Graph neural networks (GNNs) have shown great promise in rumor detection by leveraging user interactions and propagation structures. However, existing GNN-based methods primarily aggregate low-frequency signals, leading to oversmoothing and the loss of distinctive features in user feedback. Additionally, the data imbalance and sparsity in social media platforms hinder the training of robust detection models. To address these challenges, this article proposes the signed graph transformer network (SGTN) and supervised multiprototype contrastive learning (SMPCL) framework. SGTN adaptsively captures low-frequency similarities and high-frequency differences in user comments, effectively enhancing the representation of relationships in rumor propagation. SMPCL introduces learnable prototypes for each class, mitigating the effects of data imbalance and enabling more effective contrastive learning in small batches. Extensive experiments on real-world datasets, including Twitter15, Twitter16, and PHEME, demonstrate the superior performance of the proposed framework. SGTN and SMPCL achieve significant improvements, with the highest accuracy of 89.7% on Twitter15, 91.3% on Twitter16, and 84.3% on PHEME. Compared with state-of-the-art models, SMPCL achieves up to 3.5% F1-score gains in rumor classification tasks, showcasing its robustness and effectiveness in addressing oversmoothing and data imbalance challenges.

Large language models (LLMs) are computationally intensive. The computation workload and the memory footprint grow quadratically with the dimension (layer width). Most of LLMs' parameters come from the linear layers of the transformer structure and are highly redundant. These linear layers contribute more than 80% of the computation workload and 99% of the model size. To pretrain and finetune LLMs efficiently, there are three major challenges to address: 1) reducing redundancy of the linear layers; 2) reducing GPU memory footprint; 3) improving GPU utilization when using distributed training. Prior methods, such as LoRA and QLoRA, utilized low-rank structure and quantization to reduce the number of trainable parameters and model size, respectively. However, the resulting model still consumes a large amount of GPU memory. In this paper, we present high-performance GPU-based methods for both pretraining and finetuning quantized LLMs with low-rank structures. We replace a single linear layer in the transformer structure with two narrower linear layers, significantly reducing the number of parameters by several orders of magnitude. By quantizing the pretrained parameters into low precision (8-bit and 4-bit), the memory consumption of the resulting model is further reduced. Compared with existing LLMs, our methods achieve a speedup of 1.3x and a model compression ratio of 2.64 x for pretraining without accuracy drop. For finetuning, our methods achieve an average accuracy score increase of 6.3 and 24.0 in general tasks and financial tasks, respectively, and GPU memory consumption is reduced by 6.3x. The sizes of our models are smaller than 0.59 GB, allowing inference on a smartphone.

While online social media brings convenience to people’s communication, it has also caused the widespread spread of rumors and brought great harm. Recent deep-learning approaches attempt to identify rumors by engaging in interactive user feedback. However, the performance of these models suffers from insufficient and noisy labeled data. In this article, we propose a novel rumor detection model called graph contrastive learning with feature augmentation (FAGCL), which injects noise into the feature space and learns contrastively by constructing asymmetric structures. FAGCL takes user preference and news embedding as the initial features of the rumor propagation tree and then adopts a graph attention network to update node representations. To obtain the graph-level representation for rumor classification, FAGCL fuses multiple pooling techniques. Moreover, FAGCL adopts graph contrastive learning as an auxiliary task to constrain the representation consistency. Contrastive learning on noisy data mines the supervision information of the rumor propagation tree itself, making the model more robust and effective. Results on two real-world datasets demonstrate that our proposed FAGCL model achieves significant improvements over the baseline models.

Federated learning (FL) is an attractive industrial paradigm to accomplish distributed artificial intelligence (AI) training collaboratively in a data privacy-preserving manner. Most existing designs for FL systems assume that industrial user equipments (UEs) participate voluntarily in FL training. However, since both AI model training and transmission consume considerable energy, UEs are reluctant to participate without economic rewards. Hence, the lack of proper economic reward incentive mechanism results in low UE utility and frustrates UEs' enthusiasm for participating in training. To address the above challenge, in this article, we propose a two-phase energy-aware reward incentive mechanism for the edge-cloud-assisted hierarchical federated learning (HFL) system to optimize the overall UE utility, thereby, incentivizing UEs to participate more actively. Specifically, at the cloud server phase, we design an energy quantity-aware incentive mechanism for reasonably distributing rewards to its sub-edge-assisted FL systems. Subsequently, at the edge server phase, based on the quantitative analysis for the optimal reward allocation solution, we develop an energy-aware water filling-based reward incentive mechanism to adapt to individual needs of UEs and maximize the overall UE utility. Experiments verify that, compared to well-known benchmarks, our incentive mechanism can improve the overall UE utility by up to 55.94% and better incentivize UEs to participate in training.

Robust loss functions are essential for training deep neural networks in the presence of noisy labels. Some robust loss functions use Mean Absolute Error (MAE) as its necessary component. For example, the recently proposed Active Passive Loss (APL) uses MAE as its passive loss function. However, MAE treats every sample equally, slows down the convergence and can make training difficult. In this work, we propose a new class of theoretically robust passive loss functions different from MAE, namely *Normalized Negative Loss Functions* (NNLFs), which focus more on memorized clean samples. By replacing the MAE in APL with our proposed NNLFs, we improve APL and propose a new framework called *Active Negative Loss* (ANL). Experimental results on benchmark and real-world datasets demonstrate that the new set of loss functions created by our ANL framework can outperform state-of-the-art methods. The code is available at https://github.com/Virusdoll/Active-Negative-Loss.

Extracting information from large-scale high-dimensional data is a fundamentally important task in high performance computing, where the hierarchical Tucker (HT) tensor learning approach (learning a tensor-tree structure) has been widely used in many applications. However, HT tensor learning algorithms are compute-intensive due to the “curse of dimensionality,” i.e., the time complexity grows exponentially with the order of the data tensor. The computation of HT tensor learning algorithms boils down to tensor primitives, which are amenable to computing on GPU tensor cores. Existing work does not support HT tensor learning using GPU tensor cores. There are three main challenges to address: 1) to accelerate tensor learning primitives using GPU tensor cores; 2) to implement the tensor learning algorithms using GPU tensor cores and multiple GPUs; 3) to support large-scale data tensors exceeding the GPU memory capacity. In this paper, we present efficient HT tensor learning primitives using GPU tensor cores and demonstrate three applications. First, we utilize GPU tensor cores to optimize HT tensor learning primitives, including tensor contractions, tensor matricizations and tensor singular value decomposition (SVD). We employ the optimized primitives to optimize HT tensor decomposition algorithms for Big Data analysis. Second, we propose a novel HT tensor layer for deep neural networks, whose training process only involves a forward pass without back propagation. The forward pass consists of tensor operations, thus further exploiting the computing power of GPU tensor cores. Third, we apply the optimized primitives to develop a tensor-tree structured quantum machine learning algorithmtree-tensor network (TTN). Compared with TensorLy and TensorNetwork on NVIDIA A100 GPUs, our third-order HT tensor decomposition algorithm achieves up to$8.92 \times$and$6.42 \times$speedups, respectively, and our high-order case achieves up to$32.67 \times$and$23.97 \times$speedups, respectively. Our HT tensor layer for a fully connected neural network achieves$49.2 \times$compression at the cost of 0.5% drops in accuracy and$1.42 \times$speedup compared with the implementation on CUDA cores; for the AlexNet, our HT tensor layer achieves$9.45 \times$compression at the cost of 0.8% drops in accuracy and$1.87 \times$speedup compared with the implementation on CUDA cores. Our TTN algorithm achieves up to$11.17\times$speedup compared with TensorNetwork, indicating the potential of optimized tensor learning primitives for the classical simulation of quantum machine learning algorithms.

Expensive annotation costs significantly hinder the development of facial landmark tracking owing to the frame-by-frame labeling of dense landmarks. The most promising approach to address this problem is to develop a self-supervised tracker for large-scale unlabeled videos. However, existing self-supervised trackers trained using single-sourced knowledge are unstable under unconstrained environments. Herein, we propose multi-sourced knowledge integration (MSKI), a robust self-supervised tracking method. It integrates knowledge from multiple sources to provide supervisory signals, thereby improving the stability of the self-supervised tracker. Specifically, the proposed MSKI comprises two complementary modules: a temporal knowledge reasoning (TempRes) module and an interactive knowledge distillation (KnowDist) module. The TempRes module enforces the tracker to achieve cycle-consistent tracking, allowing the tracker to learn temporal correspondence based on the cycle-consistency of time. To exploit facial geometry knowledge against various occlusions, our tracker imposes a multi-level shape constraint over the structure of facial landmarks by leveraging adversarial shape learning, thereby enabling the tracking of occluded faces. Moreover, the tracker interacts with an initialization detector to further develop complementary knowledge via KnowDist. The KnowDist module distills the spatial and temporal knowledge provided by the detector and tracker to generate plausible labels automatically. Finally, these generated labels are utilized to fine-tune the detector, such that it provides high-quality initial landmarks for the cycle-consistent tracking of the tracker on unlabeled videos. The experimental results show that the proposed MSKI can stabilize the tracking trajectory and improve the robustness against various occlusions.

Federated Learning (FL) is a distributed machine learning technology that trains models on large-scale distributed devices while keeping training data localized and privatized. However, in settings where data is distributed in a not independent and identically distributed (non-I.I.D.) fashion, the single joint model produced by FL suffers in terms of test set accuracy and communication costs. And a multi-layer topology are widely deployed for FL in real scenarios. Therefore, we propose FedBox, a chunked local aggregation federated learning framework to improve the generalization ability and aggregation efficiency of model in non-I.I.D. data by adapting to the topology of the real network. Moreover, we study the adaptive gradient descent (AGC) to mitigate the feature shift caused by training non-I.I.D. data. In this work, we modified the aggregation strategy of FL by introducing a virtual node layer based on local stochastic gradient methods (SGD), and separate the edge node cluster by the similarity between the local update model and the global update model. We show that FedBox can effectively improve convergence speed and test accuracy, while reducing communication cost. Training results on FederatedEMNIST, Cifar10, Cifar100 and Shakespeare datasets indicate that FedBox allows model training to converge in fewer communication rounds and improves training accuracy by up to 3.1% compared with FedAVG. In addition, we make an empirical analysis of the extended range of virtual nodes.

In facial landmark localization tasks, various occlusions heavily degrade the localization accuracy due to the partial observability of facial features . This paper proposes a structural relation network (SRN) for occlusion-robust landmark localization. Unlike most existing methods that simply exploit the shape constraint, the proposed SRN aims to capture the structural relations among different facial components. These relations can be considered a more powerful shape constraint against occlusion. To achieve this, a hierarchical structural relation module (HSRM) is designed to hierarchically reason the structural relations that represent both long- and short-distance spatial dependencies . Compared with existing network architectures ,the HSRM can efficiently model the spatial relations by leveraging its geometry-aware network architecture, which reduces the semantic ambiguity caused by occlusion. Moreover, the SRN augments the training data by synthesizing occluded faces. To further extend our SRN for occluded video data, we formulate the occluded face synthesis as a Markov decision process (MDP). Specifically, it plans the movement of the dynamic occlusion based on an accumulated reward associated with the performance degradation of the pre-trained SRN. This procedure augments hard samples for robust facial landmark tracking. Extensive experimental results indicate that the proposed method achieves outstanding performance on occluded and masked faces. Code is available at https://github.com/zhuccly/SRN

Due to the explosion of mobile devices and the evolution of wireless communication technologies, novel applications with intensive computation demands and low-latency requirements have arisen. Edge computing has been proposed as an extension of cloud computing, which moves computation workloads from remote cloud to network edge. Cooperating edge computing and cloud computing can significantly reduce the latency of computation tasks. However, considering the heterogeneity and stochastic arrivals of tasks and the limited computation and communication resources on the edge, task offloading and resource allocation are two joint crucial problems in an edge-cloud orchestrated computing system. In this paper, we propose an online task offloading and resource allocation approach for edge-cloud orchestrated computing, with the aim to minimize the average latency of tasks over time. We first build system models to analyze the latency and energy consumption incurred under different computing modes and formally formulate the joint problem as a mixed-integer optimal decision problem. Then, we employ Lyapunov optimization and duality theory to decompose the problem into a set of subproblems, which can be solved in a semi-decentralized way. We also formally analyze that our approach can achieve near-optimal performance. Extensive simulations are conducted to verify the superiority of our approach.

With the explosion of mobile smart devices, many computation intensive applications have emerged, such as interactive gaming and augmented reality. Mobile-edge computing (EC) is put forward, as an extension of cloud computing, to meet the low-latency requirements of the applications. In this article, we consider an EC system built in an ultradense network with numerous base stations. Heterogeneous computation tasks are successively generated on a smart device moving in the network. An optimal task offloading strategy, as well as optimal CPU frequency and transmit power scheduling, is desired by the device user to minimize both task completion latency and energy consumption in a long term. However, due to the stochastic task generation and dynamic network conditions, the problem is particularly difficult to solve. Inspired by reinforcement learning, we transform the problem into a Markov decision process. Then, we propose an attention-based double deep Q network (DDQN) approach, in which two neural networks are employed to estimate the cumulative latency and energy rewards achieved by each action. Moreover, a context-aware attention mechanism is designed to adaptively assign different weights to the values of each action. We also conduct extensive simulations to compare the performance of our proposed approach with several heuristic and DDQN-based baselines.

The pancreas is located in the deep abdominal cavity of the human body. It is small in size and variable in shape, which makes the location and diagnosis of pancreatic cancer in abdominal computed tomography (CT) scan images especially difficult. The existing segmentation models of pancreatic cancer have been able to locate the pancreas correctly, but they can't yet segment the edge of the pancreas accurately enough. This paper proposes an extension of the convolutional network U-Net, which is called DLU-Net, for accurately cutting out the irregular shape of pancreatic cancer and improving the segmentation accuracy for pancreatic cancer. In DLU-Net, we use deformable convolution modules to strengthen the ability of the network to model the target edge. To facilitate the transmission of features and reuse the features to reduce the complexity of the network, we add densely connected convolutions. Moreover, Bi-Directional Convolutional Long-Short Term Memory (BConvLSTM) structures are applied to combine the features of different scales by using temporal and spatial correlations. The model was evaluated on the following two datasets: abdominal CT images of pancreatic cancer patients of Medical Segmentation Decathlon (MSD) and abdominal CT images of pancreatic cancer patients of Changhai Hospital. The experimental results show that DLU-Net can more accurately segment the edge of cancer, and has an excellent performance in other segmentation indicators.

In this paper, we propose a self-training based method for semi-supervised semantic segmentation. Our method utilizes k perturbed images of each unlabeled image to generate a new mask through the proposed vote operation which in turn is used as a supervision signal to train the model. The k predicted masks of perturbed images can provide nontrivial knowledge that is not captured by a single prediction and the proposed vote operation enables the model to output a low entropy prediction. Consistency regularization is applied between generated mask and k masks in terms of MSE loss in our network. Extensive experiments are conducted on different datasets to evaluate the effectiveness of our method. We show that the proposed method surpasses previous state-of the-art semi-supervised methods on ISIC 2017 dataset and achieves competitive performance on PASCAL VOC 2012 dataset.

Deep learning has been successful in many fields such as acoustics, image, and natural language processing. However, due to the unique characteristics of graphs, deep learning using universal graph data is not easy. The Graph Attention Networks (GATs) show the best performance in multiple authoritative node classification benchmark tests (including transductive and inductive). The purpose of this research is to design and implement an FPGA-based accelerator called S-GAT for graph attention networks that achieves excellent performance on acceleration and energy efficiency without losing accuracy, and does not rely on DSPs and large amounts of on-chip memory. We design S-GAT with software and hardware co-optimization. Specifically, we use model compression and feature quantization to reduce the model size, and use shift addition units (SAUs) to convert multiplication into shift operation to further reduce the computation requirements. We integrate the above optimizations into a universal hardware pipeline for various structures of GATs. At last, we evaluate our design on an Inspur F10A board with an Intel Arria 10 GX1150 and 16 GB DDR3 memory. Experimental results show that S-GAT can achieve 7.34 times speedup over Nvidia Tesla V100 and 593 times over Xeon CPU Gold 5115 while maintaining accuracy, and 48 times and 2400 times on energy efficiency respectively.

As an environment-friendly public transport, shared bikes have become an important urban transport, providing cheap and convenient services for urban residents. However, the number of docks of a station in a bike sharing system is fixed when it is built, and there exists imbalance between bike usage and supply in reality. An accurate real-time free dock prediction can help guide users to choose a proper station (with free bikes/docks) to rent or return a bike. Many earlier efforts are paid to do bike sharing prediction based on model-based approaches. Recently, deep neural networks (DNN), like convolutional neural networks (CNN) and recurrent neural networks (RNN), have been introduced to solve traffic prediction problems. However, three are some unsolved issues to make accurate real-time free dock prediction, such as learning complicated temporal variation and periodicity of bike usage, spatial correlations of free docks among different stations, and the impact of external factors like weather. To overcome these challenges, we propose a novel deep neural network model, which combines graph convolution and a residual structure together. We first model a bike sharing system as a weighted graph, and the non-Euclidean spatial correlations among stations (represented by weighted edges in the graph) are extracted by random walk operation in graph convolution layers. Moreover, periodic patterns of free docks in different time scales are captured by a residual structure, and external factors are considered to improve the accuracy of prediction. We also conduct comprehensive experiments based on a public real-world dataset of riding trips from Boston, and the results show that our method outperforms state-of-the-art baselines.

Diversity of training data significantly affects tracking robustness of model under unconstrained environments. However, existing labeled datasets for facial landmark tracking tend to be large but not diverse, and manually annotating the massive clips of new diverse videos is extremely expensive. To address these problems, we propose a Spatial-Temporal Knowledge Integration (STKI) approach. Unlike most existing methods which rely heavily on labeled data, STKI exploits supervisions from unlabeled data. Specifically, STKI integrates spatial-temporal knowledge from massive unlabeled videos, which has several orders of magnitude more than existing labeled video data on the diversity, for robust tracking. Our framework includes a self-supervised tracker and an image-based detector for tracking initialization. To avoid the distortion of facial shape, the tracker leverages adversarial learning to introduce facial structure prior and temporal knowledge into cycle-consistency tracking. Meanwhile, we design a graph-based knowledge distillation method, which distills the knowledge from tracking and detection results, to improve the generalization of the detector. The fine-tuned detector can provide tracker on unconstrained videos with high-quality tracking initialization. Extensive experimental results show that the proposed method achieves state-of-the-art performance on comprehensive evaluation datasets.

Action recognition has been an active research area for many years. Extracting discriminative spatial and temporal features of different actions plays a key role in accomplishing this task. Current popular methods of action recognition are mainly based on two‐stream Convolutional Networks (ConvNets) or 3D ConvNets. However, the computational cost of two‐stream ConvNets is high for the requirement of optical flow while 3D ConvNets takes too much memory because they have a large amount of parameters. To alleviate such problems, the authors propose a Dual Attention ConvNet (DANet) based on dual attention mechanism which consists of spatial attention and temporal attention. The former concentrates on main motion objects in a video frame by using ConvNet structure and the latter captures related information of multiple video frames by adopting self‐attention. Their network is entirely based on 2D ConvNet and takes in only RGB frames. Experimental results on UCF‐101 and HMDB‐51 benchmarks demonstrate that DANet gets comparable results among leading methods, which proves the effectiveness of the dual attention mechanism.

An instance with a bad mask might make a composite image that uses it look fake. This encourages us to learn segmentation by generating realistic composite images. To achieve this, we propose a novel framework that exploits a new proposed prior called the independence prior based on Generative Adversarial Networks (GANs). The generator produces an image with multiple category-specific instance providers, a layout module and a composition module. Firstly, each provider independently outputs a category-specific instance image with a soft mask. Then the provided instances’ poses are corrected by the layout module. Lastly, the composition module combines these instances into a final image. Training with adversarial loss and penalty for mask area, each provider learns a mask that is as small as possible but enough to cover a complete category-specific instance. Weakly supervised semantic segmentation methods widely use grouping cues modeling the association between image parts, which are either artificially designed or learned with costly segmentation labels or only modeled on local pairs. Unlike them, our method automatically models the dependence between any parts and learns instance segmentation. We apply our framework in two cases: (1) Foreground segmentation on category-specific images with box-level annotation. (2) Unsupervised learning of instance appearances and masks with only one image of homogeneous object cluster (HOC). We get appealing results in both tasks, which shows the independence prior is useful for instance segmentation and it is possible to unsupervisedly learn instance masks with only one image.

Color constancy considers the problem of restoring the original color of an illuminated scene. Benefiting from the development of Convolutional Neural Network (CNN), substantial progress on color constancy has been made. High-level features of CNN structure contain semantic information while low-level features show local details. If both are taken into account, they would help achieve a more accurate illuminant estimation. However, previous works paid little attention to the latter for there lacks frameworks which can combine those two kinds of features together. Inspired by the pyramid model, a top-down network that successively propagates high-level information to low-level layers is proposed. This network, named Top-down Semantic Aggregation for Color Constancy (TDCC), takes full advantage of the multi-scale representations with strong semantics. As a result, objects with intrinsic colors are captured and a better estimation is obtained. Experiments on three benchmark datasets demonstrate that TDCC significantly outperforms state-of-the-art color constancy methods.

Mobile edge computing (MEC) is a promising paradigm to meet the low latency requirement of applications like virtual/augmented reality, which moves computation workloads from remote cloud to network edge. Task offloading is a crucial problem in a MEC system, which significantly concerns with the achieved latency of tasks and the energy consumption on edge nodes. Although many efforts have been paid on the problem, most of them ignore the hierarchical architecture of MEC and the heterogeneity of tasks generated by different applications. In this paper, we consider a three-layer MEC system with tasks of various types stochastically arrive in real time, in which each task can be executed on mobile smart devices, offloaded to the edge server, or offloaded to the remote cloud. The task offloading problem in such a MEC system with the objective to minimize the averaged latency over time is NP-hard. To solve it, we employ Lyapunov optimization and duality theory to reformulate the problem and decompose it into a set of subproblems. Each subproblem can be distributedly solved by a mobile device or the edge server individually. Extensive simulations are also performed to verify the feasibility and superiority of our approach.

Knowledge graph completion can predict the possible relation between entities. Previous work such as TransE, TransR, TransPES and GTrans embed knowledge graph into vector space and treat relations between entities as translations. In most cases, the more complex the algorithm is, the better the result will be, but it is difficult to apply to large-scale knowledge graphs. Therefore, we propose TransB, an efficient model, in this paper. We avoid the complex matrix or vector multiplication operation. Meanwhile, we make the representation of entities not too simple, which can satisfy the operation in the case of non-one-to-one relation. We use link prediction to evaluate the performance of our model in the experiment. The experimental results show that our model is valid and has low time complexity.

Images obtained from an illuminated scene often have their original colour contaminated. Colour constancy is a study considering how to restore them. Substantial progress on colour constancy has been made in recent years due to the development of a convolutional neural network (CNN). In a CNN structure, high‐level features contain semantic information while low‐level features show local details. If both are taken into account, they would help achieve a more accurate illuminant estimation. However, previous works paid little attention to the latter for lack of frameworks, which can combine those two kinds of features together. Inspired by the pyramid model, a top‐down network that successively propagates high‐level information to low‐level layers is proposed. This network, named top‐down semantic aggregation for colour constancy (TDCC), takes full advantage of the multi‐scale representations with strong semantics. As a result, objects with intrinsic colours are captured and a better estimation is obtained. Experiments on three benchmark datasets demonstrate that TDCC significantly outperforms state‐of‐the‐art colour constancy methods.

Computing models provide the parallel and distributed algorithms for cloud. The ability to estimate the performance of parallel computing models for efficient resource scheduling is critical. Current techniques for predicting the performance are mostly based on analyzing and simulating. The behavior of parallel computing model directly leads to the diversity of mathematical model. Without a general prediction model, it is very hard to compare fairly different parallel computing models in several critical aspects, including computing capacity, resource configuration, scalability, fault tolerance and so on. In this paper, we design a mathematical model for predicting the performance by using queuing system. We make various computing models as a service system for shielding the diversity. The performance can be accurately estimated with the job waiting time and the job performing time. The heterogeneity of computing nodes may also be considered.

In the optimizing work of parallel program, especially in the realm of massively parallel computing, the parallel computing time and space must be concurrently carefully considered to cut down the computing time as much as possible, because lots of poor parallel space strategies would impact negative effects on computing time. Although, sometimes we have no choice but to sacrifice the space for the time's further diminishing. What relationship should the computing time and space to keep and how are they going on are two problems, which deciding our optimizing direction directly and must be clear in parallel optimizing. This paper proposes a space theory, named as space speedup, to denote the scalability of memory requirement, and discusses the relationship of time speedup and space speedup, through which the speedups' guidance capacity in optimizing parallel codes are given.

Correctness and performance are the principal requirement of a parallel system. Due to the complicated and uncertainty, it is necessary to model it. A hierarchical TCPN model proposed in this paper can investigate on various levels of abstraction and analyze concerning performance, functional validity and correctness. It describes the parallel program and the resources respectively to bring less effect to modify the program structure because of running environment changes.

Test cases are one of the most important assets in the testing process. This paper presents the testing ontology based SWEBOK and software quality model. The management and retrieval of test cases will play a vital role in test cases reuse. The keyword-based, as well as facet-based retrieval cannot meet user's flexible query requirement because of lack of semantic information. SWEBOK provides a broad agreement on the content of the software engineering discipline. At last this paper discusses the management and retrieval of test cases based on the semantic similarity of two test concepts in two ontologies according to difference sets of superconcept, subconcept, extension, and intension.

Grid based computational infrastructure is a promising next generation computing platform for solving large-scale resources- intensive problems. With the developing Grid technologies and applications, the research on the Grid monitoring system gets increasingly essential and significant. As far as the present research are concerned, there exist two mainly technologies in grid performance monitoring: MDS (monitoring and directory service) and GMA(Grid Monitoring Architecture). In this paper the author puts forward a novel Mobile Agent-based Grid Monitoring Architecture (MA-GMA), which introduces the mobile agents and cache mechanism of MDS. Based on the Open Grid Service Architecture (OGSA) standard, we merge the characteristics of intelligence and mobility of mobile agent into the current OGSA to construct a dynamic and extensible monitoring system. In the end, we do some experiments under different environments. From the results of experiments shown, this MA-GMA is proved to be effective and improves the monitoring performance greatly.

Abstract The goal of the ShanghaiGrid is to provide information services to the people. It aims to construct a metropolitan‐area information service infrastructure and establish an open standard for widespread upper‐layer applications from both communities and the government. The Information Service Grid Toolkit and a typical application called the Traffic Information Grid are discussed in detail. Copyright © 2005 John Wiley & Sons, Ltd.