摘要:
Complex knowledge graph question answering (KGQA) aims at answering natural language questions by entities retrieving from a knowledge graph (KG). Recently, the relation path-based models have shown the unique advantage for complex KGQA. However, these existing models ignore the dependency between different relation paths, which leads to aimless reasoning over the KG. To resolve this issue, we propose the question-directed reasoning with relation-aware graph attention network (QRGAT) that encodes the reasoning process as a reasoning graph. The relation-aware GAT can recognize neighbor entities along with the corresponding relations for each entity. With the relation-aware GAT stacked in multiple layers, it can collaboratively capture the dependency of different relation paths for each entity. The question-directed reasoning utilizes the information learned by the relation-aware GAT to solve the aimless reasoning on the KG by constructing a reasoning graph. Extensive experiments demonstrate that our QRGAT outperforms the baseline models on both popular datasets WebQuestionsSP and ComplexWebQuestions. Compared with the strong GNN-based baseline NSM<inline-formula><tex-math notation="LaTeX">$_{+h}$</tex-math></inline-formula>, our QRGAT achieves the performance improvements of 2.3% on WebQuestionsSP and 3.6% on ComplexWebQuestions by the metric Hits@1. Complex knowledge graph question answering (KGQA) aims at answering natural language questions by entities retrieving from a knowledge graph (KG). Recently, the relation path-based models have shown the unique advantage for complex KGQA. However, these existing models ignore the dependency between different relation paths, which leads to aimless reasoning over the KG. To resolve this issue, we propose the question-directed reasoning with relation-aware graph attention network (QRGAT) that encodes the reasoning process as a reasoning graph. The relation-aware GAT can recognize neighbor entities along with the corresponding relations for each entity. With the relation-aware GAT stacked in multiple layers, it can collaboratively capture the dependency of different relation paths for each entity. The question-directed reasoning utilizes the information learned by the relation-aware GAT to solve the aimless reasoning on the KG by constructing a reasoning graph. Extensive experiments demonstrate that our QRGAT outperforms the baseline models on both popular datasets WebQuestionsSP and ComplexWebQuestions. Compared with the strong GNN-based baseline NSM<inline-formula><tex-math notation="LaTeX">$_{+h}$</tex-math></inline-formula>, our QRGAT achieves the performance improvements of 2.3% on WebQuestionsSP and 3.6% on ComplexWebQuestions by the metric Hits@1.
作者机构:
[Hsu, Chingfang] Cent China Normal Univ, Comp Sch, 152 Luoyu Ave, Wuhan 430079, Peoples R China.;[Xia, Zhe] Wuhan Univ Technol, Dept Comp Sci, 122 Luoshi Ave, Wuhan 430071, Peoples R China.;[Cheng, Tianshu] Cent China Normal Univ, Middle Sch 1, 281 Zhuodaoquan Ave,45100 Rockhill Rd, Wuhan 430079, Peoples R China.;[Harn, Lein] Univ Missouri, Dept Comp Sci Elect Engn, Kansas City, MO 64110 USA.
通讯机构:
[Zhe Xia] D;Department of Computer Science, Wuhan University of Technology , 122 Luoshi Avenue, Wuhan 430071 , China
关键词:
RSE toward 5G;secure group communications;membership authenticated group key agreement;symmetric bivariate polynomial;logic XOR operation;lightweight and constant-round
摘要:
With rapid development of next-generation mobile networks and communications (5G networks), group-oriented applications in resource-constrained smart environments (RSEs), such as smart homes and smart classrooms, have attracted great attentions. Due to the insecure communications between resource-constrained devices, secure group communications in RSE toward 5G face many challenges. In RSE toward 5G, lightweight communications and low computational overheads are crucial. Besides, the private tokens used to generate the group key are expected to be reused multiple times. However, the conventional frameworks for secure group communications cannot meet these requirements. A practical construction of extremely lightweight constant-round membership authenticated group key establishment framework is proposed in this paper for RSE toward 5G, which not only implements identity authentication among the members and group key establishment but also ensures extremely lightweight computation and communication costs by each group member. In our proposed scheme, the increase in the number of group members will not lead to a linear or logarithmic increase in the communication and calculation costs at the member side. Our framework also resists external and internal attacks and meets all the desirable security features. In this framework, the privacy of tokens can be well protected, so that they can be reused for multiple times. Therefore, our scheme significantly reduces the costs of communication and calculation, and it is more efficient compared with the related schemes in the literature. This proposal is fairly suitable for lightweight membership authentication and group key establishment in RSE toward 5G.
关键词:
Session-based recommendationheterogeneous hypergraphshypergraph neural networksinformation lossadditional information
摘要:
In recent years, session-based recommendation (SBR), which seeks to predict the target user’s next click based on anonymous interaction sequences, has drawn increasing interest for its practicality. The key to completing the SBR task is modeling user intent accurately. Due to the popularity of graph neural networks (GNNs), most state-of-the-art (SOTA) SBR approaches attempt to model user intent from the transitions among items in a session with GNNs. Despite their accomplishments, there are still two limitations. First, most existing SBR approaches utilize limited information from short user–item interaction sequences and suffer from the data sparsity problem of session data. Second, most GNN-based SBR approaches describe pairwise relations between items while neglecting complex and high-order data relations. Although some recent studies based on hypergraph neural networks have been proposed to model complex and high-order relations, they usually output unsatisfactory results due to insufficient relation modeling and information loss. To this end, we propose a category-aware lossless heterogeneous hypergraph neural network (CLHHN) in this article to recommend possible items to the target users by leveraging the category of items. More specifically, we convert each category-aware session sequence with repeated user clicks into a lossless heterogeneous hypergraph consisting of item and category nodes as well as three types of hyperedges, each of which can capture specific relations to reflect various user intents. Then, we design an attention-based lossless hypergraph convolutional network to generate sessionwise and multi-granularity intent-aware item representations. Experiments on three real-world datasets indicate that CLHHN can outperform the SOTA models in making a better tradeoff between prediction performance and training efficiency. An ablation study also demonstrates the necessity of CLHHN’s key components. In recent years, session-based recommendation (SBR), which seeks to predict the target user’s next click based on anonymous interaction sequences, has drawn increasing interest for its practicality. The key to completing the SBR task is modeling user intent accurately. Due to the popularity of graph neural networks (GNNs), most state-of-the-art (SOTA) SBR approaches attempt to model user intent from the transitions among items in a session with GNNs. Despite their accomplishments, there are still two limitations. First, most existing SBR approaches utilize limited information from short user–item interaction sequences and suffer from the data sparsity problem of session data. Second, most GNN-based SBR approaches describe pairwise relations between items while neglecting complex and high-order data relations. Although some recent studies based on hypergraph neural networks have been proposed to model complex and high-order relations, they usually output unsatisfactory results due to insufficient relation modeling and information loss. To this end, we propose a category-aware lossless heterogeneous hypergraph neural network (CLHHN) in this article to recommend possible items to the target users by leveraging the category of items. More specifically, we convert each category-aware session sequence with repeated user clicks into a lossless heterogeneous hypergraph consisting of item and category nodes as well as three types of hyperedges, each of which can capture specific relations to reflect various user intents. Then, we design an attention-based lossless hypergraph convolutional network to generate sessionwise and multi-granularity intent-aware item representations. Experiments on three real-world datasets indicate that CLHHN can outperform the SOTA models in making a better tradeoff between prediction performance and training efficiency. An ablation study also demonstrates the necessity of CLHHN’s key components.
期刊:
ACM Transactions on Knowledge Discovery from Data,2024年18(1):1–22 ISSN:1556-4681
通讯作者:
Hu, P
作者机构:
[Wang, Huan] Huazhong Agr Univ, PKU Wuhan Inst Artificial Intelligence, Coll Informat, Wuhan 430070, Hubei, Peoples R China.;[Liu, Guoquan; Hu, Po; Hu, P] Cent China Normal Univ, Sch Comp Sci, Wuhan 430079, Hubei, Peoples R China.
通讯机构:
[Hu, P ] C;Cent China Normal Univ, Sch Comp Sci, Wuhan 430079, Hubei, Peoples R China.
关键词:
Transfer learning;link prediction;type-shared knowledge
摘要:
Link prediction has received increased attention in social network analysis. One of the unique challenges in heterogeneous social networks is link prediction in new link types without verified link information, such as recommending products to new overseas groups. Existing link prediction models tend to learn type-specific knowledge on specific link types and predict missing or future links on the same link types. However, because of the uncertainty of new link types in the evolving process of social networks, it is difficult to collect sufficient verified link information in new link types. Therefore, we propose the Transferable Domain Adversarial Network (TDAN) based on transfer learning to handle the challenge. TDAN exploits transferable type-shared knowledge in historical link types to help predict the unobserved links in new link types. TDAN mainly comprises a structural encoder, a domain discriminator, and an optimization decoder. The structural encoder learns the link representations in a heterogeneous social network. Subsequently, to learn transferable type-shared knowledge, the domain discriminator distinguishes link representations into different link types while minimizing the differences between type-specific knowledge in adversarial training. Inspired by the denoising auto-encoder, the optimization decoder reconstructs the learned type-shared knowledge to eliminate the noise generated during the adversarial training. Extensive experiments on Facebook and YouTube show that TDAN can outperform the state-of-the-art models.
期刊:
IEEE INTERNET OF THINGS JOURNAL,2024年11(2):3348-3361 ISSN:2327-4662
通讯作者:
Guo, YM
作者机构:
[Guo, Yimin; Guo, YM; Xiong, Ping] Zhongnan Univ Econ & Law, Sch Informat & Safety Engn, Wuhan 430073, Peoples R China.;[Zhang, Zhenfeng] Chinese Acad Sci, Trusted Comp & Informat Assurance Lab, Inst Software, Beijing 100045, Peoples R China.;[Guo, Yajun] Cent China Normal Univ, Sch Comp, Wuhan 430079, Hubei, Peoples R China.
通讯机构:
[Guo, YM ] Z;Zhongnan Univ Econ & Law, Sch Informat & Safety Engn, Wuhan 430073, Peoples R China.
关键词:
Authentication;blockchain;fog-enabled Internet of Things (IoT);key agreement;physical unclonable functions (PUFs)
摘要:
The insufficient trustworthiness of fog nodes in fog computing leads to new security and privacy problems in communication between entities. Existing authentication schemes rely on a trusted third party, or assume that fog nodes are trustworthy, or the authentication overhead is high, which is inconsistent with the characteristics of fog computing. To solve the problem of secure communication in the fog computing environment, we propose an efficient blockchain-based secure remote authentication protocol for the fog-enabled Internet of Things (BSRA). Specifically, blockchain is introduced to construct distributed trust for the fog computing environment. Only lightweight cryptographic primitives, such as physical unclonable functions (PUFs) and cryptographic hash functions, are exploited to design the authentication scheme. In addition, we use temporary identities and the authentication-piggybacking-synchronization to ensure the anonymity and effectiveness of the authentication scheme. We conduct security analysis to demonstrate that BSRA can provide guarantees against various known attacks. We also evaluate the performance of BSRA from several aspects, and the results show that BSRA is effective.
摘要:
Brain storm optimization (BSO) is a population-based intelligence algorithm for optimization problems, which has attracted researchers' growing attention due to its simplicity and efficiency. An improved BSO, called CIBSO, is presented in this article. First of all, a new grouping method, in which the population is partitioned into chunks according to the fitness and recombined to groups, is developed to balance each group with same quality-level. Afterwards, a new mutation strategy is designed in CIBSO and a learning mechanism is used to adaptively select appropriate strategy. Experiments on the CEC2014 test suite indicate that CIBSO is better or at least competitive performance against the compared BSO variants.
摘要:
Temporal knowledge graph (TKG) reasoning aims to infer the missing links from the massive historical facts. One of the big issues is that how to model the entity evolution from both the local and especially global perspectives. The primary temporal dependency models often fail to disentangle both perspectives due to the lack explicit annotations to distinguish the boundary of these two representations. To address these limitations, we propose a contrastive learning framework to Disentangle Local and Global perspectives for TKG Reasoning with selfsupervision framework (DLGR). Our proposed DLGR can jointly utilize the local and global perspectives on two separate graphs and disentangle them in a self -supervised manner. Firstly, we construct a temporal subgraph and a temporal unified graph to effectively learn the local and global perspective representations, respectively. Second, we extract proxies regarding the different neighbors as pseudo labels to supervise the local and global disentanglement in a contrastive manner. Finally, we adaptively fuse the learned two perspective representations for TKG reasoning. The empirical results show that our DLGR significantly outperforms other baselines (e.g., compared to the strong baseline HGLS, our DLGR achieves 4.3%, 3.4%, 1.6% and 1.1% improvements on ICEWS14, ICEWS18, YAGO and WIKI using MRR).
摘要:
Nowadays, with continuous integration of big data, artificial intelligence and cloud computing technologies, there are increasing demands and specific requirements for data sharing in sustainable smart cities: (1) practical data sharing should be implemented in the non-interactive fashion without a trusted third party to be involved; (2) dynamic thresholds are preferred since the participants may join or leave at any time; (3) multi-secret sharing is desirable to increase the packing capacity. To fulfil these requirements, we propose a general construction of ideal threshold changeable multi-secret sharing scheme (TCMSS) with information-theoretic security, in which polynomials are employed to achieve dealer-free and non-interactive in the secret reconstruction phase. The TCMSS scheme can be built on any existing linear secret sharing scheme, and it is simpler and more efficient than the existing TCSS schemes in the literature. The main difference between TCMSS and Shamir's SS is that univariate polynomial is used in Shamir's SS to generate the shares for all shareholders; while in TCMSS, each shareholder can recover her own univariate polynomial using her share. This article demonstrates that with this novel modification, the classic polynomial-based SS can be transformed into an ideal TCMSS. Moreover, the TCMSS scheme is lightweight and it can resist both internal and external attacks. It does not require pairwise key distribution and its secret reconstruction phase is improved with enhanced properties. Therefore, the designed proposal is fairly suitable and attractive to be deployed in sustainable cities.
期刊:
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS,2023年20:1-5 ISSN:1545-598X
通讯作者:
Yu, J
作者机构:
[Sun, Hao] Cent China Normal Univ, Hubei Prov Key Lab Artificial Intelligence & Smart, Sch Comp, Wuhan 430079, Peoples R China.;[Sun, Hao] Cent China Normal Univ, Natl Language Resources Monitoring & Res Ctr Netwo, Wuhan 430079, Peoples R China.;[Li, Qianqian; Zhou, Dongbo] Cent China Normal Univ, Fac Artificial Intelligence Educ, Wuhan 430079, Peoples R China.;[Yu, Jie] Wuhan Univ, State Key Lab Informat Engn Surveying Mapping & Re, Wuhan 430079, Peoples R China.;[Yu, Jie] Wuhan Univ, Off Sci & Technol Dev, Wuhan 430072, Peoples R China.
通讯机构:
[Yu, J ] W;Wuhan Univ, State Key Lab Informat Engn Surveying Mapping & Re, Wuhan 430079, Peoples R China.
关键词:
Deep learning;feature reconstruction;open-set classification;remote-sensing imagery
摘要:
Existing remote-sensing scene image (RSSI) classification methods usually rely on the static closed-set assumption that testing samples do not belong to unknown classes. However, practical applications are usually the open-set classification problem, which means that RSSIs from unknown classes will appear in the testing set. Most existing methods are prone to forcibly misclassify RSSIs of unknown classes into known classes, resulting in poor practical performance. In this letter, a deep feature reconstruction learning (DFRL) framework is proposed for the open-set classification of RSSIs (OSC-RSSIs). The proposed DFRL unifies discriminative feature learning and feature reconstruction into an end-to-end network. First, a feature extraction module is utilized to project raw input data from the image space to the feature space to extract deep features. Then, the deep features are fed to a deep feature reconstruction module for distinguishing known and unknown classes based on feature-level reconstruction errors. The feature-level reconstruction can effectively suppress the interference of complex backgrounds. In addition, a sparse regularization is introduced to improve the discrimination of image representation. Experiments on three RSSI datasets demonstrate the effectiveness of DFRL for OSC-RSSIs.
作者机构:
[Chen, Renyi; Yao, Huaxiong] Cent China Normal Univ, Comp Sch, Wuhan 430079, Peoples R China.;[Yao, Huaxiong] Cent China Normal Univ, Comp Sch, Wuhan 430079, Peoples R China.
通讯机构:
[Yao, HX ] ;Cent China Normal Univ, Comp Sch, Wuhan 430079, Peoples R China.
摘要:
A detailed theoretical study is conducted on the nonlinear interference in the same-wavelength bidirectional coherent optical fiber communication systems. The Gaussian noise (GN) model used to evaluate nonlinear interference (NLI) in unidirectional systems is applied and extended to bidirectional transmission scenarios. The extended NLI model shows that in a bidirectional transmission communication system, the backward signal almost does not introduce additional nonlinear crosstalk to the forward signal due to the strong walk-off effect between forward and backward transmitted signals. Specifically, the ratio of the nonlinear crosstalk introduced by the forward and backward signals is about 21 dB, which means that the traditional GN model is also applicable in the bidirectional scenario. This conclusion is validated on the platform of a same-wavelength bidirectional coherent optical communication system based on Optisystem software.
摘要:
This paper studies a heterogeneous multiplex network model that allows different dynamics in different layers. We explore intralayer synchronization of the multiplex network under distinct types of interlayer connections. From the perspective of spectral graph theory, we propose a set of edge weight requirements to synchronize the multiplex network. Focusing on the effect of interlayer connections to intralayer synchronization, it is found that a multiplex network can achieve intralayer synchronization with a large enough interlayer coupling strength even if a single network of one layer cannot synchronize by itself. In fact, the synchronizability of the multiplex network is found to be stronger than that of the single-layer network. These results provide insights into the practical application of multiplex network theory in engineering networks.
期刊:
IEEE Transactions on Geoscience and Remote Sensing,2023年61:1-11 ISSN:0196-2892
通讯作者:
Fu, LH
作者机构:
[Fu, Lihua; Chen, Xingrong; Xu, Yuejiao; Niu, Xiao] China Univ Geosci, Sch Math & Phys, Wuhan 430074, Peoples R China.;[Zhang, Meng] Cent China Normal Univ, Sch Comp Sci, Wuhan 430079, Peoples R China.
通讯机构:
[Fu, LH ] C;China Univ Geosci, Sch Math & Phys, Wuhan 430074, Peoples R China.
关键词:
Tensors;Three-dimensional displays;Matrix decomposition;Correlation;Singular value decomposition;Frequency-domain analysis;Spectral analysis;3-D seismic data reconstruction;fully connected tensor network (FCTN);Hankel tensor;low rank
摘要:
Rank-reduction approaches assume that seismic data in the frequency–space domain is of low-rank after a specific pretransformation. The presence of noise or missing traces will increase the rank; therefore, seismic data can be denoised and recovered via rank-reduction techniques. The iterative weighted projection onto convex sets (POCS) framework can be used for noise attenuation and data reconstruction simultaneously. Multichannel singular spectrum analysis (MSSA) is a classic 3-D seismic data reconstruction algorithm that rearranges the temporal frequency slices of the data with missing traces into a block Hankel matrix and then uses randomized singular value decomposition (RSVD) to interpolate slices. To further improve the efficiency and precision of 3-D seismic data reconstruction, we introduce the fully connected tensor network (FCTN) decomposition over the Hankel tensor of the frequency slices. We show that our novel rank-reduction method estimates fewer parameters than MSSA, yielding more accurate and robust results. Moreover, FCTN decomposes a fourth-order tensor into four factor contractions, which breaks the limitations that traditional tensor decomposition methods, such as CANDECOMP/PARAFAC (CP) and Tucker decomposition, cannot establish the connections between different factors and are less effective at characterizing relationships. The newly proposed approach does not require singular value decomposition (SVD), leading to an overall reduction in computational complexity. Synthetic and field examples are used to compare the performance of our method with MSSA, and our numerical results reveal the better performance of the proposed FCTN decomposition method for seismic data with large gaps or a high missing ratio.
期刊:
Peer-to-Peer Networking and Applications,2023年16(3):1340-1353 ISSN:1936-6442
通讯作者:
Wu, AML
作者机构:
[Wu, AML; Wu, Anmulin; Guo, Yajun] Cent China Normal Univ, Sch Comp, Wuhan 430079, Peoples R China.;[Guo, Yimin] Zhongnan Univ Econ & Law, Sch Informat & Safety Engn, Wuhan 430073, Peoples R China.
通讯机构:
[Wu, AML ] C;Cent China Normal Univ, Sch Comp, Wuhan 430079, Peoples R China.
关键词:
Internet of Vehicles;Blockchain;Mobile edge computing;Authentication mechanism;Privacy protection
摘要:
Blockchain technology can provide excellent support for identity authentication and access control mechanisms. In particular, blockchain technology can ensure that large amounts of confidential data generated by the Internet of Vehicles devices are stored and transmitted in a safe and reliable environment, which is the key to making system services optimal. In addition, mobile edge computing is the best solution for IoV applications to deal with low latency and limited computing and storage capacity of vehicle-mounted devices. Mobile edge computing can help IoV systems achieve a variety of functions and features, the most important of which is the ability to process terminal data in real-time. Even though the amount of data generated by IoV devices is growing rapidly, the system is still characterized by low latency and high efficiency. Because the communication between IoV devices is carried out in an untrusted environment, it is particularly important to design a secure and effective identity authentication scheme. Therefore, this paper proposes an efficient, safe, and time-sensitive authentication mechanism for devices on the Internet of Vehicles, which applies to a large number of scenarios. The mechanism is based on the blockchain concept and mobile edge computing technology. Security analysis shows that the proposed scheme meets the security requirements of the Internet of Vehicles and is resistant to many known attacks. By comparing with existing advanced IoT authentication schemes, the performance evaluation of the mechanism shows that the scheme enhances security features while reducing computation and communication overhead.
摘要:
Group signatures allow users to sign messages on behalf of a group without revealing authority is capable of identifying the user who generated it. However, the exposure of the user's signing key will severely damage the group signature scheme. In order to reduce the loss caused by signing key leakage, Song proposed the first forward-secure group signature. If a group signing key is revealed at the current time period, the previous signing key will not be affected. This means that the attacker cannot forge group signatures regarding messages signed in the past. To resist quantum attacks, many lattice-based forward-secure group signatures have been proposed. However, their key-update algorithm is expensive since they require some costly computations such as the Hermite normal form (HNF) operations and conversion from a full-rank set of lattice vectors into a basis.
In this paper, we propose the group signature with forward security from lattice. In comparison with previous works, we have several advantages: Firstly, our scheme is more effective since we only need to sample some vectors independently from a discrete Gaussian during the key-update algorithm. Secondly, the derived secret key size is linear instead of quadratic with the lattice dimensions, which is more friendly towards lightweight applications. Anonymous authentication plays an increasingly critical role in protecting privacy and security in the environment where private information could be collected for intelligent analysis. Our work contributes to the anonymous authentication in the post-quantum setting, which has wide potential applications in the IoT environment.
期刊:
JOURNAL OF SUPERCOMPUTING,2023年79(12):13724-13743 ISSN:0920-8542
通讯作者:
Xiang Li
作者机构:
[Wu, Fei; Li, Xiang; Zhang, Maoyuan] Cent China Normal Univ, Hubei Prov Key Lab Artificial Intelligence & Smart, Wuhan 430079, Hubei, Peoples R China.;[Wu, Fei; Li, Xiang; Zhang, Maoyuan] Cent China Normal Univ, Sch Comp, Wuhan 430079, Hubei, Peoples R China.;[Wu, Fei; Li, Xiang; Zhang, Maoyuan] Cent China Normal Univ, Natl Language Resources Monitor & Res Ctr Network, Wuhan 430079, Hubei, Peoples R China.
通讯机构:
[Xiang Li] H;Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning, Central China Normal University, Wuhan, China<&wdkj&>School of Computer, Central China Normal University, Wuhan, China<&wdkj&>National Language Resources Monitor and Research Center for Network Media, Central China Normal University, Wuhan, China
摘要:
Cross-domain sentiment analysis (CDSA) aims to overcome domain discrepancy to judge the sentiment polarity of the target domain lacking labeled data. Recent research has focused on using domain adaptation approaches to address such domain migration problems. Among them, adversarial learning performs domain distribution alignment via domain confusion to transfer domain-invariant knowledge. However, this method that transforms feature representations to be domain-invariant tends to align only the marginal distribution, and may inevitably distort the original feature representations containing discriminative knowledge, thus making the conditional distribution inconsistent. To alleviate this problem, we propose adversarial domain adaptation with model-oriented knowledge adaptation (Moka-ADA) for the CDSA task. We adopt the adversarial discriminative domain adaptation (ADDA) framework to learn domain-invariant knowledge for marginal distribution alignment, based on which knowledge adaptation is conducted between the source and target models for conditional distribution alignment. Specifically, we design a dual structure with similarity constraints on intermediate feature representations and final classification probabilities, so that the target model in training learns discriminative knowledge from the trained source model. Experimental results on a publicly available sentiment analysis dataset show that our method achieves new state-of-the-art performance.
作者:
Yao, Shixiong;Tian, Xingjian;Chen, Jiageng*;Xiong, Yi
期刊:
International Journal of Network Management,2023年33(3):e2193- ISSN:1055-7148
通讯作者:
Chen, Jiageng
作者机构:
[Xiong, Yi; Yao, Shixiong; Chen, Jiageng] Cent China Normal Univ, Comp Sch, 152 Luoyu Rd, Wuhan, Hubei, Peoples R China.;[Yao, Shixiong] Wuhan Univ, Key Lab Aerosp Informat Secur & Trust Comp, Minist Educ, Wuhan, Peoples R China.;[Tian, Xingjian] Cent China Normal Univ, Cent China Normal Univ Wollongong Joint Inst, Wuhan, Peoples R China.
通讯机构:
[Chen, Jiageng] C;Cent China Normal Univ, Comp Sch, 152 Luoyu Rd, Wuhan, Hubei, Peoples R China.
摘要:
Smart grid has drawn a lot of attention and investment in recent years, which not only helps the modern generation and distribution of traditional power but also highly widens the application of renewable energy sources. However, the main challenges in the application of smart grid are 1. the privacy preservation of users' information and 2. the trustful transmission channel among peers. In order to solve these problems, VPN and blockchain can be considered since they have some features perfectly suitable for these situations. In this paper, we propose a smart grid system based on WireGuard and Hyperledger Fabric to solve the problems mentioned above. And we also implement the whole system and give a view by web application. What's more, all the functionalities are displayed and tested, including building a smart device simulator, deploying data visualization and making some performance evaluations about transactions and WireGuard communication. Experiment results show that the introduction of WireGuard into network infrastructure does not cause too much loss of bandwidth and delay, but it ensures a certain degree of communication security. And Fabric provides the consistency and traceability of transactions in smart grid system.