arXiv subjects

Zhishu Shen

Publications and source records attributed to Zhishu Shen.

28 records · Page 2Linked to original sources

arXiv2024

Learning from Heterogeneity: A Dynamic Learning Framework for Hypergraphs

Graph neural network (GNN) has gained increasing popularity in recent years owing to its capability and flexibility in modeling complex graph structure data. Among all graph learning methods, hypergraph learning is a technique for exploring the implicit higher-order correlations when training the embedding space of the graph. In this paper, we propose a hypergraph learning framework named LFH that is capable of dynamic hyperedge construction and attentive embedding update utilizing the heterogeneity attributes of the graph. Specifically, in our framework, the high-quality features are first generated by the pairwise fusion strategy that utilizes explicit graph structure information when generating initial node embedding. Afterwards, a hypergraph is constructed through the dynamic grouping of implicit hyperedges, followed by the type-specific hypergraph learning process. To evaluate the effectiveness of our proposed framework, we conduct comprehensive experiments on several popular datasets with eleven state-of-the-art models on both node classification and link prediction tasks, which fall into categories of homogeneous pairwise graph learning, heterogeneous pairwise graph learning, and hypergraph learning. The experiment results demonstrate a significant performance gain (average 12.5% in node classification and 13.3% in link prediction) compared with recent state-of-the-art methods.

cs.LG↗

arXiv2024

Energy Efficient Offloading Policies in Multi-Access Edge Computing Systems with Task Handover

The rapid growth of mobile devices and the increasing complexity of tasks have made energy efficiency a critical challenge in Multi-Access Edge Computing (MEC) systems. This paper explores energy-efficient offloading strategies in large-scale MEC systems with heterogeneous mobile users, diverse network components, and frequent task handovers to capture user mobility. The problem is inherently complex due to the system's scale, task and resource diversity, and the need to maintain real-time performance. Traditional optimization approaches are often computationally infeasible for such scenarios. To tackle these challenges, we model the offloading problem using the restless multi-armed bandit (RMAB) framework and develop two scalable online policies that prioritize resources based on their marginal costs. The proposed policies dynamically adapt to the system's heterogeneity and mobility while ensuring near-optimal energy efficiency. Through extensive numerical simulations, we demonstrate that the policies significantly outperform baseline methods in power conservation and show robust performance under non-exponentially distributed task lifespans. These results highlight the practical applicability and scalability of our approach in dynamic MEC environments.

cs.DC↗

arXiv2024

GRL-Prompt: Towards Knowledge Graph based Prompt Optimization via Reinforcement Learning

Large language models (LLMs) have demonstrated impressive success in a wide range of natural language processing (NLP) tasks due to their extensive general knowledge of the world. Recent works discovered that the performance of LLMs is heavily dependent on the input prompt. However, prompt engineering is usually done manually in a trial-and-error fashion, which can be labor-intensive and challenging in order to find the optimal prompts. To address these problems and unleash the utmost potential of LLMs, we propose a novel LLMs-agnostic framework for prompt optimization, namely GRL-Prompt, which aims to automatically construct optimal prompts via reinforcement learning (RL) in an end-to-end manner. To provide structured action/state representation for optimizing prompts, we construct a knowledge graph (KG) that better encodes the correlation between the user query and candidate in-context examples. Furthermore, a policy network is formulated to generate the optimal action by selecting a set of in-context examples in a rewardable order to construct the prompt. Additionally, the embedding-based reward shaping is utilized to stabilize the RL training process. The experimental results show that GRL-Prompt outperforms recent state-of-the-art methods, achieving an average increase of 0.10 in ROUGE-1, 0.07 in ROUGE-2, 0.07 in ROUGE-L, and 0.05 in BLEU.

cs.CL↗

arXiv2024

Collaborative UAVs Multi-task Video Processing Optimization Based on Enhanced Distributed Actor-Critic Networks

With the rapid advancement of the Internet of Things (IoT) and Artificial Intelligence (AI), intelligent information services are being increasingly integrated across various sectors, including healthcare, industry, and transportation. Traditional solutions rely on centralized cloud processing, which encounters considerable challenges in fulfilling the Quality of Service (QoS) requirements of Computer Vision (CV) tasks generated in the resource-constrained infrastructure-less environments. In this paper, we introduce a distributed framework called CoUAV-Pro for multi-task video processing powered by Unmanned Aerial Vehicles (UAVs). This framework empowers multiple UAVs to meet the service demands of various computer vision (CV) tasks in infrastructure-less environments, thereby eliminating the need for centralized processing. Specifically, we develop a novel task allocation algorithm that leverages enhanced distributed actor-critic networks within CoUAV-Pro, aiming to optimize task processing efficiency while contending with constraints associated with UAV's energy, computational, and communication resources. Comprehensive experiments demonstrate that our proposed solution achieves satisfactory performance levels against those of centralized methods across key metrics including task acquisition rates, task latency, and energy consumption.

cs.DC↗

arXiv2024

A Sharded Blockchain-Based Secure Federated Learning Framework for LEO Satellite Networks

Low Earth Orbit (LEO) satellite networks are increasingly essential for space-based artificial intelligence (AI) applications. However, as commercial use expands, LEO satellite networks face heightened cyberattack risks, especially through satellite-to-satellite communication links, which are more vulnerable than ground-based connections. As the number of operational satellites continues to grow, addressing these security challenges becomes increasingly critical. Traditional approaches, which focus on sending models to ground stations for validation, often overlook the limited communication windows available to LEO satellites, leaving critical security risks unaddressed. To tackle these challenges, we propose a sharded blockchain-based federated learning framework for LEO networks, called SBFL-LEO. This framework improves the reliability of inter-satellite communications using blockchain technology and assigns specific roles to each satellite. Miner satellites leverage cosine similarity (CS) and Density-Based Spatial Clustering of Applications with Noise (DBSCAN) to identify malicious models and monitor each other to detect inaccurate aggregated models. Security analysis and experimental results demonstrate that our approach outperforms baseline methods in both model accuracy and energy efficiency, significantly enhancing system robustness against attacks.

cs.CR↗

arXiv2024

HyperSMOTE: A Hypergraph-based Oversampling Approach for Imbalanced Node Classifications

Hypergraphs are increasingly utilized in both unimodal and multimodal data scenarios due to their superior ability to model and extract higher-order relationships among nodes, compared to traditional graphs. However, current hypergraph models are encountering challenges related to imbalanced data, as this imbalance can lead to biases in the model towards the more prevalent classes. While the existing techniques, such as GraphSMOTE, have improved classification accuracy for minority samples in graph data, they still fall short when addressing the unique structure of hypergraphs. Inspired by SMOTE concept, we propose HyperSMOTE as a solution to alleviate the class imbalance issue in hypergraph learning. This method involves a two-step process: initially synthesizing minority class nodes, followed by the nodes integration into the original hypergraph. We synthesize new nodes based on samples from minority classes and their neighbors. At the same time, in order to solve the problem on integrating the new node into the hypergraph, we train a decoder based on the original hypergraph incidence matrix to adaptively associate the augmented node to hyperedges. We conduct extensive evaluation on multiple single-modality datasets, such as Cora, Cora-CA and Citeseer, as well as multimodal conversation dataset MELD to verify the effectiveness of HyperSMOTE, showing an average performance gain of 3.38% and 2.97% on accuracy, respectively.

cs.LG↗

arXiv2024

Unleashing Collaborative Computing for Adaptive Video Streaming with Multi-objective Optimization in Satellite Terrestrial Networks

Satellite-terrestrial networks (STNs) are anticipated to deliver seamless IoT services across expansive regions. Given the constrained resources available for offloading computationally intensive tasks like video streaming, it is crucial to establish collaborative computing among diverse components within STNs. In this paper, we present the task offloading challenge as a multi-objective optimization problem, leveraging the collaboration between ground devices/users and satellites. We propose a collaborative computing scheme that optimally assigns computing tasks to various nodes within STNs to enhance service performance including quality of experience (QoE). This algorithm initially dynamically selects an end-to-end path that balances service time and resource utilization. For each selected path, a multi-agent soft actor-critic (MA-SAC)-based algorithm is introduced to make adaptive decisions and collaboratively assign optimal heterogeneous resources to the given computing tasks. In this algorithm, the ground station bridging satellite network and terrestrial network is treated as agent to extract the information from both STNs and users. Through MA-SAC, multiple agents cooperate to determine the adaptive bitrate and network resources for the arriving tasks. The numerical results demonstrate that our proposal outperforms comparative schemes across various computing tasks in terms of various criteria.

cs.DC↗

arXiv2024

Collaborative Satellite Computing through Adaptive DNN Task Splitting and Offloading

Satellite computing has emerged as a promising technology for next-generation wireless networks. This innovative technology provides data processing capabilities, which facilitates the widespread implementation of artificial intelligence (AI)-based applications, especially for image processing tasks involving deep neural network (DNN). With the limited computing resources of an individual satellite, independently handling DNN tasks generated by diverse user equipments (UEs) becomes a significant challenge. One viable solution is dividing a DNN task into multiple subtasks and subsequently distributing them across multiple satellites for collaborative computing. However, it is challenging to partition DNN appropriately and allocate subtasks into suitable satellites while ensuring load balancing. To this end, we propose a collaborative satellite computing system designed to improve task processing efficiency in satellite networks. Based on this system, a workload-balanced adaptive task splitting scheme is developed to equitably distribute the workload of DNN slices for collaborative inference, consequently enhancing the utilization of satellite computing resources. Additionally, a self-adaptive task offloading scheme based on a genetic algorithm (GA) is introduced to determine optimal offloading decisions within dynamic network environments. The numerical results illustrate that our proposal can outperform comparable methods in terms of task completion rate, delay, and resource utilization.

cs.DC↗

arXiv2023

An Adaptive Federated Relevance Framework for Spatial Temporal Graph Learning

Spatial-temporal data contains rich information and has been widely studied in recent years due to the rapid development of relevant applications in many fields. For instance, medical institutions often use electrodes attached to different parts of a patient to analyse the electorencephal data rich with spatial and temporal features for health assessment and disease diagnosis. Existing research has mainly used deep learning techniques such as convolutional neural network (CNN) or recurrent neural network (RNN) to extract hidden spatial-temporal features. Yet, it is challenging to incorporate both inter-dependencies spatial information and dynamic temporal changes simultaneously. In reality, for a model that leverages these spatial-temporal features to fulfil complex prediction tasks, it often requires a colossal amount of training data in order to obtain satisfactory model performance. Considering the above-mentioned challenges, we propose an adaptive federated relevance framework, namely FedRel, for spatial-temporal graph learning in this paper. After transforming the raw spatial-temporal data into high quality features, the core Dynamic Inter-Intra Graph (DIIG) module in the framework is able to use these features to generate the spatial-temporal graphs capable of capturing the hidden topological and long-term temporal correlation information in these graphs. To improve the model generalization ability and performance while preserving the local data privacy, we also design a relevance-driven federated learning module in our framework to leverage diverse data distributions from different participants with attentive aggregations of their models.

cs.LG↗

arXiv2023

Exploiting Spatial-temporal Data for Sleep Stage Classification via Hypergraph Learning

Sleep stage classification is crucial for detecting patients' health conditions. Existing models, which mainly use Convolutional Neural Networks (CNN) for modelling Euclidean data and Graph Convolution Networks (GNN) for modelling non-Euclidean data, are unable to consider the heterogeneity and interactivity of multimodal data as well as the spatial-temporal correlation simultaneously, which hinders a further improvement of classification performance. In this paper, we propose a dynamic learning framework STHL, which introduces hypergraph to encode spatial-temporal data for sleep stage classification. Hypergraphs can construct multi-modal/multi-type data instead of using simple pairwise between two subjects. STHL creates spatial and temporal hyperedges separately to build node correlations, then it conducts type-specific hypergraph learning process to encode the attributes into the embedding space. Extensive experiments show that our proposed STHL outperforms the state-of-the-art models in sleep stage classification tasks.

cs.LG↗