Query：
学者姓名：程红举
Refining：
Year
Type
Indexed by
Source
Complex
Former Name
Co-
Language
Clean All
Abstract ：
Shared information refers to the common semantic information across multiple modalities, and complementary information refers to modality-specific information that complements other modalities. How to fully utilize this information is a key issue in the multimodal sentiment analysis. In this paper, we first propose a Slice Aggregation (SA) algorithm to address the issue of correlation over time. We use sliding windows to calculate the horizontal and vertical correlations, and then aggregate slices into a series of chunks, each represents a set of successive slices with consistent correlation. Second, we introduce a Dynamic Fusion (DF) strategy comprising two components: shared information fusion and complementary information fusion. The former utilizes a multilayer perceptron (MLP) to extract high-level shared representations, whereas the latter employs a cross-modal multi-head attention mechanism to fuse low-level complementary information. Finally, we propose an SA-DF framework where SA organizes raw slices into correlation-consistent chunks, and DF progressively fuses features across these chunks. The concatenated fused features are used for final sentiment prediction. The experiments on CMU-MOSI and CH-SIMS datasets show that the proposed SA-DF can achieve the best performance on sentiment analysis tasks when compared with the state-of-the-art baselines. © China Computer Federation (CCF) 2025.
Keyword ：
Cross-modal multi-head attention Cross-modal multi-head attention Dynamic fusion Dynamic fusion Modal correlation Modal correlation Multimodal sentiment analysis Multimodal sentiment analysis Slice aggregation Slice aggregation
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhan, Z. , Cao, D. , Chen, Z. et al. Multimodal sentiment analysis based on slice aggregation and dynamic fusion [J]. | CCF Transactions on Pervasive Computing and Interaction , 2025 . |
| MLA | Zhan, Z. et al. "Multimodal sentiment analysis based on slice aggregation and dynamic fusion" . | CCF Transactions on Pervasive Computing and Interaction (2025) . |
| APA | Zhan, Z. , Cao, D. , Chen, Z. , Cheng, H. , Yu, Z. . Multimodal sentiment analysis based on slice aggregation and dynamic fusion . | CCF Transactions on Pervasive Computing and Interaction , 2025 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Multimodal emotion recognition effectively uses cross-modal information to enhance model performance. However, in practical applications, the missing modalities issue often degrades emotion recognition accuracy due to the modality gap arising from differences in information representation and semantic inconsistencies across modalities. To address this challenge, this paper introduces a specific and invariant feature learning approach(SIFL). Specifically, we employ feature extraction techniques using a self-attention mechanism for modality-specific features and leverage a denoising autoencoder for invariant feature extraction to enhance semantic richness and expressiveness. Additionally, we develop a reconstruction network to generate high-quality modality features. To further optimize the process, we design and implement multiple optimization objectives, effectively bridging the semantic gap between modalities. Experimental results on the CMU-MOSI dataset demonstrate that the proposed method surpasses current mainstream baselines and exhibits robust performance, particularly under conditions with high missing rates, validating its efficacy and versatility in handling missing modalities. © 2025 IEEE.
Keyword ：
Emotion Recognition Emotion Recognition Extraction Extraction Feature extraction Feature extraction Learning systems Learning systems Modal analysis Modal analysis Psychology computing Psychology computing Semantics Semantics
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhan, Zhouwen , Cao, Dongtao , Cheng, Hongju . When Sentiment Analysis Faces Missing Modalities: A Specific and Invariant Feature Learning Approach [C] . 2025 : 533-537 . |
| MLA | Zhan, Zhouwen et al. "When Sentiment Analysis Faces Missing Modalities: A Specific and Invariant Feature Learning Approach" . (2025) : 533-537 . |
| APA | Zhan, Zhouwen , Cao, Dongtao , Cheng, Hongju . When Sentiment Analysis Faces Missing Modalities: A Specific and Invariant Feature Learning Approach . (2025) : 533-537 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Anomaly traffic detection offers essential technical support for securing Mobile Edge Computing (MEC) networks. The emerging Large Model (LM) has attracted much attention for their excellent data generation and processing capabilities, but it is difficult to deploy LM-based detection models in resource-constrained MEC networks. Existing solutions usually compress large models into tiny ones, but they tend to be impacted by data drift, resulting in decreased detection accuracy. To address this key challenge, we propose CL4Det, a novel multi-model anomaly traffic detection framework with LM-powered continuous learning, where the tiny models deployed in MEC networks can achieve the desired performance comparable to the large models via continuous retraining. Specifically, CL4Det periodically evaluates the model performance degradation caused by data drift in MEC networks and decides whether to generate retraining tasks and their configurations. Meanwhile, CL4Det schedules all traffic detection and retraining tasks with proper resource allocation, aiming to ensure real-time detection and maximize model accuracy. A case study with real-world traffic datasets verifies the effectiveness and superiority of CL4Det. Finally, we outline the challenges and future directions to fully exploit the collaborative potentials of MEC networks and LM in anomaly traffic detection.
Keyword ：
Accuracy Accuracy Anomaly detection Anomaly detection Computational modeling Computational modeling Data collection Data collection Data models Data models Edge computing Edge computing Graphics processing units Graphics processing units Image edge detection Image edge detection Mobile computing Mobile computing Multi-access edge computing Multi-access edge computing Real-time systems Real-time systems Schedules Schedules Servers Servers Solid modeling Solid modeling Telecommunication traffic Telecommunication traffic Training Training
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhang, Junjie , Chen, Zheyi , Cheng, Hongju et al. Improving Multi-Model Anomaly Traffic Detection in MEC Networks With Large-Model- Powered Continuous Learning [J]. | IEEE NETWORK , 2025 , 39 (3) : 56-62 . |
| MLA | Zhang, Junjie et al. "Improving Multi-Model Anomaly Traffic Detection in MEC Networks With Large-Model- Powered Continuous Learning" . | IEEE NETWORK 39 . 3 (2025) : 56-62 . |
| APA | Zhang, Junjie , Chen, Zheyi , Cheng, Hongju , Li, Jie , Min, Geyong . Improving Multi-Model Anomaly Traffic Detection in MEC Networks With Large-Model- Powered Continuous Learning . | IEEE NETWORK , 2025 , 39 (3) , 56-62 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
In Internet of Vehicles (IoV), unmanned aerial vehicles (UAVs) assisted mobile edge computing (MEC) can improve the system performance and communication range of intelligent transportation systems (ITSs). However, the resource allocation and computation offloading in UAVs-assisted IoV systems still face huge challenges due to the growing number of vehicle terminals (VTs), potential privacy leakage, and inefficient problem-solving. Existing solutions cannot adapt to such dynamic multi-UAV scenarios and meet the real-time requirements of VTs. To address these challenges, we propose RACOMU, a novel resource allocation and collaborative offloading framework for multi-UAV-assisted IoV. First, we introduce the convex optimization theory to decouple the original problem and then obtain the near-optimal allocation of transmission power and computing resources by solving the Karush-Kuhn-Tucker (KKT) condition. Next, we design a new collaborative offloading strategy with federated deep reinforcement learning (FDRL), where the offloading requests from VTs are processed in a distributed manner to approach the global optimum while preserving data privacy. Extensive experiments verify the effectiveness of the proposed RACOMU. Compared to benchmark methods, RACOMU achieves better performance in terms of task processing latency, decision-making time, and load balancing degree under various scenarios.
Keyword ：
Autonomous aerial vehicles Autonomous aerial vehicles Collaboration Collaboration Computational modeling Computational modeling Computation offloading Computation offloading convex optimization convex optimization Delays Delays Energy consumption Energy consumption federated deep reinforcement learning (FDRL) federated deep reinforcement learning (FDRL) Internet of Vehicles (IoV) Internet of Vehicles (IoV) Real-time systems Real-time systems resource allocation resource allocation Resource management Resource management Servers Servers System performance System performance Training Training
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Chen, Zheyi , Huang, Zhiqin , Zhang, Junjie et al. Resource Allocation and Collaborative Offloading in Multi-UAV-Assisted IoV With Federated Deep Reinforcement Learning [J]. | IEEE INTERNET OF THINGS JOURNAL , 2025 , 12 (5) : 4629-4640 . |
| MLA | Chen, Zheyi et al. "Resource Allocation and Collaborative Offloading in Multi-UAV-Assisted IoV With Federated Deep Reinforcement Learning" . | IEEE INTERNET OF THINGS JOURNAL 12 . 5 (2025) : 4629-4640 . |
| APA | Chen, Zheyi , Huang, Zhiqin , Zhang, Junjie , Cheng, Hongju , Li, Jie . Resource Allocation and Collaborative Offloading in Multi-UAV-Assisted IoV With Federated Deep Reinforcement Learning . | IEEE INTERNET OF THINGS JOURNAL , 2025 , 12 (5) , 4629-4640 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Sentiment analysis plays an indispensable part in human-computer interaction. Multimodal sentiment analysis can overcome the shortcomings of unimodal sentiment analysis by fusing multimodal data. However, how to extracte improved feature representations and how to execute effective modality fusion are two crucial problems in multimodal sentiment analysis. Traditional work uses simple sub-models for feature extraction, and they ignore features of different scales and fuse different modalities of data equally, making it easier to incorporate extraneous information and affect analysis accuracy. In this paper, we propose a Multimodal Sentiment Analysis model based on Multi-scale feature extraction and Multi-task learning (M(3)SA). First, we propose a multi-scale feature extraction method that models the outputs of different hidden layers with the method of channel attention. Second, a multimodal fusion strategy based on the key modality is proposed, which utilizes the attention mechanism to raise the proportion of the key modality and mines the relationship between the key modality and other modalities. Finally, we use the multi-task learning approach to train the proposed model, ensuring that the model can learn better feature representations. Experimental results on two publicly available multimodal sentiment analysis datasets demonstrate that the proposed method is effective and that the proposed model outperforms baselines.
Keyword ：
multimodal data fusion multimodal data fusion Multimodal sentiment analysis Multimodal sentiment analysis multi-scale feature extraction multi-scale feature extraction Multitasking Multitasking multi-task learning multi-task learning
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lin, Changkai , Cheng, Hongju , Rao, Qiang et al. M3SA: Multimodal Sentiment Analysis Basedon Multi-Scale Feature Extraction andMulti-Task Learning [J]. | IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING , 2024 , 32 : 1416-1429 . |
| MLA | Lin, Changkai et al. "M3SA: Multimodal Sentiment Analysis Basedon Multi-Scale Feature Extraction andMulti-Task Learning" . | IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING 32 (2024) : 1416-1429 . |
| APA | Lin, Changkai , Cheng, Hongju , Rao, Qiang , Yang, Yang . M3SA: Multimodal Sentiment Analysis Basedon Multi-Scale Feature Extraction andMulti-Task Learning . | IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING , 2024 , 32 , 1416-1429 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Edge computing is an emerging promising computing paradigm, which can significantly reduce the service latency by moving computing and storage demands to the edge of the network. Resource -constrained edge servers may fail to process multiple tasks simultaneously when several time -delay -sensitive and computationally demanding tasks are offloaded to only one edge server, and results in some issues such as high task processing costs. In this paper, we introduce a novel idea by dividing one task into several sub -tasks via the dependencies within the task and then offloading the sub -tasks to other edge servers in light of high concurrency for synchronization to minimize the total cost of task processing. To address the challenge of task dependencies and adaptation to dynamic scenes, we propose a Multi -Task Dependency Offloading Algorithm (MTDOA) based on deep reinforcement learning. The task offloading decision is modeled as a Markov decision process, and then a graph attention network is applied to extract the dependency information of different tasks, while LSTM and DQN are combined to deal with sequential problems. The simulation results show that the proposed MTDOA has better convergence ability compared with the baseline algorithms.
Keyword ：
Deep reinforcement learning Deep reinforcement learning Edge computing Edge computing Graph attention network Graph attention network Multi-task dependency Multi-task dependency Task offloading Task offloading
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhang, Xiaoqi , Lin, Tengxiang , Lin, Cheng-Kuan et al. Computational task offloading algorithm based on deep reinforcement learning and multi-task dependency [J]. | THEORETICAL COMPUTER SCIENCE , 2024 , 993 . |
| MLA | Zhang, Xiaoqi et al. "Computational task offloading algorithm based on deep reinforcement learning and multi-task dependency" . | THEORETICAL COMPUTER SCIENCE 993 (2024) . |
| APA | Zhang, Xiaoqi , Lin, Tengxiang , Lin, Cheng-Kuan , Chen, Zhen , Cheng, Hongju . Computational task offloading algorithm based on deep reinforcement learning and multi-task dependency . | THEORETICAL COMPUTER SCIENCE , 2024 , 993 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
More vehicles are connecting to the Internet of Things (IoT), transforming Vehicle Ad hoc Networks (VANETs) into the Internet of Vehicles (IoV), providing a more environmentally friendly and safer driving experience. Vehicular announcement networks show promise in vehicular communication applications. However, two major issues arise when establishing such a system. First, user privacy cannot be guaranteed when messages are forwarded anonymously, thus the reliability of these messages is in question. Second, users often lack interest in responding to announcements. To address these problems, we introduce a Blockchain-based incentive announcement system called PIAS. This system enables anonymous message commitment in a semi-trusted environment and encourages witnesses to respond to requests for traffic information. Additionally, PIAS uses blockchain accounts as identities to participate in the system with incentives, ensuring privacy in anonymous announcements. PIAS successfully protects the privacy of participants and motivates witnesses to respond to requests. Furthermore, our assessment of security and compatibility shows that PIAS can maintain privacy and incentivization while being compatible with both the Bitcoin and Ethereum blockchains. Further evaluation has confirmed the system's efficiency in terms of performance.
Keyword ：
Authentication Authentication Bitcoin Bitcoin blockchain blockchain Blockchains Blockchains fair payment fair payment incentive mechanism incentive mechanism Internet of Vehicles Internet of Vehicles Internet of Vehicles (IoV) Internet of Vehicles (IoV) Privacy Privacy privacy preservation privacy preservation Protocols Protocols Reliability Reliability
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhan, Yonghua , Yang, Yang , Cheng, Hongju et al. PIAS: Privacy-Preserving Incentive Announcement System Based on Blockchain for Internet of Vehicles [J]. | IEEE TRANSACTIONS ON SERVICES COMPUTING , 2024 , 17 (5) : 2762-2775 . |
| MLA | Zhan, Yonghua et al. "PIAS: Privacy-Preserving Incentive Announcement System Based on Blockchain for Internet of Vehicles" . | IEEE TRANSACTIONS ON SERVICES COMPUTING 17 . 5 (2024) : 2762-2775 . |
| APA | Zhan, Yonghua , Yang, Yang , Cheng, Hongju , Luo, Xiangyang , Guan, Zhangshuang , Deng, Robert H. . PIAS: Privacy-Preserving Incentive Announcement System Based on Blockchain for Internet of Vehicles . | IEEE TRANSACTIONS ON SERVICES COMPUTING , 2024 , 17 (5) , 2762-2775 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
With flexible mobility and broad communication coverage, unmanned aerial vehicles (UAVs) have become an important extension of multiaccess edge computing (MEC) systems, exhibiting great potential for improving the performance of federated graph learning (FGL). However, due to the limited computing and storage resources of UAVs, they may not well handle the redundant data and complex models, causing the inference inefficiency of FGL in UAV-assisted MEC systems. To address this critical challenge, we propose a novel LightWeight FGL framework, named LW-FGL, to accelerate the inference speed of classification models in UAV-assisted MEC systems. Specifically, we first design an adaptive information bottleneck (IB) principle, which enables UAVs to obtain well-compressed worthy subgraphs by filtering out the information that is irrelevant to downstream classification tasks. Next, we develop improved tiny graph neural networks (GNNs), which are used as the inference models on UAVs, thus reducing the computational complexity and redundancy. Using real-world graph data sets, extensive experiments are conducted to validate the effectiveness of the proposed LW-FGL. The results show that the LW-FGL achieves higher classification accuracy and faster inference speed than state-of-the-art methods.
Keyword ：
Autonomous aerial vehicles Autonomous aerial vehicles Biological system modeling Biological system modeling Classification inference Classification inference Computational modeling Computational modeling Data models Data models federated graph learning (FGL) federated graph learning (FGL) Graph neural networks Graph neural networks lightweight model lightweight model multiaccess edge computing (MEC) multiaccess edge computing (MEC) Task analysis Task analysis Training Training unmanned aerial vehicle (UAV) unmanned aerial vehicle (UAV)
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhong, Luying , Chen, Zheyi , Cheng, Hongju et al. Lightweight Federated Graph Learning for Accelerating Classification Inference in UAV-Assisted MEC Systems [J]. | IEEE INTERNET OF THINGS JOURNAL , 2024 , 11 (12) : 21180-21190 . |
| MLA | Zhong, Luying et al. "Lightweight Federated Graph Learning for Accelerating Classification Inference in UAV-Assisted MEC Systems" . | IEEE INTERNET OF THINGS JOURNAL 11 . 12 (2024) : 21180-21190 . |
| APA | Zhong, Luying , Chen, Zheyi , Cheng, Hongju , Li, Jie . Lightweight Federated Graph Learning for Accelerating Classification Inference in UAV-Assisted MEC Systems . | IEEE INTERNET OF THINGS JOURNAL , 2024 , 11 (12) , 21180-21190 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
As a key technique for future networks, the performance of emerging multi-edge caching is often limited by inefficient collaboration among edge nodes and improper resource configuration. Meanwhile, achieving optimal cache hit rates poses substantive challenges without effectively capturing the potential relations between discrete user features and diverse content libraries. These challenges become further sophisticated when caching schemes are exposed to adversarial attacks that seriously impair cache performance. To address these challenges, we introduce RoCoCache, a resilient collaborative caching framework that uniquely integrates robust federated deep learning with proactive caching strategies, enhancing performance under adversarial conditions. First, we design a novel partitioning mechanism for multi-dimensional cache space, enabling precise content recommendations in user classification intervals. Next, we develop a new Discrete-Categorical Variational Auto-Encoder (DC-VAE) to accurately predict content popularity by overcoming posterior collapse. Finally, we create an original training mode and proactive cache replacement strategy based on robust federated deep learning. Notably, the residual-based detection for adversarial model updates and similarity-based federated aggregation are integrated to avoid the model destruction caused by adversarial updates, which enables the proactive cache replacement adapting to optimized cache resources and thus enhances cache performance. Using the real-world testbed and datasets, extensive experiments verify that the RoCoCache achieves higher cache hit rates and efficiency than state-of-the-art methods while ensuring better robustness. Moreover, we validate the effectiveness of the components designed in RoCoCache for improving cache performance via ablation studies.
Keyword ：
cache space partitioning cache space partitioning content popularity prediction content popularity prediction Multi-edge collaborative caching Multi-edge collaborative caching proactive cache replacement proactive cache replacement robust federated deep learning robust federated deep learning
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Chen, Zheyi , Liang, Jie , Yu, Zhengxin et al. Resilient Collaborative Caching for Multi-Edge Systems With Robust Federated Deep Learning [J]. | IEEE-ACM TRANSACTIONS ON NETWORKING , 2024 , 33 (2) : 654-669 . |
| MLA | Chen, Zheyi et al. "Resilient Collaborative Caching for Multi-Edge Systems With Robust Federated Deep Learning" . | IEEE-ACM TRANSACTIONS ON NETWORKING 33 . 2 (2024) : 654-669 . |
| APA | Chen, Zheyi , Liang, Jie , Yu, Zhengxin , Cheng, Hongju , Min, Geyong , Li, Jie . Resilient Collaborative Caching for Multi-Edge Systems With Robust Federated Deep Learning . | IEEE-ACM TRANSACTIONS ON NETWORKING , 2024 , 33 (2) , 654-669 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
By effectively assigning and migrating tasks based on service requirements, the success rate of task execution in cloud-edge-end collaborative computing can be significantly enhanced, thereby ensuring the provision of high-quality services for users. The majority of conventional cloud-edge-end task offloading approaches primarily focus on static scenarios, posing challenges in ensuring the success rate of task execution in mobile scenarios. It is imperative to address the problem of constructing a joint optimization scheme for task allocation and migration that is suitable for mobile scenarios. This paper re-define the latency, energy, and migration model for task processing in mobile scenarios. Furthermore, we propose a Deep Reinforcement learning (DRL)-based Task allocation and Migration optimization algorithm (DRTM) to enhance the efficiency of task completion and minimize the total cost. DRTM introduces the traditional Actor-Critic with a mirror deep deterministic policy gradient (DDPG) and establishes a duel Q-network to update parameters on respective gradients for optimal policy acquisition. DRTM incorporates two target networks to effectively improve stability and convergence speed during training while reducing computational complexity. The experimental results demonstrate that DRTM can offer a high-performance task assignment and migration scheme in mobile scenarios, thereby significantly reducing the total cost of the task execution life cycle. © 2023 IEEE.
Keyword ：
Computation offloading Computation offloading Deep learning Deep learning Life cycle Life cycle Reinforcement learning Reinforcement learning
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhang, Xiaoqi , Cheng, Hongju . Joint Task Assignment and Migration in Cloud-Edge-End Collaborative Computing Based on DRL [C] . 2023 : 265-270 . |
| MLA | Zhang, Xiaoqi et al. "Joint Task Assignment and Migration in Cloud-Edge-End Collaborative Computing Based on DRL" . (2023) : 265-270 . |
| APA | Zhang, Xiaoqi , Cheng, Hongju . Joint Task Assignment and Migration in Cloud-Edge-End Collaborative Computing Based on DRL . (2023) : 265-270 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
