Author name cluster

Shuai Han

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.

16 papers

2 author rows

AAAI Conference 2026 Conference Paper

CLUHCS:Dual-View Contrastive Learning Enabled Unsupervised Heterogeneous Community Search with Meta-Path Behavior Modeling

Xiaoqin Xie
Bin Zhao
Mingzhu Chang
Shuai Han
Wu Yang

Existing community search methods heavily rely on labeled data or predefined structures, thus fail to capture obscure and dynamic community boundaries in open-world heterogeneous networks, leading to poor adaptability. They also ignore modeling behavioral patterns, resulting in poor search performance. To solve the above issues, this work formally defines the unsupervised behavior-driven community search problem for heterogeneous graphs and designs dual-view Contrastive Learning-based Unsupervised framework for Heterogeneous graph Community Search (CLUHCS). CLUHCS designs a relation view to encode local community cohesion and a meta-path view to capture global behavior semantics. By using PathSim averaging strategy to generate positive samples and self-supervised signals, we can completely eliminate label dependency. Then, contrastive training is leveraged to automatically learn community representations and solve the open community boundary ambiguity challenge. Furthermore, by capturing behavior patterns, the meta-path behavior modeling flexibly characterizes the formation mechanism of heterogeneous communities. Experiments on three datasets verify the effectiveness and efficiency of CLUHCS. CLUHCS significantly improves F1-score by 52.7% over the supervised baseline FCS-HGNN and by 41.5% over the unsupervised method TransZero.

PDF Details DOI

AAMAS Conference 2026 Conference Paper

Neuro-symbolic Action Masking for Deep Reinforcement Learning

Shuai Han
Mehdi Dastani
Shihan Wang

Deep reinforcement learning (DRL) may explore infeasible actions during training and execution. Existing approaches assume a symbol grounding function that maps high-dimensional states to consistent symbolic representations and a manually specified action masking techniques to constrain actions. In this paper, we propose Neuro-symbolic Action Masking (NSAM), a novel framework that automatically learn symbolic models, which are consistent with givendomainconstraintsofhigh-dimensionalstates, inaminimally supervised manner during the DRL process. Based on the learned symbolic model of states, NSAM learns action masks that rules out infeasible actions. NSAM enables end-to-end integration of symbolic reasoning and deep policy optimization, where improvements in symbolic grounding and policy learning mutually reinforce each other. We evaluate NSAM on multiple domains with constraints, and experimental results demonstrate that NSAM significantly improves sample efficiency of DRL agent while substantially reducing constraint violations.

PDF

EAAI Journal 2025 Journal Article

Detecting worker loss of balance events from point cloud sequence using unsupervised motion-pose learning

Mingyu Zhang
Lei Wang
Yinong Hu
Shuai Han
Jiawen Zhang
Heng Li

Workers' loss of balance (LB), such as slip and trip, may lead to severe injuries and even fatalities. Existing methods for detecting LB typically rely on wearable sensors and focus on specific body parts. This study introduces a novel, non-contact approach utilizing light detection and ranging (LiDAR) technology to detect LB events. By capturing full-body point cloud data, the proposed method extracts both static pose and dynamic motion features across multiple body sections and detects LB events through unsupervised learning. The high-dimensional point cloud sequence is transformed into interpretable gait features, enabling effective unsupervised learning through sequence reconstruction. A two-stream network and fusion strategy are also developed to combine pose and motion features for final LB detection. Experiments with various LB events demonstrate the method's effectiveness, achieving an F1 score of 0. 98 and a recall of 0. 98. Our analysis reveals that integrating features from multiple body parts and the fusion of pose and motion information significantly enhances detection performance. This study offers a promising alternative to traditional methods, providing effective, non-intrusive monitoring of worker safety in dynamic construction environments.

Details DOI

EAAI Journal 2025 Journal Article

Epidemiology-informed Spatiotemporal Graph Neural Network for heterogeneity-driven interpretable epidemic forecasting

Shuai Han
Lukas Stelz
Thomas R. Sokolowski
Kai Zhou
Horst Stöcker

Accurate epidemic forecasting is crucial for effective disease control and prevention. Traditional mechanistic models often struggle to estimate epidemiological parameters that vary spatiotemporally, while deep learning-based approaches typically disregard intrinsic transmission dynamics and lack interpretability. To overcome these limitations, we propose a novel Epidemiology-informed Spatiotemporal Graph Neural Network (EISTGNN): a hybrid framework integrating the proposed Spatio-Contact Susceptible–Infectious–Recovered (SCSIR) model with a spatiotemporal graph neural network to model epidemic transmission dynamics across regions. The inherently smooth and continuous nature of interregional epidemic transmission indicates that consecutive graph structures share underlying latent patterns. To leverage this property, we employ an adaptive graph to model stable contact patterns, a temporal module to capture their fluctuating interactions, and fuse both into a spatiotemporal contact graph. To address the limitations of recurrent structures, we introduce a temporal decomposition module to extract long-term trends and short-term variations, which is then integrated with a spatiotemporal graph convolutional network to simultaneously identify epidemiological parameters and forecast outbreaks. We validate EISTGNN on real-world datasets at the provincial level in China and at the state level in Germany. Experimental results demonstrate that our method effectively models the spatiotemporal dynamics of infectious diseases, offering a valuable tool for epidemic modeling and forecasting. Furthermore, by analyzing the learned parameters through the effective reproduction number ( R t ), we derive valuable insights into transmission mechanisms and enhance both interpretability and practical utility of the underlying model.

Details DOI

EWRL Workshop 2025 Workshop Paper

Learning Reward Structure with Subtasks in Reinforcement Learning

Shuai Han
Mehdi Dastani
Shihan Wang

Improving sample efficiency of Reinforcement Learning (RL) in sparse-reward environments poses a significant challenge. In scenarios where the reward structure is complex, accurate action evaluation often relies heavily on precise information about past achieved subtasks and their order. Previous approaches have often failed or proved inefficient in constructing and leveraging such intricate reward structures. In this work, we propose an RL algorithm that can automatically structure the reward function for sample efficiency, given a set of labels that signify subtasks. Given such minimal knowledge about the task, we train a high-level policy that selects optimal subtasks in each state together with a low-level policy that efficiently learns to complete each sub-task. We evaluate our algorithm in a variety of sparse-reward environments. The experiment results show that our method significantly outperforms the state-of-art baselines as the difficulty of the task increases.

PDF

EAAI Journal 2024 Journal Article

A hybrid estimation of distribution algorithm for solving assembly flexible job shop scheduling in a distributed environment

Baigang Du
Shuai Han
Jun Guo
Yibing Li

This paper proposes a novel distributed assembly flexible job shop scheduling problem (DAFJSP), which involves three stages: production stage, assembly stage, and delivery stage. The production stage is accomplished in a few flexible job shops, the assembly stage is accomplished in a few single-machine factories, and the delivery stage is to deliver the obtained products to the corresponding customers. To address the problem, a hybrid estimation of distribution algorithm based on differential evolution operator and variable neighborhood search (HEDA-DEV) is proposed with the goal of minimizing the total cost and tardiness. Firstly, a new multidimensional coding method is designed based on the features of the DAFJSP. Secondly, two mutation operators and the similarity coefficient based on the probability matrix are put forward to implement the dynamic mutation. Thirdly, five types of neighborhood structures satisfying cooperative search strategies are employed to adequately improve the local exploitation ability. Finally, the comparison experiment results suggest that the proposed HEDA-DEV has competitive performance compared to the selected efficient algorithms. Moreover, a real case study is used to demonstrate that HEDA-DEV is an effective method for solving DAFJSP.

Details DOI

TCS Journal 2024 Journal Article

Biometric-based two-factor authentication scheme under database leakage

Mingming Jiang
Shengli Liu
Shuai Han
Dawu Gu

A Two-Factor Authentication (2FA) scheme can authenticate a client if the client is able to provide the possession factor (like biometric feature, smart card) and the knowledge factor (like password, secret key) simultaneously. With only one factor, it is hard for an adversary to impersonate the client to pass the authentication, and thus 2FA provides better security than single-factor authentication schemes. However, as far as we know, all existing 2FA schemes do not consider the leakage of server's database, and their authenticity may fail when the database is also compromised (in addition to one factor). Considering numerous reports of database leakage in the real world, it seems imminent to study and design 2FA schemes resilient to database leakage. In this paper, we formalize security models for 2FA schemes by taking database leakage into account. Our security models consider malicious adversaries who can obtain both the client's one authentication factor and the server's database, and have two requirements, authenticity and zero-knowledge. Authenticity ensures that such malicious adversaries cannot impersonate the client to pass the authentication, while zero-knowledge guarantees that such malicious adversaries obtain no information about the client's the other factor. Zero-knowledge is especially important for biometric features (like faces, fingerprints), which are inherent to human beings and can hardly be changed. Then we propose a biometric-based 2FA scheme with biometric feature and secret key serving as the two authentication factors. Our 2FA scheme has three rounds, and we prove its authenticity and zero-knowledge under database leakage in the random oracle model. Notably, our construction makes a novel use of a recent technical advance called robust property-preserving hashing (Boyle et al. , ITCS 2019) together with fully homomorphic encryption, to recognize or discern clients by their biometric samplings in a homomorphic and secure way.

Details DOI

ECAI Conference 2024 Conference Paper

Learning Reward Structure with Subtasks in Reinforcement Learning

Shuai Han
Mehdi Dastani
Shihan Wang 0001

Details

EWRL Workshop 2024 Workshop Paper

Model-based Sparse Communication in Multi-agent Reinforcement Learning

Shuai Han
Mehdi Dastani
Shihan Wang

Learning to communicate efficiently is central to multi-agent reinforcement learning (MARL). Existing methods often require agents to exchange messages intensively, which abuses communication channels and leads to high communication overhead. Only a few methods target on learning sparse communication, but they allow limited information to be shared, which affects the efficiency of policy learning. In this work, we propose model-based communication (MBC), a learning framework with a decentralized communication scheduling process. The MBC framework enables multiple agents to make decisions with sparse communication. In particular, the MBC framework introduces a model-based message estimator to estimate the up-to-date global messages using past local data. A decentralized message scheduling mechanism is also proposed to determine whether a message shall be sent based on the estimation. We evaluated our method in a variety of mixed cooperative-competitive environments. The experiment results show that the MBC method shows better performance and lower channel overhead than the state-of-art baselines.

PDF

TCS Journal 2024 Journal Article

Robustly reusable fuzzy extractor from isogeny

Yu Zhou
Shengli Liu
Shuai Han

Robustly reusable Fuzzy Extractor (rrFE) allows multiple extractions from the same fuzzy source in a reproducible way. The reusability of rrFE asks the pseudo-randomness of the extracted keys, while robustness of rrFE makes sure that active attacks can be detected during the reproduction of the extracted key. With rrFE, we are able to produce cryptographic keys for our cryptosystems from fuzzy sources, like biometrics, physical unclonable functions, etc. There are rrFE schemes from the DDH, LWE and LPN assumptions. However there is no rrFE scheme from isogeny-based assumptions up to now. In this paper, we construct the first rrFE from isogeny. To obtain such an rrFE, we propose a new framework for constructing rrFE with a core technical tool, named Enhanced Effective Group Action (EEGA). EEGA is built upon the basic Effective Group Action (EGA), and is equipped with a sampling algorithm and a derivation algorithm. With such an EEGA, the same random input can be derived to produce different pseudo-random and unpredictable outputs. The EEGA, together with other routine building blocks like secure sketch and extractor, leverages an FE to achieve reusability and robustness. We construct EEGA based on CSI-FiSh, which admits the first rrFE scheme from isogeny. Besides, we also propose another two EEGA instantiations from the DDH assumption, and this provides another approach to DDH-based rrFE, which may be of independent interest.

Details DOI

EAAI Journal 2023 Journal Article

Intelligent mining of safety hazard information from construction documents using semantic similarity and information entropy

Dan Tian
Mingchao Li
Yang Shen
Shuai Han

Project construction on-site is known to be very dangerous workplace environments due to large numbers of safety hazards. Analysis of construction safety hazards is essential to formulate rational safety management plans and prevent accidents. Construction documents contain large volumes of safety hazard information available for analysis. However, such analyses are challenging because the safety hazard information in the construction documents is presented in an unstructured or semi-structured format. This study proposes a method for intelligent mining of safety hazard information, which comprises safety hazard technical term recognition and safety hazard information analysis. The safety hazard technical term recognition model is developed based on semantic similarity and information correlation to build a safety hazard technical term library. The safety hazard information based on the technical term library is mined and analyzed using the term frequency-inverse document frequency method (TF-IDF). Finally, the proposed method is applied to build the safety hazard technical term library, which contains 2697 technical terms, and develop a hydraulic project construction safety hazard analysis system, which can realize the intelligent recognition and application of technical terms. Meanwhile, this system can automatically extract safety hazard information and provide a visualization interface to intuitively show the safety hazard analysis results, which improves the extraction efficiency of safety hazard information. The study provides a new approach for recognizing technical terms and mining safety hazard information, which can lead to enhancing management efficiency and practical knowledge discovery for safety management.

Details DOI

AAMAS Conference 2023 Conference Paper

Model-based Sparse Communication in Multi-agent Reinforcement Learning

Shuai Han
Mehdi Dastani
Shihan Wang

PDF

TCS Journal 2023 Journal Article

Simulatable verifiable random function from the LWE assumption

Yiming Li
Shengli Liu
Shuai Han
Dawu Gu
Jian Weng

A verifiable random function (VRF) is a pseudorandom function F that can be publicly verified. A simulatable VRF (sVRF) is an important variant of a VRF, which additionally provides simulatability. Informally, the simulatability of a VRF depicts the ability to simulate a valid proof π that y = F ( s k, x ) for any input x and any output value y. A (simulatable) VRF can be used in the E-Cash, E-Lottery, blockchain and constructing the multi-theorem non-interactive zero-knowledge (NIZK) proof. However, up to now, the existing constructions of an sVRF either rely on non-standard assumptions (e. g. , the Q-type ones), or are built in the random oracle model, or resort to time-consuming techniques like the Cook-Levin reduction. In this paper, we design the first sVRF from the LWE assumption in the standard model (free of a random oracle) without using a Cook-Levin reduction. In our construction of an sVRF, we take as building blocks a pseudorandom function, a trapdoor fully homomorphic commitment (FHC) scheme, and a NIZK proof system for a language specified by FHC. Our trapdoor FHC is the key technical tool, which helps the simplification of the underlying NIZK language, thus making possible an instantiation of a NIZK proof from LWE without a Cook-Levin reduction. Together with an LWE-based PRF, we obtain an sVRF scheme from LWE.

Details DOI

TCS Journal 2022 Journal Article

Tightly CCA-secure inner product functional encryption scheme

Xiangyu Liu
Shengli Liu
Shuai Han
Dawu Gu

Inner product functional encryption (IPFE) is a modern public key paradigm where the master key can derive a secret key s k y for a vector y, which can then be used to decrypt a ciphertext of x to get the inner product 〈 x, y 〉 as output. In ASIACRYPT 2019, Tomida proposed the first tightly secure IPFE scheme in the multi-user and multi-challenge setting based on the matrix decisional Diffie-Hellman (MDDH) assumption. However, the construction achieves CPA security only. Up to now, there is no IPFE scheme with tight CCA security available. In this paper, we construct the first tightly CCA-secure IPFE scheme in the multi-user and multi-challenge setting. The security reduction to the MDDH assumption (including SXDH, k-LIN, etc.) loses only a factor O ( log ⁡ λ ) with λ the security parameter. Moreover, our scheme enjoys full compactness. To support inner product function of dimension m, our SXDH-based IPFE has ( m 2 + 8 m + 14 ) and ( 3 m + 14 ) group elements in the master public key and ciphertext respectively. This is comparable to the tightly CPA-secure IPFE proposed by Tomida based on the DDH assumption, whose master public key and ciphertext contain ( m 2 + 2 ) and 3m group elements, respectively. Furthermore, we construct the first IPFE with both tight CCA-security and function-hiding property, based on our CCA-secure IPFE. The tight function-hiding CCA security is obtained by adapting the techniques in Lin (CRYPTO 2017) and Gay (PKC 2020) to the multi-user and multi-challenge setting.

Details DOI

JBHI Journal 2019 Journal Article

Pattern Classification for Gastrointestinal Stromal Tumors by Integration of Radiomics and Deep Convolutional Features

Zhenyuan Ning
Jiaxiu Luo
Yong Li
Shuai Han
Qianjin Feng
Yikai Xu
Wufan Chen
Tao Chen

Predicting malignant potential is one of the most critical components of a computer-aided diagnosis system for gastrointestinal stromal tumors (GISTs). These tumors have been studied only on the basis of subjective computed tomography findings. Among various methodologies, radiomics, and deep learning algorithms, specifically convolutional neural networks (CNNs), have recently been confirmed to achieve significant success by outperforming the state-of-the-art performance in medical image pattern classification and have rapidly become leading methodologies in this field. However, the existing methods generally use radiomics or deep convolutional features independently for pattern classification, which tend to take into account only global or local features, respectively. In this paper, we introduce and evaluate a hybrid structure that includes different features selected with radiomics model and CNNs and integrates these features to deal with GISTs classification. The Radiomics model and CNNs are constructed for global radiomics and local convolutional feature selection, respectively. Subsequently, we utilize distinct radiomics and deep convolutional features to perform pattern classification for GISTs. Specifically, we propose a new pooling strategy to assemble the deep convolutional features of 54 three-dimensional patches from the same case and integrate these features with the radiomics features for independent case, followed by random forest classifier. Our method can be extensively evaluated using multiple clinical datasets. The classification performance (area under the curve (AUC): 0. 882; 95% confidence interval (CI): 0. 816-0. 947) consistently outperforms those of independent radiomics (AUC: 0. 807; 95% CI: 0. 724-0. 892) and CNNs (AUC: 0. 826; 95% CI: 0. 795-0. 856) approaches.

Details DOI

TCS Journal 2019 Journal Article

QANIZK for adversary-dependent languages and their applications

Shuai Han
Shengli Liu
Lin Lyu

Quasi-Adaptive Non-Interactive Zero-Knowledge (QANIZK) proofs make possible efficient NIZK with short proofs by allowing the common reference string to depend on the language. The strongest notion of (computational) soundness for QANIZK is Unbounded Simulation-Soundness (USS). For USS, however, the language is completely beyond the adversary's control. In this paper, we introduce a stronger notion of USS for QANIZK, called USS for Adversary-Dependent Languages (USS-ADL), by allowing the adversary to adaptively develop the language. We present a generic construction of efficient USS-ADL-QANIZK for diverse vector spaces (DVS) over graded rings, of which linear subspaces over bilinear groups are specific instantiations. – Our generic construction provides the first USS-QANIZK for DVS over graded rings. This complements Abdalla et al. 's work (Eurocrypt'15) of QANIZK with one-time simulation-soundness. – As for applications, USS-ADL-QANIZK leads to modular constructions of digital signature and linearly homomorphic (structure-preserving) signature schemes with black-box security reductions. The instantiations cover the efficient USS-QANIZK for linear subspaces over bilinear groups proposed by Kiltz and Wee (Eurocrypt'15), a variant of the efficient structure-preserving signature proposed by Kiltz et al. (Crypto'15) and the efficient linearly homomorphic structure-preserving signature proposed by Kiltz and Wee (Eurocrypt'15). Our USS-ADL-QANIZK provides a new perspective on their constructions and security proofs in a unified way.

Details DOI