摘要:
Visual Dialog aims to answer an appropriate response based on a multi-round dialog history and a given image. Existing methods either focus on semantic interaction, or implicitly capture coarse-grained structural interaction (e.g., pronoun co-references). The fine-grained and explicit structural interaction feature for dialog history is seldom explored, resulting in insufficient feature learning and difficulty in capturing precise context. To address these issues, we propose a structure-aware dual-level graph interactive network (SDGIN) that integrates verb-specific semantic roles and co-reference resolution to explicitly capture context structural features for discriminative and generative tasks in visual dialog. Specifically, we create a novel structural interaction graph that injects syntactic knowledge priors into dialog by introducing semantic role labeling that imply which words are sentence stems. Furthermore, considering the single perspective limitation of previous algorithms, we design a dual-perspective mechanism that learns fine-grained token-level context structure features and coarse-grained utterance-level interactions in parallel. It possess an elegant view to explore precise context interactions, realizing the mutual complementation and enhancement of different granularity features. Experimental results show the superiority of our proposed approach. Compared to other task-specific models, our SDGIN outperforms previous models and achieves a significant improvement on the benchmark dataset VisDial v1.0.
摘要:
Entities and relations extraction are the key tasks in the construction of biomedical knowledge graph, which play an important role in the biomedical artificial intelligence. However, extraction of entities and relations from biomedical texts is challenging because of the overlapping triples problem. The previous approaches typically divided the task into two separate sub-tasks. However, these methods failed to address the error propagation problem. Recent methods have been proposed to perform both sub-tasks simultaneously. Nonetheless, most current methods still encounter issues related to imbalanced interactions and independent features. In this paper, we propose a novel method based on feature partition encoding and relative positional embedding to joint extract biomedical entity and relation triples simultaneously. Compared to previous work, our method shows exceptional accurate in extracting entities and relations, while efficiently tackling the challenge of overlapping triples in biomedical texts. Our work has two contributions. Firstly, our method divides the features into task-specific and shared parts through entity, relation and sharing partitions at the encoding stage. And the encoded features will be aggregated according to the subsequent tasks. Secondly, we introduce a relative positional embedding method to capture the relative distance information between token pairs. In this way, our method can effectively deal with the sub-tasks interactions problem and improve entities and relations extraction. The experimental results show that our method improves the F1 scores of relations extraction by 3.2%, 2.1%, 3.4%, and 2.8% on four biomedical datasets, respectively.
作者机构:
[Zhang, Yang; Zhang, Y] Shanghai Polytech Univ, Sch Econ & Management, Shanghai 201209, Peoples R China.;[Wang, Xuechun] Hubei Univ Technol, Sch Elect & Elect Engn, Wuhan 430068, Peoples R China.;[Wen, Jinghao] Cent China Normal Univ, Sch Comp Sci, Wuhan 430079, Peoples R China.;[Zhu, Xianxun] Shanghai Univ, Sch Commun & Informat Engn, Shanghai 200444, Peoples R China.
通讯机构:
[Zhang, Y ] S;Shanghai Polytech Univ, Sch Econ & Management, Shanghai 201209, Peoples R China.
关键词:
Human presence sensing;Machine learning;Non-contact;Wireless perception
摘要:
In the swiftly evolving landscape of Internet of Things (IoT) technology, the demand for adaptive non-contact sensing has seen a considerable surge. Traditional human perception technologies, such as vision-based approaches, often grapple with problems including lack of sensor versatility and sub-optimal accuracy. To address these issues, this paper introduces a novel, non-contact method for human presence perception, relying on WiFi. This innovative approach involves a sequential process, beginning with the pre-processing of collected Channel State Information (CSI), followed by feature extraction, and finally, classification. By establishing signal models that correspond to varying states, this method enables the accurate perception and recognition of human presence. Remarkably, this technique exhibits a high level of precision, with sensing accuracy reaching up to 99%\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\%$$\end{document}. The potential applications of this approach are extensive, proving to be particularly beneficial in contexts such as smart homes and healthcare, amongst various other everyday scenarios. This underscores the significant role this novel method could play in enhancing the sophistication and effectiveness of human presence detection and recognition systems in the IoT era.
作者机构:
[Liu, Hui] Cent China Normal Univ, Sch Comp Sci, Wuhan 430079, Peoples R China.;[Liu, Hui] Cent China Normal Univ, Hubei Prov Key Lab Artificial Intelligence & Smart, Wuhan 430079, Peoples R China.;[Guo, Jiabao; Zhao, Bo] Wuhan Univ, Sch Cyber Sci & Engn, Wuhan 430072, Peoples R China.;[Zhang, Kehuan] Chinese Univ Hong Kong, Coll Informat Engn, Hong Kong 999077, Peoples R China.;[Liu, Peng] Penn State Univ, Coll Informat Sci & Technol, State Coll, PA 16801 USA.
通讯机构:
[Liu, H ] C;Cent China Normal Univ, Sch Comp Sci, Wuhan 430079, Peoples R China.;Cent China Normal Univ, Hubei Prov Key Lab Artificial Intelligence & Smart, Wuhan 430079, Peoples R China.
关键词:
Deep neural networks;Adversarial examples;Adversarial detection;Autoencoder;Isolation forest
摘要:
Although deep neural networks (DNNs) have performed well on many perceptual tasks, they are vulnerable to adversarial examples that are generated by adding slight but maliciously crafted perturbations to benign images. Adversarial detection is an important technique for identifying adversarial examples before they are entered into target DNNs. Previous studies that were performed to detect adversarial examples either targeted specific attacks or required expensive computation. Designing a lightweight unsupervised detector is still a challenging problem. In this paper, we propose an AutoEncoder-based Adversarial Examples (AEAE) detector that can guard DNN models by detecting adversarial examples with low computation in an unsupervised manner. The AEAE includes only a shallow autoencoder that performs two roles. First, a well-trained autoencoder has learned the manifold of benign examples. This autoencoder can produce a large reconstruction error for adversarial images with large perturbations, so we can detect significantly perturbed adversarial examples based on the reconstruction error. Second, the autoencoder can filter out small noises and change the DNN's prediction on adversarial examples with small perturbations. It helps to detect slightly perturbed adversarial examples based on the prediction distance. To cover these two cases, we utilize the reconstruction error and prediction distance from benign images to construct a two-tuple feature set and train an adversarial detector using the isolation forest algorithm. We show empirically that AEAE is an unsupervised and inexpensive detector against most state-of-the-art attacks. Through the detection in these two cases, there is nowhere to hide adversarial examples.
作者机构:
[Zhang, Miao] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan 430079, Peoples R China.;[Zhang, Miao; He, Tingting; Dong, Ming; Dong, M] Cent China Normal Univ, Hubei Prov Key Lab Artificial Intelligence & Smart, Wuhan 430079, Peoples R China.;[Zhang, Miao; He, Tingting; Dong, Ming; Dong, M] Cent China Normal Univ, Natl Language Resources Monitoring & Res Ctr Netwo, Wuhan 430079, Peoples R China.;[He, Tingting; Dong, Ming; Dong, M] Cent China Normal Univ, Sch Comp, Wuhan 430079, Peoples R China.
通讯机构:
[He, TT; Dong, M ] C;Cent China Normal Univ, Hubei Prov Key Lab Artificial Intelligence & Smart, Wuhan 430079, Peoples R China.;Cent China Normal Univ, Natl Language Resources Monitoring & Res Ctr Netwo, Wuhan 430079, Peoples R China.;Cent China Normal Univ, Sch Comp, Wuhan 430079, Peoples R China.
摘要:
Commonsense question answering (CQA) requires understanding and reasoning over QA context and related commonsense knowledge, such as a structured Knowledge Graph (KG). Existing studies combine language models and graph neural networks to model inference. However, traditional knowledge graph are mostly concept-based, ignoring direct path evidence necessary for accurate reasoning. In this paper, we propose MRGNN (Meta-path Reasoning Graph Neural Network), a novel model that comprehensively captures sequential semantic information from concepts and paths. In MRGNN, meta-paths are introduced as direct inference evidence and an original graph neural network is adopted to aggregate features from both concepts and paths simultaneously. We conduct sufficient experiments on the CommonsenceQA and OpenBookQA datasets, showing the effectiveness of MRGNN. Also, we conduct further ablation experiments and explain the reasoning behavior through the case study.
关键词:
Semantic processing;Word sense disambiguation;Anaphora resolution;Named entity recognition;Concept extraction;Subjectivity detection
摘要:
Semantic processing is a fundamental research domain in computational linguistics. In the era of powerful pre-trained language models and large language models, the advancement of research in this domain appears to be decelerating. However, the study of semantics is multi-dimensional in linguistics. The research depth and breadth of computational semantic processing can be largely improved with new technologies. In this survey, we analyzed five semantic processing tasks, e.g., word sense disambiguation, anaphora resolution, named entity recognition, concept extraction, and subjectivity detection. We study relevant theoretical research in these fields, advanced methods, and downstream applications. We connect the surveyed tasks with downstream applications because this may inspire future scholars to fuse these low-level semantic processing tasks with high-level natural language processing tasks. The review of theoretical research may also inspire new tasks and technologies in the semantic processing domain. Finally, we compare the different semantic processing techniques and summarize their technical trends, application trends, and future directions.
作者机构:
[Zhang, Ze; Cui, Jianqun; Hsu, Chingfang; Zhao, Zhuo] Cent China Normal Univ, Comp Sch, Wuhan 430079, Peoples R China.;[Au, Man Ho] Hong Kong Polytech Univ, Dept Comp, Hong Kong 25809, Peoples R China.;[Harn, Lein] Univ Missouri Kansas City, Dept Comp Sci Elect Engn, Kansas City, MO 64110 USA.;[Xia, Zhe] Wuhan Univ Technol, Dept Comp Sci, Wuhan 430079, Peoples R China.
通讯机构:
[Hsu, CF ] C;Cent China Normal Univ, Comp Sch, Wuhan 430079, Peoples R China.
关键词:
Internet of Drones;Lightweight;Mutual authentication;Physical unclonable functions;UAVs;ROR;AVISPA
摘要:
In recent years, the industry and research have cast great attention to the Internet of Drones (IoD), which is becoming progressively popular since it can bring a great convenience to various application scenarios, such as national map exploration, public safety monitoring and automated military applications. In these scenarios, Unmanned Aerial Vehicles (UAVs) (called drones) will be used to collect private information. Due to the fact that the private information are very sensitive, and drones working in public places easily suffer from physical capture or tampering attacks, the primary concern is that this information could be collected by adversaries or unauthorized users. In addition, as resource-constrained devices, drones are mostly equipped with small memory and have limited computing power. Therefore, how to ensure robust security as much as possible while achieving lightweight computing and communication costs has become an urgent problem to be solved in this field. In this paper, we propose A PUF-based Robust and Lightweight Authentication Protocol for Drone-Gateway and Drone-Drone Communication (PRLAP-IoD) to address these issues. Both formal security validation using conventional tools (ROR Model and AVISPA) and other informal security analysis clearly demonstrate that PRLAP-IoD can not only provide physical security, but also defend against a variety of known attacks. Finally, compared with the recent Authentication and Key Agreement (AKA) schemes, PRLAP-IoD can attain a delicate balance between computation cost and communication cost in IoD environment.
摘要:
Traffic prediction is vital to traffic planning, control, and optimization, which is necessary for intelligent traffic management. Existing methods mostly capture spatiotemporal correlations on a fine-grained traffic graph, which cannot make full use of cluster information in coarse-grained traffic graph. However, the flow variation of clusters in the coarse-grained traffic graph is more stable compared with nodes in the fine-grained traffic graph. And the flow variation of a fine-grained node is generally consistent with the trend of the cluster to which the node belongs. Thus information in the coarse-grained traffic graph can guide feature learning in the fine-grained traffic graph. To this end, we propose a Spatiotemporal Multiscale Graph Convolutional Network (SMGCN) that explores spatiotemporal correlations on a multiscale graph. Specifically, given a fine-grained traffic graph, we first generate a coarse-grained traffic graph by graph clustering, and extract spatiotemporal correlations on both fine-grained and coarse-grained traffic graphs. Then we propose a cross-scale fusion (CF) to implement information diffusion between the fine-grained and coarse-grained traffic graphs. Moreover, we employ an adaptive dynamic graph convolution network to mine both static and dynamic spatial features. We evaluate SMGCN on real-world datasets and obtain a 1.18% -3.32% improvement over state-of-the-arts.
摘要:
Abstract Event detection plays an essential role in the task of event extraction. It aims at identifying event trigger words in a sentence and classifying event types. Generally, multiple event types are usually well‐organized with a hierarchical structure in real‐world scenarios, and hierarchical correlations between event types can be used to enhance event detection performance. However, such kind of hierarchical information has received insufficient attention which can lead to misclassification between multiple event types. In addition, the most existing methods perform event detection in Euclidean space, which cannot adequately represent hierarchical relationships. To address these issues, we propose a novel event detection network HyperED which embeds the event context and types in Poincaré ball of hyperbolic geometry to help learn hierarchical features between events. Specifically, for the event detection context, we first leverage the pre‐trained BERT or BiLSTM in Euclidean space to learn the semantic features of ED sentences. Meanwhile, to make full use of the dependency knowledge, a GNN‐based model is applied when encoding event types to learn the correlations between events. Then we use a simple neural‐based transformation to project the embeddings into the Poincaré ball to capture hierarchical features, and a distance score in hyperbolic space is computed for prediction. The experiments on MAVEN and ACE 2005 datasets indicate the effectiveness of the HyperED model and prove the natural advantages of hyperbolic spaces in expressing hierarchies in an intuitive way.
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.
关键词:
Session-based recommendation;hypergraph neural networks;additional information;heterogeneous hypergraphs;information loss
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.
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.
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:
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:
With the development of information networks, the entities from different network domains interact with each other more and more frequently. Therefore, identity management and authentication are essential in cross-domain setting. The traditional Public Key Infrastructure (PKI) architecture has some problems, including single point of failure, inefficient certificate revocation status management and also lack of privacy protection, which cannot meet the demand of cross-domain identity authentication. Blockchain is suitable for multi-participant collaboration in multi-trust domain scenarios. In this paper, a cross-domain certificate management scheme CD-BCM based on the consortium blockchain is proposed. For the issue of Certificate Authority’s single point of failure, we design a multi-signature algorithm. In addition, we propose a unified structure for batch certificates verification and conversion, which improve the efficiency of erroneous certificate identification. Finally, by comparing with current related schemes, our scheme achieves good functionality and scalability in the scenario of cross-domain certificate management.
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:
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.