Author name cluster

Na 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.

31 papers

2 author rows

AAAI Conference 2026 Conference Paper

Adaptive Diffusion-based Augmentation for Recommendation

Na Li
Fanghui Sun
Yan Zou
Yangfu Zhu
Xiatian Zhu
Ying Ma

Recommendation systems often rely on implicit feedback, where only positive user-item interactions can be observed. Negative sampling is therefore crucial to provide proper negative training signals. However, existing methods tend to mislabel potentially positive but unobserved items as negatives and lack precise control over negative sample selection. We aim to address these by generating controllable negative samples, rather than sampling from the existing item pool. In this context, we propose Adaptive Diffusion-based Augmentation for Recommendation (ADAR), a novel and model-agnostic module that leverages diffusion to synthesize informative negatives. Inspired by the progressive corruption process in diffusion, ADAR simulates a continuous transition from positive to negative, allowing for fine-grained control over sample hardness. To mine suitable negative samples, we theoretically identify the transition point at which a positive sample turns negative and derive a score-aware function to adaptively determine the optimal sampling timestep. By identifying this transition point, ADAR generates challenging negative samples that effectively refine the model's decision boundary. Experiments confirm that ADAR is broadly compatible and boosts the performance of existing recommendation models substantially, including collaborative filtering and sequential recommendation, without architectural modifications.

PDF Details DOI

EAAI Journal 2026 Journal Article

Adversarial attack-defense framework for enhancing the robustness of power insulator detection in cloud-edge deployment

Qinglong Wang
Changyu Yang
Jianhua Du
Na Li
Jian Wang
Huilong Han
Yunjian Hu
Wen Peng

Power insulators are essential to the stability of high-voltage transmission lines, and unmanned aerial vehicle-based inspection systems supported by cloud-edge computing have markedly improved monitoring efficiency. However, deep neural networks remain vulnerable to adversarial attacks. Most studies focus on image classification, with limited attention given to oriented bounding box (OBB) detection under edge constraints critical for power-line monitoring. To address this, we propose an adversarial attack-defense framework tailored for cloud-edge insulator inspection. We develop an enhanced Projected Gradient Descent Plus (PGD+) algorithm that integrates dynamic step-size scheduling, multi-point initialization, momentum accumulation, and stochastic gradient perturbation to generate effective yet visually imperceptible adversarial examples. Ablation analysis quantifies the contribution of each mechanism and demonstrates reliable transferability across different detectors. We construct a specialized glass insulator dataset with OBB annotations and design a dual-stage defense combining an attention-enhanced denoising autoencoder and an embedded denoising module integrated into the detector. Experiments show that PGD + achieves a 90. 6 % attack success rate, reducing mean average precision at an intersection-over-union threshold of 0. 5 (mAP50) by over 90 %, while preserving high visual fidelity with peak signal-to-noise ratios above 38 decibels (dB) and structural-similarity index values exceeding 0. 94. The joint defense recovers mAP50 to 93. 6 % under PGD + attacks. Edge-deployment evaluation on an embedded platform demonstrates that the full pipeline sustains 23–35 frames per second, demonstrating its practical feasibility for real-time cloud-edge inspection. The proposed framework delivers algorithmic strategies, a benchmark OBB dataset, and a deployable defense architecture that enhances the robustness of intelligent power-grid inspection in adversarial environments.

Details DOI

AAAI Conference 2026 Conference Paper

Enhancing Stability and Fidelity for Zero-Shot TTS with a Multi-Level Evaluator

Hualei Wang
Na Li
Chuke Wang
Shu Wu
Zhifeng Li
Dong Yu

Recent advances in zero-shot text-to-speech (TTS), driven by language models, diffusion models and masked generation, have achieved impressive naturalness in speech synthesis. Nevertheless, stability and fidelity remain key challenges, manifesting as mispronunciations, audible noise, and quality degradation. To address these issues, we introduce Vox-Evaluator, a multi-level evaluator designed to guide the correction of erroneous speech segments and preference alignment for TTS systems. It is capable of identifying the temporal boundaries of erroneous segments and providing a holistic quality assessment of the generated speech. Specifically, to refine erroneous segments and enhance the robustness of the zero-shot TTS model, we propose to automatically identify acoustic errors with the evaluator, mask the erroneous segments, and finally regenerate speech conditioning on the correct portions. In addition, the fine-gained information obtained from Vox-Evaluator can guide the preference alignment for TTS model, thereby reducing the bad cases in speech synthesize. Due to the lack of suitable training datasets for the Vox-Evaluator, we also constructed a synthesized text-speech dataset annotated with fine-grained pronunciation errors or audio quality issues. The experimental results demonstrate the effectiveness of the proposed Vox-Evaluator in enhancing the stability and fidelity of TTS systems through the speech correction mechanism and preference optimization.

PDF Details DOI

AAAI Conference 2026 Conference Paper

LILAD: Learning In-context Lyapunov-stable Adaptive Dynamics Models

Amit Jena
Na Li
Le Xie

System identification in control theory aims to approximate dynamical systems from trajectory data. While neural networks have demonstrated strong predictive accuracy, they often fail to preserve critical physical properties such as stability and typically assume stationary dynamics, limiting their applicability under distribution shifts. Existing approaches generally address either stability or adaptability in isolation, lacking a unified framework that ensures both. We propose LILAD (Learning In-Context Lyapunov-stable Adaptive Dynamics), a novel framework for system identification that jointly guarantees adaptability and stability. LILAD simultaneously learns a dynamics model and a Lyapunov function through in-context learning (ICL), explicitly accounting for parametric uncertainty. Trained across a diverse set of tasks, LILAD produces a stability-aware, adaptive dynamics model alongside an adaptive Lyapunov certificate. At test time, both components adapt to a new system instance using a short trajectory prompt, which enables fast generalization. To rigorously ensure stability, LILAD also computes a state-dependent attenuator that enforces a sufficient decrease condition on the Lyapunov function for any state in the new system instance. This mechanism extends stability guarantees even under out-of-distribution and out-of-task scenarios. We evaluate LILAD on benchmark autonomous systems and demonstrate that it outperforms adaptive, robust, and non-adaptive baselines in predictive accuracy.

PDF Details DOI

JBHI Journal 2026 Journal Article

MoACNN-XGNet: Interpretable Multi-Omics Convolutional Network for Breast Cancer Subtyping and Prognostic Genes Identification

Qian Li
Lei Liu
Qing Zhang
Xiaobin Zhang
Na Li
Yaoyao Zhao
Jiayi Teng
Fuzhong Xue

Breast cancer, a highly heterogeneous disease at both the phenotypic and molecular levels, presents significant challenges for prognosis and treatment. Accurate subtyping of breast cancer is critical due to its complex biological characteristics, which directly influence disease progression and therapeutic outcomes. In this study, we integrate multi-omics data, including copy number variation, RNA sequencing, and DNA methylation, to generate two-dimensional representations of each sample using Uniform Manifold Approximation and Projection. This transformation enhances data interpretability and supports subsequent learning tasks. Traditional convolutional neural networks have demonstrated potential in medical image analysis but often struggle with high-dimensional omics data. To address this limitation, we propose MoACNN-XGNet, an attention-based convolutional neural network framework that prioritizes key features within image-transformed multi-omics data. Our method significantly improves the precision of subtype classification and effectively overcomes the challenges posed by the high dimensionality and structural complexity of multi-omics data. Furthermore, we employ the Guided Grad-CAM method to enhance model interpretability, enabling the identification of subtype-specific explainable genes. Subsequent enrichment and survival analyses of these genes reveal critical biological pathways and potential therapeutic targets. This study offers a novel approach to refining breast cancer subtyping and highlights the potential for personalized treatment strategies, ultimately aiming to improve patient survival outcomes.

Details DOI

JBHI Journal 2026 Journal Article

NoTAC: A Noise-Tolerance Automatic Cleaning Framework for Bone Marrow Karyotyping Data

Rihan Huang
Siyuan Chen
Yafei Li
Chunling Zhang
Yilan Zhang
Changchun Yang
Na Li
Jingdong Hu

Deep neural networks have advanced chromosome classification, a critical procedure in karyotyping for disease diagnosis. However, training an effective DNN requires clean and reliable data, whereas real-world clinical chromosome data often contain label errors and outliers, which degrade DNN performance and limit their clinical applicability. In this work, we propose a Noise-Tolerance Automatic Cleaning framework, named NoTAC, to address potential labeling errors and outliers to enhance the performance of chromosome classification. The framework consists of two branches: KaryoCleanse for label noise detection and KaryoDrift for outlier identification. First, it identifies potential label errors by leveraging the DNN’s self-confidence, estimating the latent label distribution, and ranking probabilities to prune mislabeled data. Second, it scores out-of-distribution samples based on the average K-nearest neighbor distances, enabling the identification and removal of outlier data. We conducted comprehensive comparative experiments against state-of-the-art noise-handling methods on a real-world R-band bone marrow chromosome dataset. Our results demonstrate that NoTAC achieves superior performance with an accuracy of 93. 99%, which represents a 6. 25% relative improvement over the baseline and outperforms the best competing method by 0. 92%. Furthermore, our qualitative analysis of NoTAC revealed reliable data issues in a real-world R-band bone marrow chromosome dataset, offering insights into how these issues impair DNN prediction capabilities. These findings demonstrate NoTAC’s potential to enhance both the performance and reliability of DNNs in practical medical datasets. The proposed method has also been applied to assist clinical karyotype diagnosis.

Details DOI

EAAI Journal 2026 Journal Article

Spatio-temporal grey Bernoulli model for green development of marine economy forecasting

Na Li
Xuemei Li
Song Ding

The sustainable development of the marine economy is inseparable from green development. However, the spatial correlations and dynamic evolution of green development present significant forecasting challenges. To address this, this paper first constructs an evaluation index system for the green development of marine economy based on the Driver-Pressure-State-Impact-Response (DPSIR) framework. Furthermore, the grey Bernoulli model is improved in both spatial and temporal dimensions for forecasting purposes. Interaction terms between spatial distance matrices and variables are introduced to capture spatial correlations, while a time-varying component is incorporated to reflect dynamic evolution. These enhancements enable the model to more effectively characterize the spatial, temporal, and nonlinear features of the green development of marine economy. Additionally, the model’s hyperparameters and weighting coefficients are optimized using the whale optimization algorithm. For validation, an empirical study is conducted across China’s 11 coastal provinces and municipalities. Systematic analyses show that the proposed model has high predictive accuracy. Robustness tests and sensitivity analysis further confirm that the model demonstrates excellent stability, reliability, and generalization capability.

Details DOI

NeurIPS Conference 2025 Conference Paper

Constrained Optimization From a Control Perspective via Feedback Linearization

Runyu Zhang
Arvind Raghunathan
Jeff Shamma
Na Li

Tools from control and dynamical systems have proven valuable for analyzing and developing optimization methods. In this paper, we establish rigorous theoretical foundations for using feedback linearization—a well-established nonlinear control technique—to solve constrained optimization problems. For equality-constrained optimization, we establish global convergence rates to first-order Karush-Kuhn-Tucker (KKT) points and uncover the close connection between the FL method and the Sequential Quadratic Programming (SQP) algorithm. Building on this relationship, we extend the FL approach to handle inequality-constrained problems. Furthermore, we introduce a momentum-accelerated feedback linearization algorithm and provide a rigorous convergence guarantee.

PDF Details

ECAI Conference 2025 Conference Paper

Multivariate Time Series Forecasting with Hybrid Euclidean-SPD Manifold Graph Neural Networks

Yong Fang 0001
Na Li
Hangguan Shan
Eryun Liu
Xinyu Li 0001
Wei Ni
Erping Li 0001

Multivariate Time Series (MTS) forecasting plays a vital role in various real-world applications, such as traffic management and predictive maintenance. Existing approaches typically model MTS data in either Euclidean or Riemannian space, limiting their ability to capture the diverse geometric structures and complex Spatio-Temporal (ST) dependencies inherent in real-world data. To overcome this limitation, we propose the Hybird Symmetric Positive-Definite Manifold Graph Neural Network (HSMGNN), a novel graph neural network-based model that captures data geometry within a hybrid Euclidean–Riemannian framework. To the best of our knowledge, this is the first work to leverage hybrid geometric representations for MTS forecasting, enabling expressive and comprehensive modeling of geometric properties. Specifically, we introduce a Submanifold-Cross-Segment (SCS) embedding to project input MTS into both Euclidean and Riemannian spaces, thereby capturing ST variations across distinct geometric domains. To alleviate the high computational cost of Riemannian distance, we further design an Adaptive-Distance-Bank (ADB) layer with a trainable memory mechanism. Finally, a Fusion Graph Convolutional Network (FGCN) is devised to integrate features from the dual spaces via a learnable fusion operator for accurate prediction. Experiments on three benchmark datasets demonstrate that HSMGNN achieves up to 13. 8% improvement over state-of-the-art baselines in forecasting accuracy.

Details

NeurIPS Conference 2025 Conference Paper

RODS: Robust Optimization Inspired Diffusion Sampling for Detecting and Reducing Hallucination in Generative Models

Yiqi Tian
Pengfei Jin
Mingze Yuan
Na Li
Bo Zeng
Quanzheng Li

Diffusion models have achieved state-of-the-art performance in generative modeling, yet their sampling procedures remain vulnerable to hallucinations—often stemming from inaccuracies in score approximation. In this work, we reinterpret diffusion sampling through the lens of optimization and introduce RODS (Robust Optimization–inspired Diffusion Sampler), a novel method that detects and corrects high-risk sampling steps using geometric cues from the loss landscape. RODS enforces smoother sampling trajectories and \textit{adaptively} adjusts perturbations, reducing hallucinations without retraining and at minimal additional inference cost. Experiments on AFHQv2, FFHQ, and 11k-hands demonstrate that RODS maintains comparable image quality and preserves generation diversity. More importantly, it improves both sampling fidelity and robustness, detecting over 70\% of hallucinated samples and correcting more than 25\%, all while avoiding the introduction of new artifacts. We release our code at https: //github. com/Yiqi-Verna-Tian/RODS.

PDF Details

NeurIPS Conference 2025 Conference Paper

Sample-Efficient Tabular Self-Play for Offline Robust Reinforcement Learning

Na Li
Zewu Zheng
Wei Ni
Hangguan Shan
Wenjie Zhang
Xinyu Li

Multi-agent reinforcement learning (MARL), as a thriving field, explores how multiple agents independently make decisions in a shared dynamic environment. Due to environmental uncertainties, policies in MARL must remain robust to tackle the sim-to-real gap. We focus on robust two-player zero-sum Markov games (TZMGs) in offline settings, specifically on tabular robust TZMGs (RTZMGs). We propose a model-based algorithm ( RTZ-VI-LCB ) for offline RTZMGs, which is optimistic robust value iteration combined with a data-driven Bernstein-style penalty term for robust value estimation. By accounting for distribution shifts in the historical dataset, the proposed algorithm establishes near-optimal sample complexity guarantees under partial coverage and environmental uncertainty. An information-theoretic lower bound is developed to confirm the tightness of our algorithm's sample complexity, which is optimal regarding both state and action spaces. To the best of our knowledge, RTZ-VI-LCB is the first to attain this optimality, sets a new benchmark for offline RTZMGs, and is validated experimentally.

PDF Details

EAAI Journal 2024 Journal Article

Enhanced recognition of insulator defects on power transmission lines via proposal-based detection model with integrated improvement methods

Qinglong Wang
Yongjian Li
Shihao Cui
Na Li
Xinchun Zhang
Wenqiang Jiang
Wen Peng
Jie Sun

Deep learning-driven transmission line inspection is a critical area for smart power grid development. Despite advances in deep learning for insulator defect detection, challenges remain in model robustness and adaptability for the varying real-world adaptability, especially for insignificant defects in complex backgrounds. This study presents a comprehensive improvement strategy for detecting insulators and cross-scale broken defects on transmission lines, employing a proposal-based detection model. The model introduces a holistic pipeline of improved methods, including backbone modification, anchor box scale recalibration, and improvements in Region of Interest (RoI) downsampling alignment and Intersection over Union (IoU) loss function. Various backbone networks, including convolutional network (ConvNet) and Vision Transformer (ViT) structures, are constructed and integrated with attention modules, specifically designed to amplify the perception of insulators and defective regions. The geometric scale of anchor boxes is reconstructed using a developed clustering algorithm, considering the elongated characteristics of insulator strings to improve the adaptability of anchor boxes. Bilinear interpolation is utilized to mitigate spatial misalignment issues during the downsampling process of Region Proposal Network (RPN)-based proposals. The experimental results indicate that the improved models with the Swin Transformer (Swin-T) backbone framework achieve the mean Average Precision (mAP)@0. 5 of 88. 42% and mAP@0. 7 of 60. 52%, with a defect recall rate of 81. 94%. Additionally, the improved IoU loss function contributes to the performance of the model at higher IoU thresholds. The results of this study contribute to the further development of defect detection frameworks for power vision applications.

Details DOI

NeurIPS Conference 2024 Conference Paper

Enhancing Preference-based Linear Bandits via Human Response Time

Shen Li
Yuyang Zhang
Zhaolin Ren
Claire Liang
Na Li
Julie A. Shah

Interactive preference learning systems infer human preferences by presenting queries as pairs of options and collecting binary choices. Although binary choices are simple and widely used, they provide limited information about preference strength. To address this, we leverage human response times, which are inversely related to preference strength, as an additional signal. We propose a computationally efficient method that combines choices and response times to estimate human utility functions, grounded in the EZ diffusion model from psychology. Theoretical and empirical analyses show that for queries with strong preferences, response times complement choices by providing extra information about preference strength, leading to significantly improved utility estimation. We incorporate this estimator into preference-based linear bandits for fixed-budget best-arm identification. Simulations on three real-world datasets demonstrate that using response times significantly accelerates preference learning compared to choice-only approaches. Additional materials, such as code, slides, and talk video, are available at https: //shenlirobot. github. io/pages/NeurIPS24. html.

PDF Details DOI

ICML Conference 2024 Conference Paper

Learning Low-dimensional Latent Dynamics from High-dimensional Observations: Non-asymptotics and Lower Bounds

Yuyang Zhang
Shahriar Talebi
Na Li

In this paper, we focus on learning a linear time-invariant (LTI) model with low-dimensional latent variables but high-dimensional observations. We provide an algorithm that recovers the high-dimensional features, i. e. column space of the observer, embeds the data into low dimensions and learns the low-dimensional model parameters. Our algorithm enjoys a sample complexity guarantee of order $\tilde{\mathcal{O}}(n/\epsilon^2)$, where $n$ is the observation dimension. We further establish a fundamental lower bound indicating this complexity bound is optimal up to logarithmic factors and dimension-independent constants. We show that this inevitable linear factor of $n$ is due to the learning error of the observer’s column space in the presence of high-dimensional noises. Extending our results, we consider a meta-learning problem inspired by various real-world applications, where the observer column space can be collectively learned from datasets of multiple LTI systems. An end-to-end algorithm is then proposed, facilitating learning LTI systems from a meta-dataset which breaks the sample complexity lower bound in certain scenarios.

Details

AAMAS Conference 2024 Conference Paper

MATLight: Traffic Signal Coordinated Control Algorithm based on Heterogeneous-Agent Mirror Learning with Transformer

Haipeng Zhang
Zhiwen Wang
Na Li

In order to better handle the issue of real-time multi-intersection traffic signal coordinated control, we expect that multi-agent decisionmaking can benefit from the advantages of large sequence models. In this paper, we propose a method for multi-intersection traffic signal coordinated control based on heterogeneous-agent mirror learning and Transformer to sequential multi-agent cooperative decision. First, multi-intersection traffic signal control is modeled as a sequential problem based on the heterogeneous-agent mirror learning framework. We convert real-time multi-intersection traffic signal control into a multi-agent sequential decision-making process. It completely capitalizes on the surprising connection between the multi-agent reinforcement learning decision process and sequential model prediction. And it provides strong theoretical guarantees. Then the Transformer sequence model is used to cleverly implement the sequential update scheme to learn the optimal traffic signal coordination control strategy online with a new training paradigm. The proposed method has theoretical policy promotion and convergence, alleviates the credit assignment problem in the process of multi-intersection traffic signal coordinated control, reduces the complexity of the joint policy optimization, and improves the learning efficiency of few-shot samples. We used LibSignal, a unified framework for traffic signal control tasks, for comparison testing. According to experimental results, our method can significantly improve the efficiency and performance of few-shot online learning, outperform the baseline methods in both network-level and arterial coordination, and simplify the complexity of algorithm implementation.

PDF

AIIM Journal 2024 Journal Article

Non-invasive fractional flow reserve derived from reduced-order coronary model and machine learning prediction of stenosis flow resistance

Yili Feng
Ruisen Fu
Hao Sun
Xue Wang
Yang Yang
Chuanqi Wen
Yaodong Hao
Yutong Sun

Background and objective Recently, computational fluid dynamics enables the non-invasive calculation of fractional flow reserve (FFR) based on 3D coronary model, but it is time-consuming. Currently, machine learning technique has emerged as an efficient and reliable approach for prediction, which allows saving a lot of analysis time. This study aimed at developing a simplified FFR prediction model for rapid and accurate assessment of functional significance of stenosis. Methods A reduced-order lumped parameter model (LPM) of coronary system and cardiovascular system was constructed for rapidly simulating coronary flow, in which a machine learning model was embedded for accurately predicting stenosis flow resistance at a given flow from anatomical features of stenosis. Importantly, the LPM was personalized in both structures and parameters according to coronary geometries from computed tomography angiography and physiological measurements such as blood pressure and cardiac output for personalized simulations of coronary pressure and flow. Coronary lesions with invasive FFR ≤ 0. 80 were defined as hemodynamically significant. Results A total of 91 patients (93 lesions) who underwent invasive FFR were involved in FFR derived from machine learning (FFRML) calculation. Of the 93 lesions, 27 lesions (29. 0%) showed lesion-specific ischemia. The average time of FFRML simulation was about 10 min. On a per-vessel basis, the FFRML and FFR were significantly correlated (r = 0. 86, p < 0. 001). The diagnostic accuracy, sensitivity, specificity, positive predictive value and negative predictive value were 91. 4%, 92. 6%, 90. 9%, 80. 6% and 96. 8%, respectively. The area under the receiver-operating characteristic curve of FFRML was 0. 984. Conclusion In this selected cohort of patients, the FFRML improves the computational efficiency and ensures the accuracy. The favorable performance of FFRML approach greatly facilitates its potential application in detecting hemodynamically significant coronary stenosis in future routine clinical practice.

Details DOI

ICLR Conference 2024 Conference Paper

Provable Memory Efficient Self-Play Algorithm for Model-free Reinforcement Learning

Na Li
Yuchen Jiao
Hangguan Shan
Shefeng Yan

The thriving field of multi-agent reinforcement learning (MARL) studies how a group of interacting agents make decisions autonomously in a shared dynamic environment. Existing theoretical studies in this area suffer from at least two of the following obstacles: memory inefficiency, the heavy dependence of sample complexity on the long horizon and the large state space, the high computational complexity, non-Markov policy, non-Nash policy, and high burn-in cost. In this work, we take a step towards settling this problem by designing a model-free self-play algorithm \emph{Memory-Efficient Nash Q-Learning (ME-Nash-QL)} for two-player zero-sum Markov games, which is a specific setting of MARL. We prove that ME-Nash-QL can output an $\varepsilon$-approximate Nash policy with remarkable space complexity $O(SABH)$, sample complexity $\widetilde{O}(H^4SAB/\varepsilon^2)$, and computational complexity $O(T\mathrm{poly}(AB))$, where $S$ is the number of states, $\{A, B\}$ is the number of actions for the two players, $H$ is the horizon length, and $T$ is the number of samples. Notably, our approach outperforms in terms of space complexity compared to existing algorithms for tabular cases. It achieves the lowest computational complexity while preserving Markov policies, setting a new standard. Furthermore, our algorithm outputs a Nash policy and achieves the best sample complexity compared with the existing guarantee for long horizons, i.e. when $\min \\{ A, B \\} \ll H^2$. Our algorithm also achieves the best burn-in cost $O(SAB\,\mathrm{poly}(H))$, whereas previous algorithms need at least $O(S^3 AB\,\mathrm{poly}(H))$ to attain the same level of sample complexity with ours.

Details

EAAI Journal 2023 Journal Article

Unsupervised fault diagnosis of wind turbine bearing via a deep residual deformable convolution network based on subdomain adaptation under time-varying speeds

Pengfei Liang
Bin Wang
Guoqian Jiang
Na Li
Lijie Zhang

Recent years have seen the rapid development and marvelous achievement of deep learning-based fault diagnosis (FD) methods which assume that training data and testing data have the same distribution. However, in real FD of wind turbine bearing (WTB), the particularity of time-varying speeds makes a huge difference in the distribution of training data and testing data, greatly increasing the difficulty of FD. Accordingly, in this paper, a novel deep residual deformable subdomain adaptation framework is proposed for cross-domain failure diagnosis of WTB under time-varying speeds. In the proposed approach, the traditional residual network is improved by using a deformable convolution module to replace plain counterparts, which can make the feature representation of an object adapt its configuration and enhance the ability of the model to extract transferable features. Moreover, the popular FD model based on domain adversarial neural nets and global maximum mean discrepancy is improved by removing the adversarial training mechanism and employing a local maximum mean discrepancy to align the distributions of the identical fault type in different domains, making the diagnostic model simpler and more efficient. Two experimental cases under time-varying speeds are conducted to analyze the performance of the proposed approach and the results indicate that this method can utilize the knowledge in the source domain to diagnose the fault in the target domain. Compared with the existing methods, the diagnosis accuracy and efficiency are significantly improved, demonstrating its effectiveness and potential applications in fault transfer diagnosis of wind turbine bearing.

Details DOI

NeurIPS Conference 2022 Conference Paper

On the Global Convergence Rates of Decentralized Softmax Gradient Play in Markov Potential Games

Runyu Zhang
Jincheng Mei
Bo Dai
Dale Schuurmans
Na Li

Softmax policy gradient is a popular algorithm for policy optimization in single-agent reinforcement learning, particularly since projection is not needed for each gradient update. However, in multi-agent systems, the lack of central coordination introduces significant additional difficulties in the convergence analysis. Even for a stochastic game with identical interest, there can be multiple Nash Equilibria (NEs), which disables proof techniques that rely on the existence of a unique global optimum. Moreover, the softmax parameterization introduces non-NE policies with zero gradient, making it difficult for gradient-based algorithms in seeking NEs. In this paper, we study the finite time convergence of decentralized softmax gradient play in a special form of game, Markov Potential Games (MPGs), which includes the identical interest game as a special case. We investigate both gradient play and natural gradient play, with and without $\log$-barrier regularization. The established convergence rates for the unregularized cases contain a trajectory dependent constant that can be \emph{arbitrarily large}, whereas the $\log$-barrier regularization overcomes this drawback, with the cost of slightly worse dependence on other factors such as the action set size. An empirical study on an identical interest matrix game confirms the theoretical findings.

PDF Details

NeurIPS Conference 2022 Conference Paper

Policy Optimization for Markov Games: Unified Framework and Faster Convergence

Runyu Zhang
Qinghua Liu
Huan Wang
Caiming Xiong
Na Li
Yu Bai

This paper studies policy optimization algorithms for multi-agent reinforcement learning. We begin by proposing an algorithm framework for two-player zero-sum Markov Games in the full-information setting, where each iteration consists of a policy update step at each state using a certain matrix game algorithm, and a value update step with a certain learning rate. This framework unifies many existing and new policy optimization algorithms. We show that the \emph{state-wise average policy} of this algorithm converges to an approximate Nash equilibrium (NE) of the game, as long as the matrix game algorithms achieve low weighted regret at each state, with respect to weights determined by the speed of the value updates. Next, we show that this framework instantiated with the Optimistic Follow-The-Regularized-Leader (OFTRL) algorithm at each state (and smooth value updates) can find an $\mathcal{\widetilde{O}}(T^{-5/6})$ approximate NE in $T$ iterations, and a similar algorithm with slightly modified value update rule achieves a faster $\mathcal{\widetilde{O}}(T^{-1})$ convergence rate. These improve over the current best $\mathcal{\widetilde{O}}(T^{-1/2})$ rate of symmetric policy optimization type algorithms. We also extend this algorithm to multi-player general-sum Markov Games and show an $\mathcal{\widetilde{O}}(T^{-3/4})$ convergence rate to Coarse Correlated Equilibria (CCE). Finally, we provide a numerical example to verify our theory and investigate the importance of smooth value updates, and find that using ''eager'' value updates instead (equivalent to the independent natural policy gradient algorithm) may significantly slow down the convergence, even on a simple game with $H=2$ layers.

PDF Details

IJCAI Conference 2021 Conference Paper

Modelling General Properties of Nouns by Selectively Averaging Contextualised Embeddings

Na Li
Zied Bouraoui
Jose Camacho-Collados
Luis Espinosa-Anke
Qing Gu
Steven Schockaert

While the success of pre-trained language models has largely eliminated the need for high-quality static word vectors in many NLP applications, static word vectors continue to play an important role in tasks where word meaning needs to be modelled in the absence of linguistic context. In this paper, we explore how the contextualised embeddings predicted by BERT can be used to produce high-quality word vectors for such domains, in particular related to knowledge base completion, where our focus is on capturing the semantic properties of nouns. We find that a simple strategy of averaging the contextualised embeddings of masked word mentions leads to vectors that outperform the static word vectors learned by BERT, as well as those from standard word embedding models, in property induction tasks. We notice in particular that masking target words is critical to achieve this strong performance, as the resulting vectors focus less on idiosyncratic properties and more on general semantic properties. Inspired by this view, we propose a filtering strategy which is aimed at removing the most idiosyncratic mention vectors, allowing us to obtain further performance gains in property induction.

PDF Details DOI

AAAI Conference 2021 Conference Paper

Online Optimal Control with Affine Constraints

Yingying Li
Subhro Das
Na Li

This paper considers online optimal control with affine constraints on the states and actions under linear dynamics with bounded random disturbances. The system dynamics and constraints are assumed to be known and time invariant but the convex stage cost functions change adversarially. To solve this problem, we propose Online Gradient Descent with Buffer Zones (OGD-BZ). Theoretically, we show that OGD- BZ with proper parameters can guarantee the system to satisfy all the constraints despite any admissible disturbances. Further, we investigate the policy regret of OGD-BZ, which compares OGD-BZ’s performance with the performance of the optimal linear policy in hindsight. We show that OGD-BZ can achieve a policy regret upper bound that is square root of the horizon length multiplied by some logarithmic terms of the horizon length under proper algorithm parameters.

PDF Details

YNICL Journal 2020 Journal Article

Age-related atrophy of cortical thickness and genetic effect of ANK3 gene in first episode MDD patients

Yuqi Cheng
Jian Xu
Chenglong Dong
Zonglin Shen
Cong Zhou
Na Li
Yi Lu
Liuyi Ran

Brain ageing is thought to be related to geriatric depression, but the relationship between ageing and depression among middle aged individuals is unknown. The present study aimed to evaluate whether the age-related reduction of brain cortical thickness (CT) can be found in adult first-episode MDD patients, as well as to identify the possible genetic effect of the ANK3 gene polymorphism age-relates CT reduction. This study recruited 153 first-episode MDD patients with a disease duration < 2 years and 276 healthy controls (HC), and the CT of 68 whole brain regions and two ANK3 SNPs (rs1994336 and rs10994359) were analyzed. The results showed that although the CT of both groups was negative correlated with age, the MDD group had significant greater age-related decrease in CT than the HC group (–9. 35 × 10−3 mm/year for MDD vs. –1. 23 × 10−3 mm/year for HC in the left lateral orbitofrontal lobe). The multivariate analysis of covariance (MANCOVA) results yielded significant interactions of diagnosis × age, genotype × age and diagnosis × genotype interaction for rs10994359. In HC, the C allele showed a protective effect on age-related CT reduction. The reduction in CT with age was several times as greater in non-C carriers as in C carriers (–3. 54 × 10−3 vs. –0. 15 × 10−3 mm/year in left supramarginal gyrus) for HC. However, this protective effect disappeared in patients with MDD. We did not find a clear effect of rs1994336 on the age-related CT reduction. The findings indicate that the widespread accelerated brain ageing occurs early in adult-onset depression and this ageing may be a pathological mechanisms of depression rather than an outcome of the disease. The ANK3 rs10994359 polymorphism may partially affect regional cortical ageing in MDD.

Details DOI

IJCAI Conference 2020 Conference Paper

Attention as Relation: Learning Supervised Multi-head Self-Attention for Relation Extraction

Jie Liu
Shaowei Chen
Bingquan Wang
Jiaxin Zhang
Na Li
Tong Xu

Joint entity and relation extraction is critical for many natural language processing (NLP) tasks, which has attracted increasing research interest. However, it is still faced with the challenges of identifying the overlapping relation triplets along with the entire entity boundary and detecting the multi-type relations. In this paper, we propose an attention-based joint model, which mainly contains an entity extraction module and a relation detection module, to address the challenges. The key of our model is devising a supervised multi-head self-attention mechanism as the relation detection module to learn the token-level correlation for each relation type separately. With the attention mechanism, our model can effectively identify overlapping relations and flexibly predict the relation type with its corresponding intensity. To verify the effectiveness of our model, we conduct comprehensive experiments on two benchmark datasets. The experimental results demonstrate that our model achieves state-of-the-art performances.

PDF Details DOI

NeurIPS Conference 2020 Conference Paper

Leveraging Predictions in Smoothed Online Convex Optimization via Gradient-based Algorithms

Yingying Li
Na Li

We consider online convex optimization with time-varying stage costs and additional switching costs. Since the switching costs introduce coupling across all stages, multi-step-ahead (long-term) predictions are incorporated to improve the online performance. However, longer-term predictions tend to suffer from lower quality. Thus, a critical question is: how to reduce the impact of long-term prediction errors on the online performance? To address this question, we introduce a gradient-based online algorithm, Receding Horizon Inexact Gradient (RHIG), and analyze its performance by dynamic regrets in terms of the temporal variation of the environment and the prediction errors. RHIG only considers at most $W$-step-ahead predictions to avoid being misled by worse predictions in the longer term. The optimal choice of $W$ suggested by our regret bounds depends on the tradeoff between the variation of the environment and the prediction accuracy. Additionally, we apply RHIG to a well-established stochastic prediction error model and provide expected regret and concentration bounds under correlated prediction errors. Lastly, we numerically test the performance of RHIG on quadrotor tracking problems.

PDF Details

NeurIPS Conference 2020 Conference Paper

Scalable Multi-Agent Reinforcement Learning for Networked Systems with Average Reward

Guannan Qu
Yiheng Lin
Adam Wierman
Na Li

It has long been recognized that multi-agent reinforcement learning (MARL) faces significant scalability issues due to the fact that the size of the state and action spaces are exponentially large in the number of agents. In this paper, we identify a rich class of networked MARL problems where the model exhibits a local dependence structure that allows it to be solved in a scalable manner. Specifically, we propose a Scalable Actor-Critic (SAC) method that can learn a near optimal localized policy for optimizing the average reward with complexity scaling with the state-action space size of local neighborhoods, as opposed to the entire network. Our result centers around identifying and exploiting an exponential decay property that ensures the effect of agents on each other decays exponentially fast in their graph distance.

PDF Details

IJCAI Conference 2019 Conference Paper

Network Embedding with Dual Generation Tasks

Jie Liu
Na Li
Zhicheng He

We study the problem of Network Embedding (NE) for content-rich networks. NE models aim to learn efficient low-dimensional dense vectors for network vertices which are crucial to many network analysis tasks. The core problem of content-rich network embedding is to learn and integrate the semantic information conveyed by network structure and node content. In this paper, we propose a general end-to-end model, Dual GEnerative Network Embedding (DGENE), to leverage the complementary information of network structure and content. In this model, each vertex is regarded as an object with two modalities: node identity and textual content. Then we formulate two dual generation tasks. One is Node Identification (NI) which recognizes nodes’ identities given their contents. Inversely, the other one is Content Generation (CG) which generates textual contents given the nodes’ identities. We develop specific Content2Node and Node2Content models for the two tasks. Under the DGENE framework, the two dual models are learned by sharing and integrating intermediate layers, with which they mutually enhance each other. Extensive experimental results show that our model yields a significant performance gain compared to the state-of-the-art NE methods. Moreover, our model has an interesting and useful byproduct, that is, a component of our model can generate texts, which is potentially useful for many tasks.

PDF Details

NeurIPS Conference 2019 Conference Paper

Online Optimal Control with Linear Dynamics and Predictions: Algorithms and Regret Analysis

Yingying Li
Xin Chen
Na Li

This paper studies the online optimal control problem with time-varying convex stage costs for a time-invariant linear dynamical system, where a finite lookahead window of accurate predictions of the stage costs are available at each time. We design online algorithms, Receding Horizon Gradient-based Control (RHGC), that utilize the predictions through finite steps of gradient computations. We study the algorithm performance measured by dynamic regret: the online performance minus the optimal performance in hindsight. It is shown that the dynamic regret of RHGC decays exponentially with the size of the lookahead window. In addition, we provide a fundamental limit of the dynamic regret for any online algorithms by considering linear quadratic tracking problems. The regret upper bound of one RHGC method almost reaches the fundamental limit, demonstrating the effectiveness of the algorithm. Finally, we numerically test our algorithms for both linear and nonlinear systems to show the effectiveness and generality of our RHGC.

PDF Details

YNICL Journal 2016 Journal Article

Changes of grey matter volume in first-episode drug-naive adult major depressive disorder patients with different age-onset

Zonglin Shen
Yuqi Cheng
Shuran Yang
Nan Dai
Jing Ye
Xiaoyan Liu
Jin Lu
Na Li

OBJECTIVE: Little is known about the pathological mechanism of early adult onset depression (EOD) and later adult onset depression (LOD). We seek to determine whether grey matter volume (GMV) change in EOD and LOD are different, which could also delineate EOD and LOD. METHODS: In present study, 147 first-episode, drug-naive patients with major depressive disorder (MDD), age between 18 and 45, were divided into two groups on the basis of age of MDD onset: the early adult onset group (age 18-29) and the later adult onset group (age 30-44), and a total of 130 gender-, and age-, matched healthy controls (HC) were also divided into two groups which fit for each patient group. Magnetic resonance imaging was conducted on all subjects. The voxel-based morphometry (VBM) approach was employed to analyze the images. RESULTS: Widespread abnormalities of GMV throughout parietal, temporal, limbic regions, occipital cortex and cerebellum were observed in MDD patients. Compare to young HC, reduced GMV in right fusiform gyrus, right middle temporal gyrus, vermis III and increased GMV in right middle occipital gyrus were seen in the EOD group. In contrast, relative to old HC, decreased GMV in the right hippocampus and increased GMV in the left middle temporal gyrus were observed in the LOD group. Compared to the LOD group, the EOD group had smaller GMV in right posterior cingulate cortex. There was no significant correlation between GMV of the right posterior cingulate cortex and the score of the depression rating scale in patients group. CONCLUSIONS: The GMV of the brain areas that were related to mood regulation was decreased in the first-episode, drug-naive adult patients with MDD. Adult patients with EOD and LOD exhibited different GMV changes relative to each age-matched comparison group, suggesting depressed adult patients with different age-onset might have different pathological mechanism.

Details DOI

IJCAI Conference 2016 Conference Paper

Incentivizing Reliability in Demand-Side Response

Hongyao Ma
Valentin Robu
Na Li
David C. Parkes

We study the problem of incentivizing reliable demand-response in modern electricity grids. Each agent is uncertain about her future ability to reduce demand and unreliable. Agents who choose to participate in a demand-response scheme may be paid when they respond and penalized otherwise. The goal is to reliably achieve a demand reduction target while selecting a minimal set of agents from those willing to participate. We design incentive-aligned, direct and indirect mechanisms. The direct mechanism elicits both response probabilities and costs, while the indirect mechanism elicits willingness to accept a penalty in the case of non-response. We benchmark against a spot auction, in which demand reduction is purchased from agents when needed. Both the direct and indirect mechanisms achieve the reliability target in a dominant-strategy equilibrium, select a small number of agents to prepare, and do so at low cost and with much lower variance in payments than the spot auction.

PDF Details

ECAI Conference 2016 Conference Paper

Salient Region Detection Based on the Global Contrast Combining Background Measure for Indoor Robots

Na Li
Zhenhua Wang 0001
Lining Sun
Guodong Chen 0001

In this paper, we propose a new method of salient region detection for indoor robots, which integrate the background distribution into the primary saliency. Region roundness is proposed to describe the compactness of a region to measure background distribution more robustly. In order to validate the proposed method, several influential ones are compared on the DSD dataset. The results demonstrate that the proposed approach outperforms existing methods and is useful for indoor robots.

Details