Abstract Graph Neural Networks (GNNs) have become essential for solving graph-level tasks, such as classification and regression, across diverse domains including social networks and biology. However, existing GNNs struggle with the expressivity that captures complex structural patterns, and the generalization that ensures robust performance on diverse and noisy datasets. To address these challenges, we propose a novel GNN model that integrates a k -path rooted subgraph encoder, an adaptive graph contrastive learning approach, and a consistency-aware loss. The k -path rooted subgraph encoder enhances expressivity by capturing and distinguishing intricate substructures, with theoretical guarantees for counting paths and cycles. The adaptive graph contrastive learning framework improves generalization by generating domain-aware graph augmentations based on edge importance, while the consistency-aware loss ensures task-relevant properties are preserved across augmented views. Extensive experiments on 26 datasets spanning graph classification, regression, and realistic scenarios such as noise, class imbalance, and few-shot learning show that our model achieves superior performance against 18 state-of-the-art GNN models in both effectiveness and efficiency. The code is released in https://anonymous.4open.science/r/GEGNN .

Temporal link prediction in dynamic graphs is a critical task with applications in diverse domains such as social networks, recommendation systems, and e-commerce platforms. While existing Temporal Graph Neural Networks (T-GNNs) have achieved notable success by leveraging complex architectures to model temporal and structural dependencies, they often suffer from scalability and efficiency challenges due to high computational overhead. In this paper, we propose EAGLE, a lightweight framework that integrates short-term temporal recency and long-term global structural patterns. EAGLE consists of a time-aware module that aggregates information from a node's most recent neighbors to reflect its immediate preferences, and a structure-aware module that leverages temporal personalized PageRank to capture the influence of globally important nodes. To balance these attributes, EAGLE employs an adaptive weighting mechanism to dynamically adjust their contributions based on data characteristics. Also, EAGLE eliminates the need for complex multi-hop message passing or memory-intensive mechanisms, enabling significant improvements in efficiency. Extensive experiments on seven real-world temporal graphs demonstrate that EAGLE consistently achieves superior performance against state-of-the-art T-GNNs in both effectiveness and efficiency, delivering more than a 50× speedup over effective transformer-based T-GNNs.

Approximate Nearest Neighbor Search (ANNS) on high dimensional vector data is now widely used in various applications, including information retrieval, question answering, and recommendation. As the amount of vector data grows continuously, it becomes important to support updates to vector index, the enabling technique that allows for efficient and accurate ANNS on vectors.

In this paper, general logic cell and module designs in basic digital signal processing (DSP), for transparent, flexible chips and wearable electronics are presented. Modified Circuits from ratioed logic and pass transistor logic styles are modified and proposed, based on n-type-only indium tin oxide (ITO) stabilized ZnO thin-film transistors (TFTs) process. Elaborations on logic circuits with purely n-type TFT transistors were carried out to extend the logic swing of circuit outputs and accelerate the signal propagation in complex logic functions with simplified pull-up/pull-down or passive networks. To implement logic complexes on multiple OR-of-ANDs functions with better performance, tailored active controlled ratioed logic style is adopted with faster speed and smaller area by simplifying the transistor networks properly. All the circuits were fabricated on transparent glass plate. The featured 2-input/3-input XOR gate, 4-1 MUX and D flip flop (DFF) can operate with maximum featured delays of 2-$6~\mu \text{s}$at 5 V power supply, with comparatively over 50% less delays and areas than other state-of-art works. The featured 4-bit adder performs maximum$16.41~\mu \text{s}$delay at 5 V in measurement. A 4-bit multiplier is also presented based on the adder and DFF. These proposed TFT circuits exhibited smaller area with relatively moderate-high performance in comparison, which were promising building blocks for transparent flexible DSP electronics with low-speed requirements.

Clinically, physicians collect the benchmark medical data to establish archives for a stroke patient and then add the follow up data regularly. It has great significance on prognosis prediction for stroke patients. In this paper, we present an interpretable deep learning model to predict the one-year mortality risk on stroke. We design sub-modules to reconstruct features from original clinical data that highlight the dissimilarity and temporality of different variables. The model consists of Bidirectional Long Short-Term Memory (Bi-LSTM), in which a novel correlation attention module is proposed that takes the correlation of variables into consideration. In experiments, datasets are collected clinically from the department of neurology in a local AAA hospital. It consists of 2,275 stroke patients hospitalized in the department of neurology from 2014 to 2016. Our model achieves a precision of 0.9414, a recall of 0.9502 and an F1-score of 0.9415. In addition, we provide the analysis of the interpretability by visualizations with reference to clinical professional guidelines.

To overcome the shortcomings of the basic glowworm swarm optimization (GSO) algorithm, such as low accuracy, slow convergence speed and easy to fall into local minima, chaos algorithm and cloud model algorithm are introduced to optimize the evolution mechanism of GSO, and a chaos GSO algorithm based on cloud model (CMCGSO) is proposed in the paper. The simulation results of benchmark function of global optimization show that the CMCGSO algorithm performs better than the cuckoo search (CS), invasive weed optimization (IWO), hybrid particle swarm optimization (HPSO), and chaos glowworm swarm optimization (CGSO) algorithm, and CMCGSO has the advantages of high accuracy, fast convergence speed and strong robustness to find the global optimum. Finally, the CMCGSO algorithm is used to solve the problem of face recognition, and the results are better than the methods from literatures.

Scheduling for directed acyclic graph (DAG) tasks with the objective of minimizing makespan has become an important problem in a variety of applications on heterogeneous computing platforms, which involves making decisions about the execution order of tasks and task-to-processor mapping. Recently, the chemical reaction optimization (CRO) method has proved to be very effective in many fields. In this paper, an improved hybrid version of the CRO method called HCRO (hybrid CRO) is developed for solving the DAG-based task scheduling problem. In HCRO, the CRO method is integrated with the novel heuristic approaches, and a new selection strategy is proposed. More specifically, the following contributions are made in this paper. (1) A Gaussian random walk approach is proposed to search for optimal local candidate solutions. (2) A left or right rotating shift method based on the theory of maximum Hamming distance is used to guarantee that our HCRO algorithm can escape from local optima. (3) A novel selection strategy based on the normal distribution and a pseudo-random shuffle approach are developed to keep the molecular diversity. Moreover, an exclusive-OR (XOR) operator between two strings is introduced to reduce the chance of cloning before new molecules are generated. Both simulation and real-life experiments have been conducted in this paper to verify the effectiveness of HCRO. The results show that the HCRO algorithm schedules the DAG tasks much better than the existing algorithms in terms of makespan and speed of convergence.

In order to overcome the drawbacks of the K-means (KM) for clustering problems such as excessively depending on the initial guess values and easily getting into local optimum, a clustering algorithm of invasive weed optimization (IWO) and KM based on the cloud model has been proposed in the paper. The so-called cloud model IWO (CMIWO) is adopted to direct the search of KM algorithm to ensure that the population has a definite evolution direction in the iterative process, thus improving the performance of CMIWO K-means (CMIWOKM) algorithm in terms of convergence speed, computing precision and algorithm robustness. The experimental results show that the proposed algorithm has such advantages as higher accuracy, faster constringency, and stronger stability.

Task scheduling has been proven to be NP-hard problem and we can usually approximate the best solutions with some classical algorithm, such as Heterogeneous Earliest Finish Time (HEFT), Genetic Algorithm. However, the huge types of scheduling problems and the small number of generally acknowledged methods mean that more methods are needed. In this paper, we propose a new method to schedule the execution of a group of dependent tasks for heterogeneous computing environments. The algorithm consists of two elements: An intelligent approach to assign the execution orders of tasks by task level, and an allocation algorithm based on chemical-reaction-inspired metaheuristic called Chemical Reaction Optimization (CRO) to map processors to tasks. The experiments show that the CRO-based algorithm performs consistently better than HEFT and Critical Path On a Processor (CPOP) without incurring much computational cost. Multiple runs of the algorithm can further improve the search result.

As the data collection volumes growing rapidly, some complex computation are beyond the ability of our classical process methods. A framework combine between MapReduce and workflow can present a good contribution to this problem through parallel processing for the largescale systems. Currently there are several researches on the scheduling policy for this combination framework in homogeneous cluster or simple heterogeneous cluster, however the scheduling on MapReduce-level and workflow-level are detached. Thus we firstly propose a MapReduce-enabled scientific workflow integrated with an optimization scheduling algorithm to consider both level simultaneously and to support complex heterogeneous environment. Our new Model comprise two components: The job prioritizing module to compute the priorities of all jobs, and the task assignment module to allocate suitable slots for each block and schedule the tasks with respect to data-local. We prove by experiment that in our combination framework the new scheduler policy (MRWS) outperforms other polices in this area.