Gu
Hui Xiong

Multi-modal transportation recommendation has a goal of recommending a travel plan which considers various transportation modes, such as walking, cycling, automobile, and public transit, and how to connect among these modes. The successful development of multi-modal transportation recommendation systems can help to satisfy the diversified needs of travelers and improve the efficiency of transport networks. However, existing transport recommender systems mainly focus on unimodal transport planning. To this end, in this paper, we propose a joint representation learning framework for multi-modal transportation recommendation based on a carefully-constructed multi-modal transportation graph. Specifically, we first extract a multi-modal transportation graph from large-scale map query data to describe the concurrency of users, Origin-Destination (OD) pairs, and transport modes. Then, we provide effective solutions for the optimization problem and develop an anchor embedding for transport modes to initialize the embeddings of transport modes. Moreover, we infer user relevance and OD pair relevance, and incorporate them to regularize the representation learning. Finally, we exploit the learned representations for online multimodal transportation recommendations. Indeed, our method has been deployed into one of the largest navigation Apps to serve hundreds of millions of users, and extensive experimental results with real-world map query data demonstrate the enhanced performance of the proposed method for multimodal transportation recommendations.

YNICL Journal 2019 Journal Article

White matter impairment in type 2 diabetes mellitus with and without microvascular disease

Yaoyao Zhuo
Fang Fang
Lunbo Lu
Ting Li
Jingge Lian
Yun Xiong
Dexing Kong
Kangan Li

BACKGROUND AND OBJECTIVE: Type 2 diabetes mellitus (T2DM) is a serious public health problem, and the phenomenon of T2DM occurring in younger people has directed more attention to functional changes in the brain. In this study, the microstructural integrity of white matter (WM) was evaluated in three groups of middle-aged subjects: healthy controls (HCs) and T2DM patients with and without peripheral microvascular complications (T2DM-C and T2DM-NC patients, respectively). METHODS: Diffusion tensor imaging (DTI) and related clinical examinations were performed in 66 subjects, including 20 T2DM-C patients, 20 T2DM-NC patients, 26 age- and sex-matched HCs. Magnetic resonance imaging (MRI) at 3 T was used to perform DTI; then, FSL and tract-based spatial statistics (TBSS) software were used to assess differences in the fractional anisotropy (FA) and mean diffusivity (MD) among the groups. The use of the FA and MD as parameters was evaluated by receiver operating characteristic (ROC) curve analysis. RESULTS: There were no significant differences in sex or age among the groups, and the clinical data of the groups met the experimental requirements. There was no significant difference in the FA values between the HCs and T2DM-NC groups. Compared with the HCs, the T2DM-C patients showed decreased FA values and increased MD values in the corpus callosum, bilateral anterior limb of the internal capsule, right retrolenticular part of the internal capsule, bilateral posterior thalamic radiation, right superior longitudinal fasciculus, bilateral superior corona radiata and left middle frontal gyrus (P < .01). Compared with the T2DM-NC patients, the T2DM-C patients showed decreased FA values and increased MD values in the corpus callosum, bilateral fornix, right retrolenticular part of the internal capsule, middle cerebral peduncle, right superior longitudinal fasciculus, right posterior thalamic radiation, and left middle frontal gyrus (P < .01). CONCLUSIONS: This study indicates that WM impairment is present in T2DM patients and may be related to microvascular complications. More importantly, this study also shows that such impairment may be diagnosed using the DTI mode of functional MRI before it can be diagnosed clinically.

EAAI Journal 2014 Journal Article

Multi-objective ecological reservoir operation based on water quality response models and improved genetic algorithm: A case study in Three Gorges Reservoir, China

Ming Hu
Guo H. Huang
Wei Sun
Yongping Li
Xiaowen Ding
Chunjiang An
Xiaofei Zhang
Ting Li

This study proposes a self-adaptive GA-aided multi-objective ecological reservoir operation model (SMEROM) and applies it to water quality management in the Xiangxi River near to the Three Gorges Reservoir, China. The SMEROM integrates statistical water quality models, multi-objective reservoir operations, and a self-adaptive GA within a general framework. Among them, the statistical water quality models of the Xiangxi River are formulated to deal with the relationships between reservoir operation and water quality, which are embedded in constraints of the SMEROM. The multiple objective functions, including maximizing hydropower generation, minimizing loss of flood control, minimizing rate of flood risk, maximizing the average remaining capacity of flood control and maximizing the benefit of shipping, are considered simultaneously to obtain comprehensive benefit among the environment, society and economy. The weighting method is employed to convert the multiple objectives to a single objective. To solve the complex SMEROM, an improved self-adaptive GA is employed through incorporating simulated binary crossover and self-adaptive mutation. To demonstrate the advantage of the developed SMEROM model, the solutions through ecological reservoir operation are compared with those through the traditional reservoir operation and the practical operation in 2011, in terms of water quality, reservoir operation and objective function values. The results show that most of benefit in the ecological operation is better than that in the traditional or practical operations except for the hydropower benefit and loss benefit of flood control. This is because flood control and environmental protection are reasonably considered in the ecological operation.