Continuous-time dynamic graphs (CTDG) composed of chronological events, arise in many real-world complex network applications with high dynamics. Memory-based temporal graph neural networks, due to capacity to update and retain historical node states, excel at capturing dynamic changes, handling long-term dependencies with better interpretability compared to memory-less methods. Despite the effectiveness, memory-based methods suffer from two fatal fundamental flaws (i.e. long-standing staleness and memory offline update time issues), which are usually overlooked by constraints of rigid assumptions in recent works. To address the above flaws, in this work, we propose a novel Dynamic Fresh Memory Vigorous Preserver named DyFMVP, a well-designed state-traceable dual memory architecture for efficient anti-staling representation learning. To eliminate staleness within memory, a continuous memory neural ordinary differential equation process (NDP) is proposed to model the underlying memory transition distribution, rejuvenating the memory to a fresh state. In addition, a history-augmented temporal graph attention is proposed to enhance neighbor aggregation in a history-aware manner. Furthermore, a time-aligning RNN-ODE (TARO) restarter is proposed to be offline updating-free and restart at any future timestamps flexibly. Extensive experiments on various downstream tasks demonstrate the primary model DyFMVP and restarter TARO significantly outperform other state-of-the-art CTDG methods by a large margin, while also exhibiting strong robustness against extreme sparsity and long-term interval. Our code has been available on GitHub11https://github.com/CrescentMoon3/icde2025DyFMVP.

Driven by the increasing demands of vehicular tasks, edge offloading has emerged as a promising paradigm to enhance quality of experience (QoE) in Internet of Vehicles (IoV) networks. This approach enables vehicles to offload computation-intensive tasks to edge servers, resulting in reduced computation delays and lower energy consumption. However, traditional binary offloading limits the efficiency of edge offloading. To address this gap, we propose a partial offloading strategy that jointly optimizes the offloading ratio, computation, and communication resources in IoV. Recognizing the varying priorities of vehicular tasks regarding task delay and energy consumption, we formulate two distinct scenarios: one focused on minimizing delay and the other on minimizing energy consumption. Furthermore, we employ a reinforcement learning approach to establish a multi-dimensional joint optimization function by setting different objectives for each scenario. Based on this framework, we introduce a multi-state iteration deep deterministic policy gradient algorithm (SIDDPG), which effectively determines task partitioning and resource allocation. Simulation results demonstrate that the proposed algorithm outperforms benchmark schemes in terms of task delay and energy consumption.

MOTIVATION: Effective tagging single-nucleotide polymorphism (SNP)-set selection is crucial to SNP-set analysis in genome-wide association studies (GWAS). Most of the existing tagging SNP-set selection methods cannot make full use of the information hidden in common or rare variants associated diseases. It is noticed that some SNPs have overlapping genetic information owing to linkage disequilibrium (LD) structure between SNPs. Therefore, when testing the association between SNPs and disease susceptibility, it is sufficient to elect the representative SNPs (called tag SNP-set or tagSNP-set) with maximum information. RESULTS: It is proposed a new tagSNP-set selection method based on LD information between SNPs, namely TagSNP-Set with Maximum Information. Compared with classical SNP-set analytical method, our method not only has higher power, but also can minimize the number of selected tagSNPs and maximize the information provided by selected tagSNPs with less genotyping cost and lower time complexity. CONTACT: [email protected]. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Order-preserving submatrices (OPSM's) have been shown useful in capturing concurrent patterns in data when the relative magnitudes of data items are more important than their exact values. For instance, in analyzing gene expression profiles obtained from microarray experiments, the relative magnitudes are important both because they represent the change of gene activities across the experiments, and because there is typically a high level of noise in data that makes the exact values untrustable. To cope with data noise, repeated experiments are often conducted to collect multiple measurements. We propose and study a more robust version of OPSM, where each data item is represented by a set of values obtained from replicated experiments. We call the new problem OPSM-RM (OPSM with repeated measurements). We define OPSM-RM based on a number of practical requirements. We discuss the computational challenges of OPSM-RM and propose a generic mining algorithm. We further propose a series of techniques to speed up two time dominating components of the algorithm. We show the effectiveness and efficiency of our methods through a series of experiments conducted on real microarray data.