Author name cluster

Yuan 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.

45 papers

2 author rows

EAAI Journal 2026 Journal Article

A hybrid method for anomaly data detection and reconstruction in proton exchange membrane fuel cells to enhance life prediction accuracy

Donghai Hu
Yan Sun
Yinjie Xu
Yuan Li
Biaoyi Liu
Hua Ding
Jing Wang
Hongwei Liu

Life prediction of proton exchange membrane fuel cell (PEMFC) is highly dependent on high-quality data, so accurate detection and effective reconstruction of abnormal data are crucial. The existing research has problems such as a single abnormal data detection model, overly simple reconstruction methods, and insufficient linkage with life prediction. This poses challenges for abnormal detection, data reconstruction and life prediction. This paper proposes an abnormal detection and data reconstruction model based on Variational Autoencoder-Self-Attention Conditional Generative Adversarial Network (VAE-SACGAN). A closed-loop evaluation framework of “detection-reconstruction-lifespan prediction” has been constructed and compared with benchmark models under different traffic and data conditions. The results of abnormal data detection show that the true positive rate of different types of abnormal data exceeds 90%. The results of abnormal data reconstruction show that the Root Mean Square Error (RMSE)/Mean Absolute Error (MAE) is significantly reduced compared with the Generative Adversarial Networks model. The air inlet pressure is reduced from 10. 85/8. 72 to 1. 96/1. 60, and the hydrogen inlet temperature is reduced from 1. 86/1. 54 to 0. 52/0. 42. The results of life prediction show that under congested traffic conditions, compared with abnormal data, the RMSE/MAE of the reconstructed life prediction are significantly reduced. The air inlet pressure is reduced from 3. 42/2. 48 to 1. 84/1. 29, and the hydrogen inlet temperature is reduced from 2. 70/2. 00 to 1. 84/1. 28. The results validate the combined advantages of the model in terms of abnormal detection, data reconstruction and life prediction stability.

AAAI Conference 2026 Conference Paper

DGP: A Dual-Granularity Prompting Framework for Fraud Detection with Graph-Enhanced LLMs

Yuan Li
Jun Hu
Bryan Hooi
Bingsheng He
Cheng Chen

Real-world fraud detection applications benefit from graph learning techniques that jointly exploit node features—often rich in textual data—and graph structural information. Recently, Graph-Enhanced LLMs have emerged as a promising graph learning approach that converts graph information into prompts, exploiting LLMs' ability to reason over both textual and structural information. Among them, text-only prompting, which converts graph information into prompts consisting solely of text tokens, offers a solution that relies only on LLM tuning without requiring additional graph-specific encoders. However, text-only prompting struggles on heterogeneous fraud-detection graphs: multi-hop relations expand exponentially with each additional hop, leading to rapidly growing neighborhoods associated with dense textual information. These neighborhoods may overwhelm the model with long, irrelevant content in the prompt and suppress key signals from the target node, thereby degrading performance. To address this challenge, we propose Dual Granularity Prompting (DGP), which mitigates information overload by preserving fine-grained textual details for the target node while summarizing neighbor information into coarse-grained text prompts. DGP introduces tailored summarization strategies for different data modalities—bi-level semantic abstraction for textual fields and statistical aggregation for numerical features—enabling effective compression of verbose neighbor content into concise, informative prompts. Experiments across public and industry datasets demonstrate that DGP operates within a manageable token budget while improving fraud detection performance by up to 6.8% (AUPRC) over state-of-the-art methods, showing the potential of Graph-Enhanced LLMs for fraud detection.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Echoless Label-Based Pre-computation for Memory-Efficient Heterogeneous Graph Learning

Jun Hu
Shangheng Chen
Yufei He
Yuan Li
Bryan Hooi
Bingsheng He

Heterogeneous Graph Neural Networks (HGNNs) are widely used for deep learning on heterogeneous graphs. Typical end-to-end HGNNs require repetitive message passing during training, limiting efficiency for large-scale real-world graphs. Pre-computation-based HGNNs address this by performing message passing only once during preprocessing, collecting neighbor information into regular-shaped tensors, which enables efficient mini-batch training. Label-based pre-computation methods collect neighbors' label information but suffer from training label leakage, where a node's own label information propagates back to itself during multi-hop message passing—the echo effect. Existing mitigation strategies are memory-inefficient on large graphs or suffer from compatibility issues with advanced message passing methods. We propose Echoless Label-based Pre-computation (Echoless-LP), which eliminates training label leakage with Partition-Focused Echoless Propagation (PFEP). PFEP partitions target nodes and performs echoless propagation, where nodes in each partition collect label information only from neighbors in other partitions, avoiding echo while remaining memory-efficient and compatible with any message passing method. We also introduce an Asymmetric Partitioning Scheme (APS) and a PostAdjust mechanism to address information loss from partitioning and distributional shifts across partitions. Experiments on public datasets demonstrate that Echoless-LP achieves superior performance and maintains memory efficiency compared to baselines.

PDF Details DOI

TCS Journal 2026 Journal Article

Fast leader selection for opinion maximization in signed graphs

Xinna Zhou
Xiaotian Zhou
Yuan Li
Zhongzhi Zhang

A signed graph captures both collaborative and competitive relationships in social networks, offering insights beyond what unsigned graphs provide. This paper delves into the leader selection problem based on the leader-follower Altafini model, represented by a signed graph of n nodes. This model includes a small subset of nodes as competing leaders (either positive or negative) with binary opinions (-1 or 1), while the rest function as followers. We focus on maximizing the overall equilibrium opinion by selecting k = O ( 1 ) positive leaders from the followers, a task that proves to be NP-hard. We introduce a greedy algorithm that operates in O(n 3) time by iteratively selecting one optimal node in each iteration. To design an efficient algorithm, we analyze the equilibrium opinion through a novel random walk approach on the signed graph, expressing the equilibrium opinion of each node in terms of the opinions of leaders and the difference between two newly introduced absorbing probabilities. Then, we devise a Monte Carlo algorithm that samples several random walks with maximal length l, achieving sublinear time complexity of O(kn 1/2 llog5/2 n/ϵ3) for any error parameter ϵ > 0. In each iteration, the algorithm efficiently selects a node whose deviation from the locally optimal marginal gain is limited to a maximum of nϵ. Extensive experiment results indicate that our fast Monte Carlo algorithm outperforms baseline methods and is scalable to large graphs with over 18 million nodes.

AAAI Conference 2026 Conference Paper

FUSE: Fine-Grained and Semantic-Aware Learning for Unified Image Understanding and Generation

Peng Zhang
Wanggui He
Mushui Liu
Wenyi Xiao
Siyu Zou
Yuan Li
Xingjian Wang
Guanghao Zhang

Recent unified models have demonstrated that the reasoning capacity of Multimodal Large Language Models (MLLMs) can be leveraged to facilitate diffusion-based image generation with impressive flexibility and performance. However, approaches that rely heavily on MLLMs for high-level semantic encoding often struggle with fine-grained visual tasks like image editing and virtual try-on. To address this gap, we propose FUSE, a unified framework excelling at both high-level vision–language understanding and fine-grained generation. First, we introduce a Semantic-to-Detail Connector that pre-aligns fine-grained visual features with the MLLM's semantic space. This design counteracts the low-level information loss inherent in MLLM encodings, creating a unified representation that steers the diffusion process with both global semantics and rich local details. Second, to further enhance semantic awareness and detail preservation, we introduce Adaptive-GRPO, a post-training objective that dynamically balances semantic coherence against pixel-level fidelity. The integration of these two innovations allows FUSE to generate images that are both semantically faithful and visually fine-grained. Comprehensive experiments on text-to-image and instruction-guided editing benchmarks show that FUSE significantly outperforms existing unified baselines, achieving 0.89 on Geneval, 0.65 on WISE, and 3.88 on ImageEdit.

PDF Details DOI

AAAI Conference 2026 Conference Paper

NTSFormer: A Self-Teaching Graph Transformer for Multimodal Isolated Cold-Start Node Classification

Jun Hu
Yufei He
Yuan Li
Bryan Hooi
Bingsheng He

Isolated cold-start node classification on multimodal graphs is challenging because such nodes have no edges and often have missing modalities (e.g., absent text or image features). Existing methods address structural isolation by degrading graph learning models to multilayer perceptrons (MLPs) for isolated cold-start inference, using a teacher model (with graph access) to guide the MLP. However, this results in limited model capacity in the student, which is further challenged when modalities are missing. In this paper, we propose Neighbor-to-Self Graph Transformer (NTSFormer), a unified Graph Transformer framework that jointly tackles the isolation and missing-modality issues via a self-teaching paradigm. Specifically, NTSFormer uses a cold-start attention mask to simultaneously make two predictions for each node: a "student" prediction based only on self information (i.e., the node's own features), and a "teacher" prediction incorporating both self and neighbor information. This enables the model to supervise itself without degrading to an MLP, thereby fully leveraging the Transformer's capacity to handle missing modalities. To handle diverse graph information and missing modalities, NTSFormer performs a one-time multimodal graph pre-computation that converts structural and feature data into token sequences, which are then processed by Mixture-of-Experts (MoE) Input Projection and Transformer layers for effective fusion. Experiments on public datasets show that NTSFormer achieves superior performance for multimodal isolated cold-start node classification.

PDF Details DOI

ECAI Conference 2025 Conference Paper

A Frequency-Temporal Causal Inference Guided Adversarial Network for Cross-Subject MI-BCI Decoding

Yuan Li
Diwei Su
Xiangcun Wang
Hongxi Zhao
Jiacai Zhang

Motor Imagery Brain-Computer Interface (MI-BCI) is a key technology of Brain-Computer Interfaces (BCIs). In practical applications, high-accuracy cross-subject decoding is difficult to achieve due to multi-source heterogeneity caused by individual differences among subjects. Transfer learning technology has been widely applied to try to solve this problem, but existing transfer learning models have neglected the frequency features of EEG signals and the temporal pattern dependency present in high-level features. This restricts the performance and generalization ability of existing cross-subject decoding methods. This study leverages frequency prior knowledge related to motor imagery for data augmentation and designs feature extractor, combined with adversarial learning to achieve cross-subject feature alignment. Unlike traditional adversarial learning frameworks, this work introduces a temporal causal inference module in the classifier to reprocess high-level features, dynamically model the temporal characteristics of EEG signals to reduce bias, and achieve efficient decoding through synchronous training of the discriminator and classifier. Based on a pure convolutional neural network (CNN) architecture, the framework achieved decoding accuracies of 82. 64% and 85. 51% on the BCI Competition IV 2a and 2b datasets, respectively, surpassing state-of-the-art Transformer architectures (e. g. , GAT, BLSAN). These results provide a feasible solution for developing efficient and practical MI-BCI systems and lay a foundation for optimizing cross-subject decoding.

ICLR Conference 2025 Conference Paper

CityAnchor: City-scale 3D Visual Grounding with Multi-modality LLMs

Jinpeng Li
Haiping Wang 0004
Jiabin Chen
Yuan Liu 0025
Zhiyang Dou
Yuexin Ma
Sibei Yang
Yuan Li

In this paper, we present a 3D visual grounding method called CityAnchor for localizing an urban object in a city-scale point cloud. Recent developments in multiview reconstruction enable us to reconstruct city-scale point clouds but how to conduct visual grounding on such a large-scale urban point cloud remains an open problem. Previous 3D visual grounding system mainly concentrates on localizing an object in an image or a small-scale point cloud, which is not accurate and efficient enough to scale up to a city-scale point cloud. We address this problem with a multi-modality LLM which consists of two stages, a coarse localization and a fine-grained matching. Given the text descriptions, the coarse localization stage locates possible regions on a projected 2D map of the point cloud while the fine-grained matching stage accurately determines the most matched object in these possible regions. We conduct experiments on the CityRefer dataset and a new synthetic dataset annotated by us, both of which demonstrate our method can produce accurate 3D visual grounding on a city-scale 3D point cloud.

AAAI Conference 2025 Conference Paper

Deep Evidential Hashing for Trustworthy Cross-Modal Retrieval

Yuan Li
Liangli Zhen
Yuan Sun
Dezhong Peng
Xi Peng
Peng Hu

Cross-modal hashing provides an efficient solution for retrieval tasks across various modalities, such as images and text. However, most existing methods are deterministic models, which overlook the reliability associated with the retrieved results. This omission renders them unreliable for determining matches between data pairs based solely on Hamming distance. To bridge the gap, in this paper, we propose a novel method called Deep Evidential Cross-modal Hashing (DECH). This method equips hashing models with the ability to quantify the reliability level of the association between a query sample and each corresponding retrieved sample, bringing a new dimension of reliability to the cross-modal retrieval process. To achieve this, our method addresses two key challenges: i) To leverage evidential theory in guiding the model to learn hash codes, we design a novel evidence acquisition module to collect evidence and place the evidence captured by hash codes on a Beta distribution to derive a binomial opinion. Unlike existing evidential learning approaches that rely on classifiers, our method collects evidence directly through hash codes. ii) To tackle the task-oriented challenge, we first introduce a method to update the derived binomial opinion, allowing it to present the uncertainty caused by conflicting evidence. Following this manner, we present a strategy to precisely evaluate the reliability level of retrieved results, culminating in performance improvement. We validate the efficacy of our DECH through extensive experimentation on four benchmark datasets. The experimental results demonstrate our superior performance compared to 12 state-of-the-art methods.

PDF Details DOI

ICML Conference 2025 Conference Paper

EgoPrivacy: What Your First-Person Camera Says About You?

Yijiang Li
Genpei Zhang
Jiacheng Cheng
Yi Li 0051
Xiaojun Shan
Dashan Gao 0001
Jiancheng Lyu
Yuan Li

While the rapid proliferation of wearable cameras has raised significant concerns about egocentric video privacy, prior work has largely overlooked the unique privacy threats posed to the camera wearer. This work investigates the core question: How much privacy information about the camera wearer can be inferred from their first-person view videos? We introduce EgoPrivacy, the first large-scale benchmark for the comprehensive evaluation of privacy risks in egocentric vision. EgoPrivacy covers three types of privacy (demographic, individual, and situational), defining seven tasks that aim to recover private information ranging from fine-grained (e. g. , wearer’s identity) to coarse-grained (e. g. , age group). To further emphasize the privacy threats inherent to egocentric vision, we propose Retrieval-Augmented Attack, a novel attack strategy that leverages ego-to-exo retrieval from an external pool of exocentric videos to boost the effectiveness of demographic privacy attacks. An extensive comparison of the different attacks possible under all threat models is presented, showing that private information of the wearer is highly susceptible to leakage. For instance, our findings indicate that foundation models can effectively compromise wearer privacy even in zero-shot settings by recovering attributes such as identity, scene, gender, and race with 70–80% accuracy. Our code and data are available at https: //github. com/williamium3000/ego-privacy.

EAAI Journal 2025 Journal Article

Fast shallow multi-subnet detector for real-time object detection

Yuan Li
Mengdie Song
Ke Hu
Song Chen
Yi Kang

Real-time object detection algorithms, underpinned by Deep Neural Networks (DNNs), are extensively applied in fields like autonomous driving and security surveillance. However, current algorithms face issues of low hardware resource utilization and high synchronization delays between network layers when deployed on DNN hardware accelerators, adversely affecting overall performance and efficiency. To address these issues, we have proposed an innovative single-stage object detection framework, the Shallow Multi-Subnet Detector (SMS-Det). SMS-Det adopts a multi-parallel-shallow-subnet architecture, which reduces inter-layer synchronization latency by decreasing network depth. Furthermore, it fully utilizes DNN hardware accelerators by executing convolution operations in parallel, preventing resource underutilization and maximizing throughput. The proposed network is comprised of multiple parallel shallow subnets, each of which processes feature maps of different scales. The Feature Fusion Layer (FFL) ensures seamless information exchange across subnets, significantly improving the detection of small and occluded objects. Finally, we introduce the multi-scale channel attention projections to enhance the feature mapping between the teacher model and the student model in the training process. Experimental results on the Microsoft Common Objects in Context (MS COCO) dataset demonstrate that our model achieves a state-of-the-art mean Average Precision (mAP) of 42. 6%, surpassing You Only Look Once Version 5 Small (YOLOv5-S 37. 4%) with only 19. 4 Giga Floating Point Operations (GFLOPs) and 11. 0 million parameters. Our model obtains 156 Frames Per Second (FPS), achieving a real-time inference acceleration of 51. 4% compared to YOLOv5-S (103 FPS).

NeurIPS Conference 2025 Conference Paper

Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective

Jorge (Zhoujun) Cheng
Shibo Hao
Tianyang Liu
Fan Zhou
Yutao Xie
Feng Yao
Yuexin Bian
Nilabjo Dey

Reinforcement learning (RL) has shown promise in enhancing large language model (LLM) reasoning, yet progress towards broader capabilities is limited by the availability of high-quality, multi-domain datasets. This work introduces \ours, a 92K RL-for-reasoning dataset designed to address this gap, covering six reasoning domains: Math, Code, Science, Logic, Simulation, and Tabular, each with corresponding verifiers. We build \ours via a careful data-curation pipeline, including sourcing, deduplication, reward design, and domain-specific and difficulty-based filtering, to facilitate the systematic investigation of cross-domain RL generalization. Our study using \ours suggests the efficacy of a simple mixed-domain RL training approach and reveals several key aspects affecting cross-domain transferability. We further train two models {\ours}-7B and {\ours}-32B purely with RL on our curated data and observe largely improved performance over leading open RL reasoning model baselines, with gains of 7. 3\% and 7. 8\% respectively on an extensive 17-task, six-domain evaluation suite. We are releasing our dataset, code, and evaluation suite to the community, aiming to support further research and development of more general RL-enhanced reasoning models.

EAAI Journal 2025 Journal Article

Semi-supervised federated learning for collaborative security threat detection in control system for distributed power generation

Yuan Li
Yuancheng Li

In response to the frequent occurrence of security incidents in existing control system for distributed power generation, the current security threat detection technologies face issues such as low detection accuracy, as well as inadequate data utilization due to objective reasons such as the high cost and low efficiency of manual data annotation, and the unreliability of automatic pseudo-annotation by models. we propose a semi-supervised federated learning-based security threat detection framework called federated uncertainty-aware pseudo-label selection (FedUPS). Firstly, this method utilizes Convolutional Neural Networks (CNNs) to effectively capture threats in control system for distributed power generation. Secondly, considering the characteristics of data spanning across devices and regions, we introduce federated learning methods to ensure the privacy and security of local data. Furthermore, to address the issue of unlabeled data within the system, we employ an Uncertainty-aware Pseudo-label Selection (UPS) framework to pseudo-label unlabeled data, ensuring the credibility of these pseudo-labels and incorporating them into the model training process. Lastly, in response to the dynamic changes in sample size and local model accuracy, we design a dynamic weighted aggregation method to optimize parameter updates and the model training process. Extensive experimental results demonstrate that our proposed method achieves an improvement in the optimal accuracy rate ranging from 2. 46% to 12. 28% within 50 iterations of training on the Network-Based Internet of Things (N-BaIoT) dataset. This method exhibits both effectiveness and practicality in detecting security threats in distributed power regulation systems.

AAAI Conference 2025 Conference Paper

SIGraph: Saliency Image-Graph Network for Retinal Disease Classification in Fundus Image

Peng Zhang
Yuan Li
Haotian Song
Yankai Jiang
Yubo Tao
Hai Lin
Hongguang Cui

An efficient and precise diagnosis of retinal diseases is a fundamental goal for auxiliary diagnostic systems in ophthalmology. Inspired by the importance of scattered subtle lesions in manual retinal disease diagnosis, recent research has achieved state-of-the-art performance by mining information related to subtle lesions, including their texture and shape. However, the spatial distribution patterns of subtle lesion areas, which are also crucial in manual diagnosis, have been overlooked in existing research. Neglecting these spatial distribution patterns (e.g., the ring distribution of microaneurysms in diabetic macular edema) may negatively impact the diagnostic process. In this paper, we introduce the Saliency-Image-Graph (SIGraph) network to capture the spatial distribution patterns of lesion areas. We first employ saliency-based perception to identify latent lesion pixels. Subsequently, we propose a novel image-graph block to efficiently capture the global distribution of abundant lesion pixels with minimal information loss. By leveraging additional distribution patterns, SIGraph achieves state-of-the-art performance with at least a 1.5% performance gain across three datasets. Furthermore, ablation studies demonstrate that our image-graph block can be integrated into other visual backbones and effectively boost performance.

PDF Details DOI

AAAI Conference 2024 Conference Paper

DALDet: Depth-Aware Learning Based Object Detection for Autonomous Driving

Ke Hu
Tongbo Cao
Yuan Li
Song Chen
Yi Kang

3D object detection achieves good detection performance in autonomous driving. However, it requires substantial computational resources, which prevents its practical application. 2D object detection has less computational burden but lacks spatial and geometric information embedded in depth. Therefore, we present DALDet, an efficient depth-aware learning based 2D detector, achieving high-performance object detection for autonomous driving. We design an efficient one-stage detection framework and seamlessly integrate depth cues into convolutional neural network by introducing depth-aware convolution and depth-aware average pooling, which effectively improve the detector's ability to perceive 3D space. Moreover, we propose a depth-guided loss function for training DALDet, which effectively improves the localization ability of the detector. Due to the use of depth map, DALDet can also output the distance of the object, which is of great importance for driving applications such as obstacle avoidance. Extensive experiments demonstrate the superiority and efficiency of DALDet. In particular, our DALDet ranks 1st on both KITTI Car and Cyclist 2D detection test leaderboards among all 2D detectors with high efficiency as well as yielding competitive performance among many leading 3D detectors. Code will be available at https://github.com/hukefy/DALDet.

PDF Details DOI

I&C Journal 2024 Journal Article

Monomial Boolean functions with large high-order nonlinearities

Jinjie Gao
Haibin Kan
Yuan Li
Jiahua Xu
Qichun Wang

Exhibiting an explicit Boolean function with a large high-order nonlinearity is an important problem in cryptography, coding theory, and computational complexity. We prove lower bounds on the second-order, third-order, and higher order nonlinearities of some monomial Boolean functions. We prove lower bounds on the second-order nonlinearities of functions tr n ( x 7 ) and tr n ( x 2 r + 3 ) where n = 2 r. Among all monomial Boolean functions, our bounds match the best second-order nonlinearity lower bounds by Carlet [IEEE Transactions on Information Theory 54(3), 2008] and Yan and Tang [Discrete Mathematics 343(5), 2020] for odd and even n, respectively. We prove a lower bound on the third-order nonlinearity for functions tr n ( x 15 ), which is the best third-order nonlinearity lower bound. For any r, we prove that the r-th order nonlinearity of tr n ( x 2 r + 1 − 1 ) is at least 2 n − 1 − 2 ( 1 − 2 − r ) n + r 2 r − 1 − 1 − O ( 2 n 2 ). For r ≪ log 2 ⁡ n, this is the best lower bound among all explicit functions.

NeurIPS Conference 2024 Conference Paper

Neural Gaffer: Relighting Any Object via Diffusion

Haian Jin
Yuan Li
Fujun Luan
Yuanbo Xiangli
Sai Bi
Kai Zhang
Zexiang Xu
Jin Sun

Single-image relighting is a challenging task that involves reasoning about the complex interplay between geometry, materials, and lighting. Many prior methods either support only specific categories of images, such as portraits, or require special capture conditions, like using a flashlight. Alternatively, some methods explicitly decompose a scene into intrinsic components, such as normals and BRDFs, which can be inaccurate or under-expressive. In this work, we propose a novel end-to-end 2D relighting diffusion model, called Neural Gaffer, that takes a single image of any object and can synthesize an accurate, high-quality relit image under any novel environmental lighting condition, simply by conditioning an image generator on a target environment map, without an explicit scene decomposition. Our method builds on a pre-trained diffusion model, and fine-tunes it on a synthetic relighting dataset, revealing and harnessing the inherent understanding of lighting present in the diffusion model. We evaluate our model on both synthetic and in-the-wild Internet imagery and demonstrate its advantages in terms of generalization and accuracy. Moreover, by combining with other generative methods, our model enables many downstream 2D tasks, such as text-based relighting and object insertion. Our model can also operate as a strong relighting prior for 3D tasks, such as relighting a radiance field.

PDF Details DOI

TCS Journal 2024 Journal Article

Obtaining simulation extractable NIZKs in the updatable CRS model generically

Liguan Wang
Yuan Li
Haibin Kan

Non-interactive zero-knowledge proofs as well as succinct non-interactive argument of knowledge (SNARK) are playing a central role in both theory and application of cryptography. Simulation extractable for SNARKs is considered a necessary security requirement by most applications which prevents the protocol from malleable attacks. However, a trusted party is required to generate the common reference string (CRS) for SNARKs which can be quite problematic in real applications. Recently, the subvertible and updatable CRS model has been proposed to relax the trust in the CRS generation procedure. In this paper, we propose two generic compilers that can achieve simulation extractable in the updatable CRS model. By using an efficient updatable verifiable random function defined in this paper which may be of independent interest, we show that our compiler can lift the updatable knowledge soundness of the underlying SNARKs to achieve updatable simulation extractability. We extend our results by proposing another compiler that can lift a NIZK that has an even weaker security notion called updatable soundness to achieve updatable simulation extractability. We instantiate our compilers and compare them to other related works. This shows that our efficient compilers can be used in various applications.

ICML Conference 2024 Conference Paper

Position: TrustLLM: Trustworthiness in Large Language Models

Yue Huang 0001
Lichao Sun 0001
Haoran Wang 0005
Siyuan Wu 0001
Qihui Zhang
Yuan Li
Chujie Gao
Yixin Huang

Large language models (LLMs) have gained considerable attention for their excellent natural language processing capabilities. Nonetheless, these LLMs present many challenges, particularly in the realm of trustworthiness. This paper introduces TrustLLM, a comprehensive study of trustworthiness in LLMs, including principles for different dimensions of trustworthiness, established benchmark, evaluation, and analysis of trustworthiness for mainstream LLMs, and discussion of open challenges and future directions. Specifically, we first propose a set of principles for trustworthy LLMs that span eight different dimensions. Based on these principles, we further establish a benchmark across six dimensions including truthfulness, safety, fairness, robustness, privacy, and machine ethics. We then present a study evaluating 16 mainstream LLMs in TrustLLM, consisting of over 30 datasets. Our findings firstly show that in general trustworthiness and capability (i. e. , functional effectiveness) are positively related. Secondly, our observations reveal that proprietary LLMs generally outperform most open-source counterparts in terms of trustworthiness, raising concerns about the potential risks of widely accessible open-source LLMs. However, a few open-source LLMs come very close to proprietary ones, suggesting that open-source models can achieve high levels of trustworthiness without additional mechanisms like moderator, offering valuable insights for developers in this field. Thirdly, it is important to note that some LLMs may be overly calibrated towards exhibiting trustworthiness, to the extent that they compromise their utility by mistakenly treating benign prompts as harmful and consequently not responding. Besides these observations, we’ve uncovered key insights into the multifaceted trustworthiness in LLMs. We emphasize the importance of ensuring transparency not only in the models themselves but also in the technologies that underpin trustworthiness. We advocate that the establishment of an AI alliance between industry, academia, the open-source community to foster collaboration is imperative to advance the trustworthiness of LLMs.

IROS Conference 2023 Conference Paper

Real-Time Whole-Body Collision Avoidance and Path Following of a Snake Robot Through MPC-based Optimization Strategies

Liuyin Wang
Gang Wang 0024
Yuan Li
Peng Li 0019
Yunfeng Ji
Chaoli Wang 0002
Yantao Shen 0001

The work in this paper delves into the challenge of whole elongated body's obstacle avoidance during path following for a class of bionic snake robots. Currently, most studies focus solely on preventing the robot's head from colliding with obstacles through designed controllers. However, due to the unique elongated structure and biomimetic locomotion modes of snake robots, it is unavoidable that the rest of the robot's body could still collide with obstacles. To resolve this problem, we propose a novel real-time optimization obstacle avoidance strategy for a class of terrestrial snake robots with multi-link elongated body using model predictive control (MPC). Moreover, by leveraging the elongated body characteristics of the robot, an improved path guidance strategy is also developed. The effectiveness of the proposed strategies is verified and validated through extensive simulations and experiments on a custom-built nine-link elongated snake robot. The results demonstrate that all links of the robot can well avoid obstacles while continuing to track the given path.

NeurIPS Conference 2022 Conference Paper

A Unified Diversity Measure for Multiagent Reinforcement Learning

Zongkai Liu
Chao Yu
Yaodong Yang
Peng Sun
Zifan Wu
Yuan Li

Promoting behavioural diversity is of critical importance in multi-agent reinforcement learning, since it helps the agent population maintain robust performance when encountering unfamiliar opponents at test time, or, when the game is highly non-transitive in the strategy space (e. g. , Rock-Paper-Scissor). While a myriad of diversity metrics have been proposed, there are no widely accepted or unified definitions in the literature, making the consequent diversity-aware learning algorithms difficult to evaluate and the insights elusive. In this work, we propose a novel metric called the Unified Diversity Measure (UDM) that offers a unified view for existing diversity metrics. Based on UDM, we design the UDM-Fictitious Play (UDM-FP) and UDM-Policy Space Response Oracle (UDM-PSRO) algorithms as efficient solvers for normal-form games and open-ended games. In theory, we prove that UDM-based methods can enlarge the gamescape by increasing the response capacity of the strategy pool, and have convergence guarantee to two-player Nash equilibrium. We validate our algorithms on games that show strong non-transitivity, and empirical results show that our algorithms achieve better performances than strong PSRO baselines in terms of the exploitability and population effectivity.

TCS Journal 2022 Journal Article

Certificate complexity of elementary symmetric Boolean functions

Jing Zhang
Yuan Li

Boolean functions have important applications in information technology and computer science. Certificate complexity is an important combinatorial measure of Boolean function complexity. In this paper, we first introduce many concise and efficient notations then we study the elementary symmetric Boolean functions and obtain their certificate complexities when their degrees are odd or powers of 2. We show that both upper and lower bounds of certificate complexities can be attained.

JBHI Journal 2022 Journal Article

Dynamic Link Prediction for Discovery of New Impactful COVID-19 Research Approaches

Xiangyu Wang
Yuan Li
Taiyu Ban
Jiarun Zhu
Lyuzhou Chen
Muhammad Usman
Xin Wang
Huanhuan Chen

In fighting the COVID-19 pandemic, the main challenges include the lack of prior research and the urgency to find effective solutions. It is essential to accurately and rapidly summarize the relevant research work and explore potential solutions for diagnosis, treatment and prevention of COVID-19. It is a daunting task to summarize the numerous existing research works and to assess their effectiveness. This paper explores the discovery of new COVID-19 research approaches based on dynamic link prediction, which analyze the dynamic topological network of keywords to predict possible connections of research concepts. A dynamic link prediction method based on multi-granularity feature fusion is proposed. Firstly, a multi-granularity temporal feature fusion method is adopted to extract the temporal evolution of different order subgraphs. Secondly, a hierarchical feature weighting method is proposed to emphasize actively evolving nodes. Thirdly, a semantic repetition sampling mechanism is designed to avoid the negative effect of semantically equivalent medical entities on the real structure of the graph, and to capture the real topological structure features. Experiments are performed on the COVID-19 Open Research Dataset to assess the performance of the model. The results show that the proposed model performs significantly better than existing state-of-the-art models, thereby confirming the effectiveness of the proposed method for the discovery of new COVID-19 research approaches.

NeurIPS Conference 2022 Conference Paper

Heterogeneous Skill Learning for Multi-agent Tasks

Yuntao Liu
Yuan Li
Xinhai Xu
Yong Dou
Donghong Liu

Heterogeneous behaviours are widespread in many multi-agent tasks, which have not been paid much attention in the community of multi-agent reinforcement learning. It would be a key factor for improving the learning performance to efficiently characterize and automatically find heterogeneous behaviours. In this paper, we introduce the concept of the skill to explore the ability of heterogeneous behaviours. We propose a novel skill-based multi-agent reinforcement learning framework to enable agents to master diverse skills. Specifically, our framework consists of the skill representation mechanism, the skill selector and the skill-based policy learning mechanism. We design an auto-encoder model to generate the latent variable as the skill representation by incorporating the environment information, which ensures the distinguishable of agents for skill selection and the discriminability for the skill learning. With the representation, a skill selection mechanism is invented to realize the assignment from agents to skills. Meanwhile, diverse skill-based policies are generated through a novel skill-based policy learning method. To promote efficient skill discovery, a mutual information based intrinsic reward function is constructed. Empirical results show that our framework obtains the best performance on three challenging benchmarks, i. e. , StarCraft II micromanagement tasks, Google Research Football and GoBigger, over state-of-the-art MARL methods.

IJCAI Conference 2022 Conference Paper

SatFormer: Saliency-Guided Abnormality-Aware Transformer for Retinal Disease Classification in Fundus Image

Yankai Jiang
Ke Xu
Xinyue Wang
Yuan Li
Hongguang Cui
Yubo Tao
Hai Lin

Automatic and accurate retinal disease diagnosis is critical to guide proper therapy and prevent potential vision loss. Previous works simply exploit the most discriminative features while ignoring the pathological visual clues of scattered subtle lesions. Therefore, without a comprehensive understanding of features from different lesion regions, they are vulnerable to noise from complex backgrounds and suffer from misclassification failures. In this paper, we address these limitations with a novel saliency-guided abnormality-aware transformer which explicitly captures the correlation between different lesion features from a global perspective with enhanced pathological semantics. The model has several merits. First, we propose a saliency enhancement module (SEM) which adaptively integrates disease related semantics and highlights potentially salient lesion regions. Second, to the best of our knowledge, this is the first work to explore comprehensive lesion feature dependencies via a tailored efficient self-attention. Third, with the saliency enhancement module and abnormality-aware attention, we propose a new variant of Vision Transformer models, called SatFormer, which outperforms the state-of-the-art methods on two public retinal disease classification benchmarks. Ablation study shows that the proposed components can be easily embedded into any Vision Transformers via a plug-and-play manner and effectively boost the performance.

PDF Details DOI

JBHI Journal 2022 Journal Article

Self-Supervised Transfer Learning Based on Domain Adaptation for Benign-Malignant Lung Nodule Classification on Thoracic CT

Hong Huang
Ruoyu Wu
Yuan Li
Chao Peng

The spatial heterogeneity is an important indicator of the malignancy of lung nodules in lung cancer diagnosis. Compared with 2D nodule CT images, the 3D volumes with entire nodule objects hold richer discriminative information. However, for deep learning methods driven by massive data, effectively capturing the 3D discriminative features of nodules in limited labeled samples is a challenging task. Different from previous models that proposed transfer learning models in a 2D pattern or learning from scratch 3D models, we develop a self-supervised transfer learning based on domain adaptation (SSTL-DA) 3D CNN framework for benign-malignant lung nodule classification. At first, a data pre-processing strategy termed adaptive slice selection (ASS) is developed to eliminate the redundant noise of the input samples with lung nodules. Then, the self-supervised learning network is constructed to learn robust image representations from CT images. Finally, a transfer learning method based on domain adaptation is designed to obtain discriminant features for classification. The proposed SSTL-DA method has been assessed on the LIDC-IDRI benchmark dataset, and it obtains an accuracy of 91. 07% and an AUC of 95. 84%. These results demonstrate that the SSTL-DA model achieves quite a competitive classification performance compared with some state-of-the-art approaches

TIST Journal 2022 Journal Article

The OARF Benchmark Suite: Characterization and Implications for Federated Learning Systems

Sixu Hu
Yuan Li
Xu Liu
Qinbin Li
Zhaomin Wu
Bingsheng He

This article presents and characterizes an Open Application Repository for Federated Learning (OARF), a benchmark suite for federated machine learning systems. Previously available benchmarks for federated learning (FL) have focused mainly on synthetic datasets and use a limited number of applications. OARF mimics more realistic application scenarios with publicly available datasets as different data silos in image, text, and structured data. Our characterization shows that the benchmark suite is diverse in data size, distribution, feature distribution, and learning task complexity. The extensive evaluations with reference implementations show the future research opportunities for important aspects of FL systems. We have developed reference implementations, and evaluated the important aspects of FL, including model accuracy, communication cost, throughput, and convergence time. Through these evaluations, we discovered some interesting findings such as FL can effectively increase end-to-end throughput. The code of OARF is publicly available on GitHub. 1

AAAI Conference 2022 Conference Paper

TransBoost: A Boosting-Tree Kernel Transfer Learning Algorithm for Improving Financial Inclusion

Yiheng Sun
Tian Lu
Cong Wang
Yuan Li
Huaiyu Fu
Jingran Dong
Yunjie Xu

The prosperity of mobile and financial technologies has bred and expanded various kinds of financial products to a broader scope of people, which contributes to financial inclusion. It brings non-trivial social benefits of diminishing financial inequality. However, the technical challenges in individual financial risk evaluation exacerbated by the unforeseen user characteristic distribution and limited credit history of new users, as well as the inexperience of newly-entered companies in handling complex data and obtaining accurate labels, impede further promotion of financial inclusion. To tackle these challenges, this paper develops a novel transfer learning algorithm (i. e. , TransBoost) that combines the merits of tree-based models and kernel methods. The TransBoost is designed with a parallel tree structure and efficient weights updating mechanism with theoretical guarantee, which enables it to excel in tackling realworld data with high dimensional features and sparsity in O(n) time complexity. We conduct extensive experiments on two public datasets and a unique largescale dataset from Tencent Mobile Payment. The results show that the TransBoost outperforms other state-ofthe-art benchmark transfer learning algorithms in terms of prediction accuracy with superior efficiency, demonstrate stronger robustness to data sparsity, and provide meaningful model interpretation. Besides, given a financial risk level, the TransBoost enables financial service providers to serve the largest number of users including those who would otherwise be excluded by other algorithms. That is, the TransBoost improves financial inclusion.

AAAI Conference 2021 Conference Paper

Robust Knowledge Transfer via Hybrid Forward on the Teacher-Student Model

Liangchen Song
Jialian Wu
Ming Yang
Qian Zhang
Yuan Li
Junsong Yuan

When adopting deep neural networks for a new vision task, a common practice is to start with fine-tuning some offthe-shelf well-trained network models from the community. Since a new task may require training a different network architecture with new domain data, taking advantage of off-theshelf models is not trivial and generally requires considerable try-and-error and parameter tuning. In this paper, we denote a well-trained model as a teacher network and a model for the new task as a student network. We aim to ease the efforts of transferring knowledge from the teacher to the student network, robust to the gaps between their network architectures, domain data, and task definitions. Specifically, we propose a hybrid forward scheme in training the teacher-student models, alternately updating layer weights of the student model. The key merit of our hybrid forward scheme is on the dynamical balance between the knowledge transfer loss and task specific loss in training. We demonstrate the effectiveness of our method on a variety of tasks, e. g, model compression, segmentation, and detection, under a variety of knowledge transfer settings.

JBHI Journal 2021 Journal Article

Weakly Supervised Histopathology Image Segmentation With Sparse Point Annotations

Zhe Chen
Zhao Chen
Jingxin Liu
Qiang Zheng
Yuang Zhu
Yanfei Zuo
Zhaoyu Wang
Xiaosong Guan

Digital histopathology image segmentation can facilitate computer-assisted cancer diagnostics. Given the difficulty of obtaining manual annotations, weak supervision is more suitable for the task than full supervision is. However, most weakly supervised models are not ideal for handling severe intra-class heterogeneity and inter-class homogeneity in histopathology images. Therefore, we propose a novel end-to-end weakly supervised learning framework named WESUP. With only sparse point annotations, it performs accurate segmentation and exhibits good generalizability. The training phase comprises two major parts, hierarchical feature representation and deep dynamic label propagation. The former uses superpixels to capture local details and global context from the convolutional feature maps obtained via transfer learning. The latter recognizes the manifold structure of the hierarchical features and identifies potential targets with the sparse annotations. Moreover, these two parts are trained jointly to improve the performance of the whole framework. To further boost test performance, pixel-wise inference is adopted for finer prediction. As demonstrated by experimental results, WESUP is able to largely resolve the confusion between histological foreground and background. It outperforms several state-of-the-art weakly supervised methods on a variety of histopathology datasets with minimal annotation efforts. Trained by very sparse point annotations, WESUP can even beat an advanced fully supervised segmentation network.

NeurIPS Conference 2020 Conference Paper

AutoSync: Learning to Synchronize for Data-Parallel Distributed Deep Learning

Hao Zhang
Yuan Li
Zhijie Deng
Xiaodan Liang
Lawrence Carin
Eric Xing

Synchronization is a key step in data-parallel distributed machine learning (ML). Different synchronization systems and strategies perform differently, and to achieve optimal parallel training throughput requires synchronization strategies that adapt to model structures and cluster configurations. Existing synchronization systems often only consider a single or a few synchronization aspects, and the burden of deciding the right synchronization strategy is then placed on the ML practitioners, who may lack the required expertise. In this paper, we develop a model- and resource-dependent representation for synchronization, which unifies multiple synchronization aspects ranging from architecture, message partitioning, placement scheme, to communication topology. Based on this representation, we build an end-to-end pipeline, AutoSync, to automatically optimize synchronization strategies given model structures and resource specifications, lowering the bar for data-parallel distributed ML. By learning from low-shot data collected in only 200 trial runs, AutoSync can discover synchronization strategies up to 1. 6x better than manually optimized ones. We develop transfer-learning mechanisms to further reduce the auto-optimization cost -- the simulators can transfer among similar model architectures, among similar cluster configurations, or both. We also present a dataset that contains over 10000 synchronization strategies and run-time pairs on a diverse set of models and cluster specifications.

AAAI Conference 2020 Conference Paper

Complementary Auxiliary Classifiers for Label-Conditional Text Generation

Yuan Li
Chunyuan Li
Yizhe Zhang
Xiujun Li
Guoqing Zheng
Lawrence Carin
Jianfeng Gao

Learning to generate text with a given label is a challenging task because natural language sentences are highly variable and ambiguous. It renders difﬁculties in trade-off between sentence quality and label ﬁdelity. In this paper, we present CARA to alleviate the issue, where two auxiliary classiﬁers work simultaneously to ensure that (1) the encoder learns disentangled features and (2) the generator produces labelrelated sentences. Two practical techniques are further proposed to improve the performance, including annealing the learning signal from the auxiliary classiﬁer, and enhancing the encoder with pre-trained language models. To establish a comprehensive benchmark fostering future research, we consider a suite of four datasets, and systematically reproduce three representative methods. CARA shows consistent improvement over the previous methods on the task of labelconditional text generation, and achieves state-of-the-art on the task of attribute transfer.

ICLR Conference 2020 Conference Paper

Fast Neural Network Adaptation via Parameter Remapping and Architecture Search

Jiemin Fang
Yuzhu Sun
Kangjian Peng
Qian Zhang 0009
Yuan Li
Wenyu Liu 0001
Xinggang Wang

Deep neural networks achieve remarkable performance in many computer vision tasks. Most state-of-the-art~(SOTA) semantic segmentation and object detection approaches reuse neural network architectures designed for image classification as the backbone, commonly pre-trained on ImageNet. However, performance gains can be achieved by designing network architectures specifically for detection and segmentation, as shown by recent neural architecture search (NAS) research for detection and segmentation. One major challenge though, is that ImageNet pre-training of the search space representation (a.k.a. super network) or the searched networks incurs huge computational cost. In this paper, we propose a Fast Neural Network Adaptation (FNA) method, which can adapt both the architecture and parameters of a seed network (e.g. a high performing manually designed backbone) to become a network with different depth, width, or kernels via a Parameter Remapping technique, making it possible to utilize NAS for detection/segmentation tasks a lot more efficiently. In our experiments, we conduct FNA on MobileNetV2 to obtain new networks for both segmentation and detection that clearly out-perform existing networks designed both manually and by NAS. The total computation cost of FNA is significantly less than SOTA segmentation/detection NAS approaches: 1737$\times$ less than DPC, 6.8$\times$ less than Auto-DeepLab and 7.4$\times$ less than DetNAS. The code is available at https://github.com/JaminFong/FNA .

ICLR Conference 2020 Conference Paper

FasterSeg: Searching for Faster Real-time Semantic Segmentation

Wuyang Chen 0001
Xinyu Gong
Xianming Liu 0005
Qian Zhang
Yuan Li
Zhangyang Wang

We present FasterSeg, an automatically designed semantic segmentation network with not only state-of-the-art performance but also faster speed than current methods. Utilizing neural architecture search (NAS), FasterSeg is discovered from a novel and broader search space integrating multi-resolution branches, that has been recently found to be vital in manually designed segmentation models. To better calibrate the balance between the goals of high accuracy and low latency, we propose a decoupled and fine-grained latency regularization, that effectively overcomes our observed phenomenons that the searched networks are prone to "collapsing" to low-latency yet poor-accuracy models. Moreover, we seamlessly extend FasterSeg to a new collaborative search (co-searching) framework, simultaneously searching for a teacher and a student network in the same single run. The teacher-student distillation further boosts the student model’s accuracy. Experiments on popular segmentation benchmarks demonstrate the competency of FasterSeg. For example, FasterSeg can run over 30% faster than the closest manually designed competitor on Cityscapes, while maintaining comparable accuracy.

AIIM Journal 2020 Journal Article

Rule-based automatic diagnosis of thyroid nodules from intraoperative frozen sections using deep learning

Yuan Li
Pingjun Chen
Zhiyuan Li
Hai Su
Lin Yang
Dingrong Zhong

Frozen sections provide a basis for rapid intraoperative diagnosis that can guide surgery, but the diagnoses often challenge pathologists. Here we propose a rule-based system to differentiate thyroid nodules from intraoperative frozen sections using deep learning techniques. The proposed system consists of three components: (1) automatically locating tissue regions in the whole slide images (WSIs), (2) splitting located tissue regions into patches and classifying each patch into predefined categories using convolutional neural networks (CNN), and (3) integrating predictions of all patches to form the final diagnosis with a rule-based system. To be specific, we fine-tune the InceptionV3 model for thyroid patch classification by replacing the last fully connected layer with three outputs representing the patch's probabilities of being benign, uncertain, or malignant. Moreover, we design a rule-based protocol to integrate patches’ predictions to form the final diagnosis, which provides interpretability for the proposed system. On 259 testing slides, the system correctly predicts 95. 3% (61/64) of benign nodules and 96. 7% (148/153) of malignant nodules, and classify 16. 2% (42/259) slides as uncertain, including 19 benign and 16 malignant slides, which are a sufficiently small number to be manually examined by pathologists or fully processed through permanent sections. Besides, the system allows the localization of suspicious regions along with the diagnosis. A typical whole slide image, with 80, 000 × 60, 000 pixels, can be diagnosed within 1 min, thus satisfying the time requirement for intraoperative diagnosis. To the best of our knowledge, this is the first study to apply deep learning to diagnose thyroid nodules from intraoperative frozen sections. The code is released at https: //github. com/PingjunChen/ThyroidRule.

TCS Journal 2019 Journal Article

Maximal sensitivity of Boolean nested canalizing functions

Yuan Li
John O. Adeyeye

Boolean nested canalizing functions (NCF) have important applications in molecular regulatory networks, engineering and computer science. In the literature, there are two sensitivities to measure the complexity of a Boolean function. One is average sensitivity, the other one is maximal sensitivity. We follow the tradition and omit the word “maximal”. In other words, in this paper, sensitivity is always maximal sensitivity. Using the past work of the authors and their coauthors on a characterization of NCF, we obtain the formula of the sensitivity of any NCF. We find that the sensitivity of any NCF is between ⌈ n + 2 2 ⌉ and n. Both lower and upper bounds are tight. We prove that the block sensitivity, hence the l-block sensitivity, is the same as the sensitivity for NCF. It is well known that monotone Boolean functions (MBF) also have this property. We characterize all functions which are both monotone and nested canalizing (MNCF). The closed formula of the cardinality of the set of MNCFs is also provided.

NeurIPS Conference 2018 Conference Paper

Hybrid Retrieval-Generation Reinforced Agent for Medical Image Report Generation

Yuan Li
Xiaodan Liang
Zhiting Hu
Eric Xing

Generating long and coherent reports to describe medical images poses challenges to bridging visual patterns with informative human linguistic descriptions. We propose a novel Hybrid Retrieval-Generation Reinforced Agent (HRGR-Agent) which reconciles traditional retrieval-based approaches populated with human prior knowledge, with modern learning-based approaches to achieve structured, robust, and diverse report generation. HRGR-Agent employs a hierarchical decision-making procedure. For each sentence, a high-level retrieval policy module chooses to either retrieve a template sentence from an off-the-shelf template database, or invoke a low-level generation module to generate a new sentence. HRGR-Agent is updated via reinforcement learning, guided by sentence-level and word-level rewards. Experiments show that our approach achieves the state-of-the-art results on two medical report datasets, generating well-balanced structured sentences with robust coverage of heterogeneous medical report contents. In addition, our model achieves the highest detection precision of medical abnormality terminologies, and improved human evaluation performance.

TCS Journal 2017 Journal Article

Multistate nested canalizing functions and their networks

Claus Kadelka
Yuan Li
Jack Kuipers
John O. Adeyeye
Reinhard Laubenbacher

This paper provides a collection of mathematical and computational tools for the study of robustness in nonlinear gene regulatory networks, represented by time- and state-discrete dynamical systems taking on multiple states. The focus is on networks governed by nested canalizing functions (NCFs), first introduced in the Boolean context by S. Kauffman. After giving a general definition of NCFs we analyze the class of such functions. We derive a formula for the normalized average c-sensitivities of multistate NCFs, which enables the calculation of the Derrida plot, a popular measure of network stability. We also provide a unique canonical parametrized polynomial form of NCFs. This form has several consequences. We can easily generate NCFs for varying parameter choices, and derive a closed form formula for the number of such functions in a given number of variables, as well as an asymptotic formula. Finally, we compute the number of equivalence classes of NCFs under permutation of variables. Together, the results of the paper represent a useful mathematical framework for the study of NCFs and their dynamic networks.

YNIMG Journal 2016 Journal Article

Decoupled temporal variability and signal synchronization of spontaneous brain activity in loss of consciousness: An fMRI study in anesthesia

Zirui Huang
Jun Zhang
Jinsong Wu
Pengmin Qin
Xuehai Wu
Zhiyao Wang
Rui Dai
Yuan Li

Two aspects of the low frequency fluctuations of spontaneous brain activity have been proposed which reflect the complex and dynamic features of resting-state activity, namely temporal variability and signal synchronization. The relationship between them, especially its role in consciousness, nevertheless remains unclear. Our study examined the temporal variability and signal synchronization of spontaneous brain activity, as well as their relationship during loss of consciousness. We applied an intra-subject design of resting-state functional magnetic resonance imaging (rs-fMRI) in two conditions: during wakefulness, and under anesthesia with clinical unconsciousness. In addition, an independent group of patients with disorders of consciousness (DOC) was included in order to test the reliability of our findings. We observed a global reduction in the temporal variability, local and distant brain signal synchronization for subjects during anesthesia. Importantly, we found a link between temporal variability and both local and distant signal synchronizations during wakefulness: the higher the degree of temporal variability, the higher its intra-regional homogeneity and inter-regional functional connectivity. In contrast, this link was broken down under anesthesia, implying a decoupling between temporal variability and signal synchronization; this decoupling was reproduced in patients with DOC. Our results suggest that there exist some as yet unclear physiological mechanisms of consciousness which “couple” the two mathematically independent measures, temporal variability and signal synchronization of spontaneous brain activity. Our findings not only extend our current knowledge of the neural correlates of anesthetic-induced unconsciousness, but have implications for both computational neural modeling and clinical practice, such as in the diagnosis of loss of consciousness in patients with DOC.

ICRA Conference 2016 Conference Paper

Speed evaluation of a freely swimming robotic fish with an artificial lateral line

Wei Wang 0078
Yuan Li
Xingxing Zhang
Chen Wang 0005
Shiming Chen
Guangming Xie

Artificial lateral line has been drawing an increasing attention recently for its potential applications in robotics. Experiments are usually conducted with a bioinspired robot in a controlled environment, where the sensing platform is held stationary or slowly driven with a simple linear motion. In this paper, we conduct a more practical and challenging study where the robot uses artificial lateral line to evaluate its linear velocity while freely swimming. We use onboard artificial lateral line to measure the pressure profiles over the surface of a robotic fish and employ onboard IMU (inertial measurement unit) to record the motion kinematics of the robot while freely swimming at various speeds. We find that 1) pressure changes are greatest on the head of the robot; 2) pressures increase along with the swimming speed and the oscillation amplitude of angular velocity of the robot. Therefore, we propose a nonlinear prediction model which incorporates distributed pressure and angular velocity to estimate the speed of the robot. Online speed evaluation experiment demonstrates the effectiveness and the accuracy of the proposed model.

IROS Conference 2015 Conference Paper

A haptic shared control algorithm for flexible human assistance to semi-autonomous robots

Ningbo Yu
Kui Wang
Yuan Li
Chang Xu
Jingtai Liu

Autonomous as well as teleoperated robots find wide applications in various environments. Their capability to accomplish complex and dynamic operations can be significantly improved by fusing human intelligence with autonomous algorithms. In this paper, we propose a haptic shared control algorithm to provide flexible human assistance for semi-autonomous mobile robots. Through the admittance and impedance models, the haptic shared controller smoothly puts together human operator inputs with robot autonomy. Further, the level of autonomy is fully determined by the operator with the grasp motion. A decomposed design has been taken for the autonomous controller of the mobile robot. The algorithm was implemented on the haptic interface omega. 7 together with a QBot mobile robot, and its feasibility and efficacy have been validated by experiments.

ICRA Conference 2014 Conference Paper

Feedback stabilizer-based trajectory planning of mobile robots with kinematic constraints

Xuebo Zhang 0003
Yuan Li
Yongchun Fang
Baoquan Li

Many theoretic approaches for feedback stabilization control of nonholonomic mobile robots cannot be directly applied to practical robots since various kinematic constraints such as the velocity and acceleration limits are not considered in existing methods. To deal with this issue, we aim to propose a generic approach which first uses an (arbitrary) feedback stabilizer to generate the `path' and then rebuilt the corresponding `trajectory' along this `path' to meet various kinematic constraints, which ultimately gives a practical satisfactory solution for local trajectory planning. Specifically, a general framework is established to transform feedback stabilizers into a feasible and highly efficient trajectory planner by using path generation and optimal velocity planning techniques, considering both kinematic and differential constraints. Extensive simulation results are provided to validate the proposed approach.

FOCS Conference 2014 Conference Paper

On the AC0 Complexity of Subgraph Isomorphism

Yuan Li
Alexander A. Razborov
Benjamin Rossman

Let P be a fixed graph (hereafter called a “pattern”), and let SUBGRAPH(P) denote the problem of deciding whether a given graph G contains a subgraph isomorphic to P. We are interested in AC0-complexity of this problem, determined by the smallest possible exponent C(P) for which SUBGRAPH(P) possesses bounded-depth circuits of size n C(P)+o(1). Motivated by the previous research in the area, we also consider its “colorful” version SUBGRAPHcol(P) in which the target graph G is V(P)colored, and the average-case version SUBGRAP Have (P) under the distribution G(n, n -θ (P)), where θ(P) is the threshold exponent of P. Defining C col (P) and Cave(P) analogously to C(P), our main contributions can be summarized as follows. (1) C col (P) coincides with the tree-width of the pattern P within a logarithmic factor. This shows that the previously known upper bound by Alon, Yuster, Zwick [3] is almost tight. (2) We give a characterization of Cave(P) in purely combinatorial terms within a multiplicative factor of 2. This shows that the lower bound technique of Rossman [21] is essentially tight, for any pattern P whatsoever. (3) We prove that if Q is a minor of P then SUBGRAPH col (Q) is reducible to SUBGRAPH col (P) via a linear-size monotone projection. At the same time, we show that there is no monotone projection whatsoever that reduces SUBGRAPH(M 3 ) to SUBGRAPH(P 3 + M 2 ) (P 3 is a path on 3 vertices, Mk is a matching with k edges, and “+” stands for the disjoint union). This result strongly suggests that the colorful version of the subgraph isomorphism problem is much better structured and well-behaved than the standard (worstcase, uncolored) one.

TCS Journal 2013 Journal Article

Boolean nested canalizing functions: A comprehensive analysis

Yuan Li
John O. Adeyeye
David Murrugarra
Boris Aguilar
Reinhard Laubenbacher

Boolean network models of molecular regulatory networks have been used successfully in computational systems biology. The Boolean functions that appear in published models tend to have special properties, in particular the property of being nested canalizing, a concept inspired by the concept of canalization in evolutionary biology. It has been shown that networks comprised of nested canalizing functions have dynamic properties that make them suitable for modeling molecular regulatory networks, namely a small number of (large) attractors, as well as relatively short limit cycles. This paper contains a detailed analysis of this class of functions, based on a novel normal form as polynomial functions over the Boolean field. The concept of layer is introduced that stratifies variables into different classes depending on their level of dominance. Using this layer concept a closed form formula is derived for the number of nested canalizing functions with a given number of variables. Additional metrics considered include Hamming weight, the activity number of any variable, and the average sensitivity of the function. It is also shown that the average sensitivity of any nested canalizing function is between 0 and 2. This provides a rationale for why nested canalizing functions are stable, since a random Boolean function in n variables has average sensitivity n 2. The paper also contains experimental evidence that the layer number is an important factor in network stability.

YNIMG Journal 2012 Journal Article

Reduced caudate volume and enhanced striatal-DMN integration in chess experts

Xujun Duan
Sheng He
Wei Liao
Dongmei Liang
Lihua Qiu
Luqing Wei
Yuan Li
Chengyi Liu

The superior capability of chess experts largely depends on quick automatic processing skills which are considered to be mediated by the caudate nucleus. We asked whether continued practice or rehearsal of the skill over a long period of time can lead to structural changes in this region. We found that, comparing to novice controls, grandmaster and master level Chinese chess players (GM/Ms), who had a mean period of over 10years of tournament and training practice, exhibited significant smaller gray-matter volume in the bilateral caudate nuclei. When these regions were used as seeds in functional connectivity analysis in resting-state fMRI, significantly enhanced integration was found in GM/Ms between the caudate and the default mode network (DMN), a constellation of brain areas important for goal-directed cognitive performance and theory of mind. These findings demonstrate the structural changes in the caudate nucleus in response to its extensive engagement in chess problem solving, and its enhanced functional integration with widely distributed circuitry to better support high-level cognitive control of behavior.