Arrow Research search

Author name cluster

Fei Liu

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.

25 papers
2 author rows

Possible papers

25

EAAI Journal 2026 Journal Article

Automatic stem phenotyping in soybean using keypoint detection

  • Fei Liu
  • Qiong Wu
  • Zhongzhi Han
  • Longgang Zhao
  • Shanchen Pang
  • Shudong Wang

Soybean breeding critically relies on stem phenotypes, as they directly impact yield and lodging resistance. Traditional measurement methods are labor-intensive, prone to human error, and often require destructive sampling. Although artificial intelligence (AI) has emerged as a transformative alternative, existing studies on soybean stem phenotyping remain limited and imprecise. An AI implementation integrating keypoint detection and localization provides a promising solution. This study proposes Soybean-pose, a novel approach that models soybean plants as structural “bodily forms” via keypoint detection. By integrating a semi-supervised iterative self-training paradigm with a hybrid Convolutional Neural Network-Swin Vision Transformer (CNN-SViT) architecture, Soybean-pose achieves high-precision detection of soybean stem nodes via limited labeled data and pseudo-label iterative optimization strategies, and integrates phenotypic quantification algorithms to accomplish automated parsing of stem-related phenotypes. To support this research, the Soybean Stem Keypoint (SSK) dataset is constructed and publicly released. Soybean-pose achieves an average precision at 50 % intersection-over-union (AP50) of 91. 8 % on the validation set and 93. 2 % on the test-dev set. The Pearson correlation coefficients (R) for pitch number, internode length, and main stem length are 0. 986, 0. 989, and 0. 978, respectively. This AI application enables accurate measurement of soybean stem phenotypes, reduces labor costs, and minimizes measurement errors, demonstrating its potential to accelerate breeding processes.

Details DOI

AAAI Conference 2026 Conference Paper

Debate over Mixed-knowledge: A Robust Multi-Agent Reasoning Framework for Incomplete Knowledge Graph Question Answering

  • Jilong Liu
  • Pengyang Shao
  • Wei Qin
  • Fei Liu
  • Yonghui Yang
  • Richang Hong

Knowledge Graph Question Answering (KGQA) aims to improve factual accuracy by leveraging structured knowledge. However, real-world Knowledge Graphs (KGs) are often incomplete, leading to the problem of Incomplete KGQA (IKGQA). A common solution is to incorporate external data to fill knowledge gaps, but existing methods lack the capacity to adaptively and contextually fuse multiple sources, failing to fully exploit their complementary strengths. To this end, we propose Debate over Mixed-knowledge (DoM), a novel framework that enables dynamic integration of structured and unstructured knowledge for IKGQA. Built upon the Multi-Agent Debate paradigm, DoM assigns specialized agents to perform inference over knowledge graphs and external texts separately, and coordinates their outputs through iterative interaction. It decomposes the input question into sub-questions, retrieves evidence via dual agents (KG and Retrieval-Augmented Generation, RAG), and employs a judge agent to evaluate and aggregate intermediate answers. This collaboration exploits knowledge complementarity and enhances robustness to KG incompleteness. In addition, existing IKGQA datasets simulate incompleteness by randomly removing triples, failing to capture the irregular and unpredictable nature of real-world knowledge incompleteness. To address this, we introduce a new dataset, Incomplete Knowledge Graph WebQuestions, constructed by leveraging real-world knowledge updates. These updates reflect knowledge beyond the static scope of KGs, yielding a more realistic and challenging benchmark. Through extensive experiments, we show that DoM consistently outperforms state-of-the-art baselines.

PDF Details DOI

AAAI Conference 2026 Conference Paper

EoH-S: Evolution of Heuristic Set Using LLMs for Automated Heuristic Design

  • Fei Liu
  • Yilu Liu
  • Qingfu Zhang
  • Tong Xialiang
  • Mingxuan Yuan

Automated Heuristic Design (AHD) using Large Language Models (LLMs) has achieved notable success in the past two years. Despite the effectiveness of existing approaches, they only design a single heuristic to serve all problem instances, often inducing poor generalization across different distributions or sizes. To address this issue, we propose Automated Heuristic Set Design (AHSD), a new methodology for LLM-driven AHD. The aim of AHSD is to automatically design a small-sized complementary heuristic set to serve diverse problem instances, such that each problem instance could be optimized by at least one heuristic in this set. We propose Evolution of Heuristic Set (EoH-S), which realizes AHSD using an evolutionary search framework. It incorporates a complementary population management and a memetic search to design a set of heuristics. Extensive experiments on online bin packing, traveling salesman problem, and capacitated vehicle routing problem show that EoH-S consistently outperforms existing AHD methods. The resulting heuristics exhibit complementary performance across instances of varying sizes and distributions.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Destroy and Repair Using Hyper-Graphs for Routing

  • Ke Li
  • Fei Liu
  • Zhenkun Wang
  • Qingfu Zhang

Recent advancements in Neural Combinatorial Optimization (NCO) have shown promise in solving routing problems like the Traveling Salesman Problem (TSP) and Capacitated Vehicle Routing Problem (CVRP) without handcrafted designs. Research in this domain has explored two primary categories of methods: iterative and non-iterative. While non-iterative methods struggle to generate near-optimal solutions directly, iterative methods simplify the task by learning local search steps. However, existing iterative methods are often limited by restricted neighborhood searches, leading to suboptimal results. To address this limitation, we propose a novel approach that extends the search to larger neighborhoods by learning a destroy-and-repair strategy. Specifically, we introduce a Destroy-and-Repair framework based on Hyper-Graphs (DRHG). This framework reduces consecutive intact edges to hyper-edges, allowing the model to pay more attention to the destroyed part and decrease the complexity of encoding all nodes. Experiments demonstrate that DRHG achieves state-of-the-art performance on TSP with up to 10,000 nodes and shows strong generalization to real-world TSPLib and CVRPLib problems.

PDF Details DOI

EAAI Journal 2025 Journal Article

Efficient intelligent quality detection of pistachios using multi-view deep learning

  • Hongfei Zhu
  • Huayu Fu
  • Cong Wang
  • Zhenlu Hua
  • Xingyu Liu
  • Weiming Shi
  • Ziyan Zong
  • Yanshen Zhao

The market value of pistachios is primarily determined by their external quality. In this study, we propose a novel method for the rapid detection of pistachio external quality. Multi-view imaging was employed to capture comprehensive external features, addressing the limitations of incomplete information in single-view systems. We utilized a convolutional neural network, specifically the Residual Network with 18 layers, as the backbone model for detecting pistachio quality. The model was pruned using first-order Taylor expansion to reduce the number of filters and thus the model's complexity. Under three-view imaging, the pruned network achieved an accuracy of 99. 56%, with a per-image detection time of 0. 0880 s. With two-view imaging, the accuracy was 99. 39%, reducing detection time to 0. 0667 s per image. The pruning process reduced the number of model parameters by 96. 02% compared to the original network. Finally, the optimized models were integrated into two types of pistachio sorting machines for real-time detection of open and closed pistachios. This method delivers high detection accuracy, faster processing speeds, and significantly reduced model complexity.

Details DOI

NeurIPS Conference 2025 Conference Paper

Learning to Insert for Constructive Neural Vehicle Routing Solver

  • Fu Luo
  • Xi Lin
  • Mengyuan Zhong
  • Fei Liu
  • Zhenkun Wang
  • Jianyong Sun
  • Qingfu Zhang

Neural Combinatorial Optimisation (NCO) is a promising learning-based approach for solving Vehicle Routing Problems (VRPs) without extensive manual design. While existing constructive NCO methods typically follow an appending-based paradigm that sequentially adds unvisited nodes to partial solutions, this rigid approach often leads to suboptimal results. To overcome this limitation, we explore the idea of the insertion-based paradigm and propose Learning to Construct with Insertion-based Paradigm (L2C-Insert), a novel learning-based method for constructive NCO. Unlike traditional approaches, L2C-Insert builds solutions by strategically inserting unvisited nodes at any valid position in the current partial solution, which can significantly enhance the flexibility and solution quality. The proposed framework introduces three key components: a novel model architecture for precise insertion position prediction, an efficient training scheme for model optimization, and an advanced inference technique that fully exploits the insertion paradigm's flexibility. Extensive experiments on both synthetic and real-world instances of the Travelling Salesman Problem (TSP) and Capacitated Vehicle Routing Problem (CVRP) demonstrate that L2C-Insert consistently achieves superior performance across various problem sizes. The code is available at https: //github. com/CIAM-Group/L2C_Insert.

PDF Details

JMLR Journal 2025 Journal Article

Lexicographic Lipschitz Bandits: New Algorithms and a Lower Bound

  • Bo Xue
  • Ji Cheng
  • Fei Liu
  • Yimu Wang
  • Lijun Zhang
  • Qingfu Zhang

This paper studies a multiobjective bandit problem under lexicographic ordering, wherein the learner aims to maximize $m$ objectives, each with different levels of importance. First, we introduce the local trade-off, $\lambda_*$, which depicts the trade-off between different objectives. For the case when an upper bound of $\lambda_*$ is known, i.e., $\lambda\geq\lambda_*$, we develop an algorithm that achieves a general regret bound of $\widetilde{O}(\Lambda^i(\lambda)T^{(d_z^i+1)/(d_z^i+2)})$ for the $i$-th objective, where $i\in\{1,2,\ldots,m\}$, $\Lambda^i(\lambda)=1+\lambda+\cdots+\lambda^{i-1}$, $d_z^i$ is the zooming dimension for the $i$-th objective, and $T$ is the time horizon. Next, we provide a matching lower bound for the lexicographic Lipschitz bandit problem, proving that our algorithm is optimal in terms of $\lambda_*$ and $T$. Finally, for the case where $m=2$, we remove the dependence on the knowledge about $\lambda_*$, albeit at the cost of increasing the regret bound to $\widetilde{O}(\Lambda^i(\lambda_*)T^{(3d_z^i+4)/(3d_z^i+6)})$, which remains optimal in terms of $\lambda_*$. Compared to existing work on lexicographic multi-armed bandits, our approach improves the current regret bound of $\widetilde{O}(T^{2/3})$ and extends the number of arms to infinity. Numerical experiments confirm the effectiveness of our algorithms. [abs] [ pdf ][ bib ] &copy JMLR 2025. ( edit, beta )

PDF Details

IJCAI Conference 2025 Conference Paper

LLM-enhanced Score Function Evolution for Causal Structure Learning

  • Zidong Wang
  • Fei Liu
  • Qi Feng
  • Qingfu Zhang
  • Xiaoguang Gao

Causal structure learning (CSL) plays a pivotal role in causality and is often formulated as an optimization problem within score-and-search methods. Under the assumption of an infinite dataset and a predefined distribution, several well-established and consistent score functions have been shown to be both optimal and reliable for identifying ground-truth causal graphs. However, in practice, these idealized assumptions are often infeasible, which can result in CSL algorithms learning suboptimal structures. In this paper, we introduce L-SFE, a framework designed to automatically discover effective score functions by exploring the "score function space". L-SFE addresses this task from a bi-level optimization perspective. First, it leverages a Large Language Model (LLM) to interpret the characteristics of score functions and generate the corresponding code implementations. Next, L-SFE employs evolutionary algorithms along with carefully designed operators, to search for solutions with higher fitness. Additionally, we take the BIC as example and prove the consistency of the generated score functions. Experimental evaluations, conducted on discrete, continuous, and real datasets, demonstrate the high stability, generality and effectiveness of L-SFE.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Multi-Objective Evolution of Heuristic Using Large Language Model

  • Shunyu Yao
  • Fei Liu
  • Xi Lin
  • Zhichao Lu
  • Zhenkun Wang
  • Qingfu Zhang

Heuristics are commonly used to tackle various search and optimization problems. Design heuristics usually require tedious manual crafting with domain knowledge. Recent works have incorporated Large Language Models (LLMs) into automatic heuristic search, leveraging their powerful language and coding capacity. However, existing research focuses on the optimal performance on the target problem as the sole objective, neglecting other criteria such as efficiency and scalability, which are vital in practice. To tackle this challenge, we propose to model the heuristic search as a multi-objective optimization problem and consider introducing additional practical criteria beyond optimal performance. Due to the complexity of the search space, conventional multi-objective optimization methods struggle to effectively handle LLM-based multi-objective heuristic search. We propose the first LLM-based multi-objective heuristic search framework, Multi-objective Evolution of Heuristic (MEoH), which integrates LLMs in a zero-shot manner to generate a non-dominated set of heuristics to meet multiple design criteria. We design a new dominance-dissimilarity mechanism for effective population management and selection, which incorporates both code dissimilarity in the search space and dominance in the objective space. MEoH is demonstrated in two well-known combinatorial optimization problems: the online Bin Packing Problem (BPP) and the Traveling Salesman Problem (TSP). The results indicate that a variety of elite heuristics are automatically generated in a single run, offering more trade-off options than the existing methods. It successfully achieves competitive or superior performance while improving efficiency up to 10 times. Moreover, we also observe that the multi-objective search introduces novel insights into heuristic design and leads to the discovery of diverse heuristics.

PDF Details DOI

EAAI Journal 2024 Journal Article

A hybrid deep learning framework for conflict prediction of diverse merge scenarios at roundabouts

  • Ye Li
  • Chang Ge
  • Lu Xing
  • Chen Yuan
  • Fei Liu
  • Jieling Jin

The unique traffic situation at roundabouts causes complex interactions between merging vehicles, thereby increasing the likelihood of conflicts. Reliable prediction of conflict risk contributes to active safety improvement, but few studies have investigated the merge risk of roundabouts at a microscopic level. In light of this, this study develops a hybrid deep learning framework for predicting potential conflict risks in complex merging scenarios at roundabouts. Specifically, a roundabout coordinate system is devised to define vehicle characteristics based on trajectory data. Then, an improved 2D-TTC (time-to-collision) indicator is employed to identify two-dimensional merge conflicts. Since the surrounding vehicles may change as vehicles merge into a roundabout, this study analyzes several merging scenarios involving different vehicle groups and conflict durations in order to provide a comprehensive understanding of the conflict mechanism. For these scenarios, a hybrid model consisting of a convolutional neural network (CNN) and a long short-term memory network (LSTM) integrated with the convolutional block attention module (CBAM) is utilized to identify key features. The superiority of the proposed prediction method is demonstrated in comparisons with benchmark models. Results showed that segmental predictions were more accurate than overall predictions in terms of conflict duration. Furthermore, it is possible that a specific vehicle group has a decisive effect on the merging conflict risk, as indicated by the fact that information from multiple vehicle groups does not significantly improve the prediction performance. Another finding is that the driving state of vehicles merging at the roundabout varies considerably, but rarely with consecutive or multiple changes. The study provides novel insights into roundabout conflict prediction, which could serve as a tool for enhancing safety management involving complex traffic scenarios.

Details DOI

EAAI Journal 2024 Journal Article

Bearing fault diagnosis based on high-confidence pseudo-labels and dual-view multi-adversarial sparse joint attention network under variable working conditions

  • Cailu Pan
  • Zhiwu Shang
  • Wanxiang Li
  • Fei Liu
  • Lutai Tang

Domain adaptive technology has been extensively employed in the research of bearing fault diagnosis under cross-different working conditions. Nevertheless, most studies ignore the two domains' conditional distribution alignment and domain-invariant features' discriminative properties. Hence, this paper proposes a dual-view multi-adversarial network combined with improved pseudo-label learning (DMNIPL) to address the cross-different working fault diagnosis of bearings when the target domain sample labels are unavailable. Specifically, the proposed model uses pseudo-label learning to generate labels for unlabeled target domain samples and achieves conditional distribution alignment between the source and target domains through adversarial training. The adversarial training process is between the local-domain discriminator module involving multiple domain discriminators and the feature extractor. Since pseudo-labels with low-confidence interfere with model training, this work introduces an adaptive dynamic threshold to filter pseudo-labels. Additionally, two independent health state classifiers are designed to classify the same fault sample, enhance the model's learning ability on discriminable features. Furthermore, we combine spatial and channel attention, use sparse operations, and propose the sparse joint attention (SJA) scheme to enhance the model's ability to capture fault features. Finally, the effectiveness and advancement of the proposed method are verified using two datasets. Experimental results show that the accuracy of the proposed method can achieve more than 95% in 12 diagnostic tasks, which is higher than other methods. This research work provides a reliable fault diagnosis method to detect the health status of rotating machinery equipment.

Details DOI

YNIMG Journal 2024 Journal Article

Light3DHS: A lightweight 3D hippocampus segmentation method using multiscale convolution attention and vision transformer

  • Zhiyong Xiao
  • Yuhong Zhang
  • Zhaohong Deng
  • Fei Liu

The morphological analysis and volume measurement of the hippocampus are crucial to the study of many brain diseases. Therefore, an accurate hippocampal segmentation method is beneficial for the development of clinical research in brain diseases. U-Net and its variants have become prevalent in hippocampus segmentation of Magnetic Resonance Imaging (MRI) due to their effectiveness, and the architecture based on Transformer has also received some attention. However, some existing methods focus too much on the shape and volume of the hippocampus rather than its spatial information, and the extracted information is independent of each other, ignoring the correlation between local and global features. In addition, many methods cannot be effectively applied to practical medical image segmentation due to many parameters and high computational complexity. To this end, we combined the advantages of CNNs and ViTs (Vision Transformer) and proposed a simple and lightweight model: Light3DHS for the segmentation of the 3D hippocampus. In order to obtain richer local contextual features, the encoder first utilizes a multi-scale convolutional attention module (MCA) to learn the spatial information of the hippocampus. Considering the importance of local features and global semantics for 3D segmentation, we used a lightweight ViT to learn high-level features of scale invariance and further fuse local-to-global representation. To evaluate the effectiveness of encoder feature representation, we designed three decoders of different complexity to generate segmentation maps. Experiments on three common hippocampal datasets demonstrate that the network achieves more accurate hippocampus segmentation with fewer parameters. Light3DHS performs better than other state-of-the-art algorithms.

Details DOI

AAAI Conference 2024 Conference Paper

Multiobjective Lipschitz Bandits under Lexicographic Ordering

  • Bo Xue
  • Ji Cheng
  • Fei Liu
  • Yimu Wang
  • Qingfu Zhang

This paper studies the multiobjective bandit problem under lexicographic ordering, wherein the learner aims to simultaneously maximize? objectives hierarchically. The only existing algorithm for this problem considers the multi-armed bandit model, and its regret bound is O((KT)^(2/3)) under a metric called priority-based regret. However, this bound is suboptimal, as the lower bound for single objective multi-armed bandits is Omega(KlogT). Moreover, this bound becomes vacuous when the arm number K is infinite. To address these limitations, we investigate the multiobjective Lipschitz bandit model, which allows for an infinite arm set. Utilizing a newly designed multi-stage decision-making strategy, we develop an improved algorithm that achieves a general regret bound of O(T^((d_z^i+1)/(d_z^i+2))) for the i-th objective, where d_z^i is the zooming dimension for the i-th objective, with i in {1,2,...,m}. This bound matches the lower bound of the single objective Lipschitz bandit problem in terms of T, indicating that our algorithm is almost optimal. Numerical experiments confirm the effectiveness of our algorithm.

PDF Details DOI

IJCAI Conference 2024 Conference Paper

Prompt Learning for Generalized Vehicle Routing

  • Fei Liu
  • Xi Lin
  • Weiduo Liao
  • Zhenkun Wang
  • Qingfu Zhang
  • Xialiang Tong
  • Mingxuan Yuan

Neural combinatorial optimization (NCO) is a promising learning-based approach to solving various vehicle routing problems without much manual algorithm design. However, the current NCO methods mainly focus on the in-distribution performance, while the real-world problem instances usually come from different distributions. A costly fine-tuning approach or generalized model retraining from scratch could be needed to tackle the out-of-distribution instances. Unlike the existing methods, this work investigates an efficient prompt learning approach in NCO for cross-distribution adaptation. To be concrete, we propose a novel prompt learning method to facilitate fast zero-shot adaptation of a pre-trained model to solve routing problem instances from different distributions. The proposed model learns a set of prompts among various distributions and then selects the best-matched one to prompt a pre-trained attention model for each problem instance. Extensive experiments show that the proposed prompt learning approach facilitates the fast adaptation of pre-trained routing models. It also outperforms existing generalized models on both in-distribution prediction and zero-shot generalization to a diverse set of new tasks. Our code implementation is available online at https: //github. com/FeiLiu36/PromptVRP.

PDF Details DOI

EAAI Journal 2024 Journal Article

The integration of knowledge graph convolution network with denoising autoencoder

  • Gurinder Kaur
  • Fei Liu
  • Yi-Ping Phoebe Chen

The knowledge graph convolution network (KGCN) is a recommendation model that provides a set of top recommendations based on knowledge graph developed between users, items, and their attributes. In this study, we integrate the KGCN model with denoising autoencoder (DAE) to improve its recommendation performance. A trained DAE is used to sample K-dimensional latent representation for each user, which then transforms that representation to generate a probability distribution over items. The relationship between acquired latent representation and the meta features is modelled using multivariate multiple regression (MMR) kernel. As a result, without the need for new configuration assessments, performance estimation of new data is pursued directly through MMR and the decoder of DAE. Empirically, we demonstrate that on real-world datasets, the proposed method substantially outperforms other state-of-the-art baselines. Movie-Lens 100K (ML-100K) and Movie-Lens 1M (ML-1M), two common MovieLens datasets, are used to verify the accuracy of the proposed approach. The results from experiments show significant improvement of 41. 17% when the proposed method is applied on KGCN model. The proposed framework outperforms other state-of-the-art frameworks on Recall@K and normalized discounted cumulative gain (NDCG@K) metrics by achieving higher scores for Recall@5, Recall@10, NDCG@1, and NDCG@10.

Details DOI

ICML Conference 2024 Conference Paper

Unsupervised Domain Adaptation for Anatomical Structure Detection in Ultrasound Images

  • Bin Pu
  • Xingguo Lv
  • Jiewen Yang
  • Guannan He
  • Xingbo Dong
  • Yiqun Lin
  • Shengli Li 0001
  • Tan Ying

Models trained on ultrasound images from one institution typically experience a decline in effectiveness when transferred directly to other institutions. Moreover, unlike natural images, dense and overlapped structures exist in fetus ultrasound images, making the detection of structures more challenging. Thus, to tackle this problem, we propose a new Unsupervised Domain Adaptation (UDA) method named ToMo-UDA for fetus structure detection, which consists of the Topology Knowledge Transfer (TKT) and the Morphology Knowledge Transfer (MKT) module. The TKT leverages prior knowledge of the medical anatomy of fetal as topological information, reconstructing and aligning anatomy features across source and target domains. Then, the MKT formulates a more consistent and independent morphological representation for each substructure of an organ. To evaluate the proposed ToMo-UDA for ultrasound fetal anatomical structure detection, we introduce FUSH$^2$, a new F etal U ltra S ound benchmark, comprises H eart and H ead images collected from Two health centers, with 16 annotated regions. Our experiments show that utilizing topological and morphological anatomy information in ToMo-UDA can greatly improve organ structure detection. This expands the potential for structure detection tasks in medical image analysis.

Details

NeurIPS Conference 2023 Conference Paper

Disentangling Cognitive Diagnosis with Limited Exercise Labels

  • Xiangzhi Chen
  • Le Wu
  • Fei Liu
  • Lei Chen
  • Kun Zhang
  • Richang Hong
  • Meng Wang

Cognitive diagnosis is an important task in intelligence education, which aims at measuring students’ proficiency in specific knowledge concepts. Given a fully labeled exercise-concept matrix, most existing models focused on mining students' response records for cognitive diagnosis. Despite their success, due to the huge cost of labeling exercises, a more practical scenario is that limited exercises are labeled with concepts. Performing cognitive diagnosis with limited exercise labels is under-explored and remains pretty much open. In this paper, we propose Disentanglement based Cognitive Diagnosis (DCD) to address the challenges of limited exercise labels. Specifically, we utilize students' response records to model student proficiency, exercise difficulty and exercise label distribution. Then, we introduce two novel modules - group-based disentanglement and limited-labeled alignment modules - to disentangle the factors relevant to concepts and align them with real limited labels. Particularly, we introduce the tree-like structure of concepts with negligible cost for group-based disentangling, as concepts of different levels exhibit different independence relationships. Extensive experiments on widely used benchmarks demonstrate the superiority of our proposed model.

PDF Details

EAAI Journal 2023 Journal Article

Integrated learning self-triggered control for model-free continuous-time systems with convergence guarantees

  • Haiying Wan
  • Hamid Reza Karimi
  • Xiaoli Luan
  • Shuping He
  • Fei Liu

This paper presents an integrated self-triggered control strategy with convergence guarantees for model-free continuous-time systems using reinforcement learning. To consider the control cost and triggering consumption in the self-triggered scheme simultaneously, an integrated cost function is proposed. With this integrated cost function, the trade-off between the triggering occupation and control performance could be adjusted according to different requirements. Then, the actor-critic framework of reinforcement learning is employed to learn the control inputs and triggering intervals by minimizing the corresponding integrated cost function. Considering the divergent characteristics between the control inputs and triggering intervals, two different actors are utilized to learn the triggering strategy and control policy, respectively. Also, the convergence of the developed model-free self-triggered control learning algorithm is proved to ensure the limited learning duration of both the control policy and triggering strategy. The proposed framework can be used to design self-triggered controllers for a wide range of engineering systems with unknow dynamics, including control of aircraft, robots, chemical processes, and other automated systems. Finally, the effectiveness and superiorities of the proposed method are verified by an illustrative example.

Details DOI

NeurIPS Conference 2023 Conference Paper

Neural Combinatorial Optimization with Heavy Decoder: Toward Large Scale Generalization

  • Fu Luo
  • Xi Lin
  • Fei Liu
  • Qingfu Zhang
  • Zhenkun Wang

Neural combinatorial optimization (NCO) is a promising learning-based approach for solving challenging combinatorial optimization problems without specialized algorithm design by experts. However, most constructive NCO methods cannot solve problems with large-scale instance sizes, which significantly diminishes their usefulness for real-world applications. In this work, we propose a novel Light Encoder and Heavy Decoder (LEHD) model with a strong generalization ability to address this critical issue. The LEHD model can learn to dynamically capture the relationships between all available nodes of varying sizes, which is beneficial for model generalization to problems of various scales. Moreover, we develop a data-efficient training scheme and a flexible solution construction mechanism for the proposed LEHD model. By training on small-scale problem instances, the LEHD model can generate nearly optimal solutions for the Travelling Salesman Problem (TSP) and the Capacitated Vehicle Routing Problem (CVRP) with up to 1000 nodes, and also generalizes well to solve real-world TSPLib and CVRPLib problems. These results confirm our proposed LEHD model can significantly improve the state-of-the-art performance for constructive NCO.

PDF Details

TCS Journal 2021 Journal Article

Colouring fuzziness for systems biology

  • George Assaf
  • Monika Heiner
  • Fei Liu

Snoopy is a powerful modelling and simulation tool for various types of Petri nets, which have been applied to a wide range of biochemical reaction networks. We present an enhanced version of Snoopy, now supporting coloured and uncoloured stochastic, continuous and hybrid Petri Nets with fuzzy kinetic parameters. Colour helps to cope with modelling challenges imposed by larger and more complex networks. Fuzzy parameters are specifically useful when kinetic parameter values can not be precisely measured or estimated. By running fuzzy simulation we obtain output bands of the variables of interest induced by the effect of the fuzzy kinetic parameters. Simulation is always done on the uncoloured level. For this purpose, coloured fuzzy Petri nets are automatically unfolded to their corresponding uncoloured counterparts. Combining the power of fuzzy kinetic parameters with the modelling convenience of coloured Petri nets provides a new quality in user support with sophisticated modelling and analysis features.

Details DOI

JBHI Journal 2021 Journal Article

Joint Extraction of Retinal Vessels and Centerlines Based on Deep Semantics and Multi-Scaled Cross-Task Aggregation

  • Rui Xu
  • Tiantian Liu
  • Xinchen Ye
  • Fei Liu
  • Lin Lin
  • Liang Li
  • Satoshi Tanaka
  • Yen-Wei Chen

Retinal vessel segmentation and centerline extraction are crucial steps in building a computer-aided diagnosis system on retinal images. Previous works treat them as two isolated tasks, while ignoring their tight association. In this paper, we propose a deep semantics and multi-scaled cross-task aggregation network that takes advantage of the association to jointly improve their performances. Our network is featured by two sub-networks. The forepart is a deep semantics aggregation sub-network that aggregates strong semantic information to produce more powerful features for both tasks, and the tail is a multi-scaled cross-task aggregation sub-network that explores complementary information to refine the results. We evaluate the proposed method on three public databases, which are DRIVE, STARE and CHASE_DB1. Experimental results show that our method can not only simultaneously extract retinal vessels and their centerlines but also achieve the state-of-the-art performances on both tasks.

Details DOI

AAAI Conference 2020 Conference Paper

Controlling the Amount of Verbatim Copying in Abstractive Summarization

  • Kaiqiang Song
  • Bingqing Wang
  • Zhe Feng
  • Ren Liu
  • Fei Liu

An abstract must not change the meaning of the original text. A single most effective way to achieve that is to increase the amount of copying while still allowing for text abstraction. Human editors can usually exercise control over copying, resulting in summaries that are more extractive than abstractive, or vice versa. However, it remains poorly understood whether modern neural abstractive summarizers can provide the same flexibility, i. e. , learning from single reference summaries to generate multiple summary hypotheses with varying degrees of copying. In this paper, we present a neural summarization model that, by learning from single human abstracts, can produce a broad spectrum of summaries ranging from purely extractive to highly generative ones. We frame the task of summarization as language modeling and exploit alternative mechanisms to generate summary hypotheses. Our method allows for control over copying during both training and decoding stages of a neural summarization model. Through extensive experiments we illustrate the significance of our proposed method on controlling the amount of verbatim copying and achieve competitive results over strong baselines. Our analysis further reveals interesting and unobvious facts.

PDF Details

AAAI Conference 2020 Conference Paper

Joint Parsing and Generation for Abstractive Summarization

  • Kaiqiang Song
  • Logan Lebanoff
  • Qipeng Guo
  • Xipeng Qiu
  • Xiangyang Xue
  • Chen Li
  • Dong Yu
  • Fei Liu

Sentences produced by abstractive summarization systems can be ungrammatical and fail to preserve the original meanings, despite being locally fluent. In this paper we propose to remedy this problem by jointly generating a sentence and its syntactic dependency parse while performing abstraction. If generating a word can introduce an erroneous relation to the summary, the behavior must be discouraged. The proposed method thus holds promise for producing grammatical sentences and encouraging the summary to stay true-to-original. Our contributions of this work are twofold. First, we present a novel neural architecture for abstractive summarization that combines a sequential decoder with a tree-based decoder in a synchronized manner to generate a summary sentence and its syntactic parse. Secondly, we describe a novel human evaluation protocol to assess if, and to what extent, a summary remains true to its original meanings. We evaluate our method on a number of summarization datasets and demonstrate competitive results against strong baselines.

PDF Details

IJCAI Conference 2019 Conference Paper

Densely Connected Attention Flow for Visual Question Answering

  • Fei Liu
  • Jing Liu
  • Zhiwei Fang
  • Richang Hong
  • Hanqing Lu

Learning effective interactions between multi-modal features is at the heart of visual question answering (VQA). A common defect of the existing VQA approaches is that they only consider a very limited amount of interactions, which may be not enough to model latent complex image-question relations that are necessary for accurately answering questions. Therefore, in this paper, we propose a novel DCAF (Densely Connected Attention Flow) framework for modeling dense interactions. It densely connects all pairwise layers of the network via Attention Connectors, capturing fine-grained interplay between image and question across all hierarchical levels. The proposed Attention Connector efficiently connects the multi-modal features at any two layers with symmetric co-attention, and produces interaction-aware attention features. Experimental results on three publicly available datasets show that the proposed method achieves state-of-the-art performance.

PDF Details

JBHI Journal 2013 Journal Article

360° Fourier Transform Profilometry in Surface Reconstruction for Fluorescence Molecular Tomography

  • Bi'er Shi
  • Bin Zhang
  • Fei Liu
  • Jianwen Luo
  • Jing Bai

Fluorescence molecular tomography (FMT) is an emerging tool in the observation of diseases. A fast and accurate surface reconstruction of the experimental object is needed as a boundary constraint for FMT reconstruction. In this paper, an automatic, noncontact, and 3-D surface reconstruction method named 360° Fourier transform profilometry (FTP) is proposed to reconstruct 3-D surface profiles for FMT system. This method can reconstruct 360° integrated surface profiles utilizing the single-frame FTP at different angles. Results show that the relative mean error of the surface reconstruction of this method is less than 1. 4% in phantom experiments, and is no more than 2. 9% in mouse experiments in vivo. Compared with the Radon transform method, the proposed method reduces the computation time by more than 90% with a minimal error increase. At last, a combined 360° FTP/FMT experiment is conducted on a nude mouse. Not only can the 360° FTP system operate with the FMT system simultaneously, but it can also help to monitor the status of animals. Moreover, the 360° FTP system is independent of FMT system and can be performed to reconstruct the surface by itself.

Details DOI