Temporal Graph Network (TGN) is increasingly adopted to model evolving relationships in dynamic graphs. However, the training pipeline is plagued by pervasive redundancy in computation, storage, and data loading. These redundancies harm computational efficiency, exacerbate memory pressure, and induce excessive CPU-GPU data transfers. We present PULSE, an end-to-end TGN training framework that systematically eliminates redundancies guided by a unified minimal-unit principle. To realize such principle, PULSE defines three synergetic units: 1) the Minimal Input Unit (MIU) for component-wise deduplication and operator-level reconstruction of redundant computations, 2) the Minimal Storage Unit (MSU) for dependency-guided message reconstruction, only preserving irreproducible entries while enabling on-demand recovery of others, and 3) the Minimal Reuse Unit (MRU) for GPU memory management, combining a BlockPool-based buffer allocator with a bipartite temporal reuse strategy to mitigate fragmentation and exploit inter-batch locality. Experimental results on representative benchmarks demonstrate that PULSE improves training throughput by up to 6.67× over the state-of-the-art baselines.

Temporal Graph Networks (TGNs) are widely used to model evolving relationships in dynamic graphs. However, existing inference systems enforce a step-wise paradigm: processing each temporal graph sequentially with a memory update followed by aggregation. We break this dependency by decoupling memory updates from aggregation while preserving prediction accuracy, thereby enabling a global view for fine-grained parallelism control. This design unlocks new optimization opportunities but introduces three system-level challenges: managing intermediate multi-state representations, curbing memory-bound update overheads, and selecting a safe yet efficient aggregation granularity. We present APERTURE, a TGN inference framework that bridges algorithmic semantics and system design. To address the above challenges, APERTURE (1) jointly aggregates temporal states via computation graph transformation, (2) minimizes redundant memory traffic through dependency-aware update reconstruction; (3) selects the optimal granularity by analytically modeling. The experimental results show that APERTURE achieves up to 59.3× speedup over state-of-the-art baselines without compromising accuracy.

Collaborative learning between edge servers (e.g., base stations) and end devices (e.g., drones) enables simultaneous model training in web applications through knowledge sharing. The resulting models effectively reduce service latency. However, existing approaches either assume isomorphic models on edge servers and end devices or incur substantial transmission overhead when training. Moreover, edge servers are often unable to access data from end devices on time due to long-distance constraints or strict data privacy regulations. This paper proposes a Prototype Augmentation-based Edge-end Collaborative Learning method (PAECL). It simultaneously trains heterogeneous edge and end models in the absence of data on edge servers by transmitting only augmented class-wise feature vectors (prototypes), significantly reducing communication overhead compared to sharing models, data, or logits. Specifically, on end devices, prototype-implied latent knowledge is augmented via local prototype contrast and global prototype alignment. On edge servers, prototypes are further augmented to produce bounded virtual vectors by mixing them with random noise, and the augmented prototypes are then delivered to generative models to provide data during edge model training. Through simulations and field experiments, PAECL achieves the highest accuracy for edge and end models under limited training resources and reduces the transmission burden by at least 297 times compared to existing edge-end heterogeneous learning methods.

Edge-end collaborative learning trains models with exchanged knowledge through distributed interaction, alleviating the cloud's burden. Edge-end heterogeneous collaborative learning further enables edge servers and end devices to train models of different scales in parallel based on their computational capabilities. This technology supports various applications in different resource conditions and improves server resource utilization. However, implementing it is challenging due to heavy communication costs and high global costs (time and energy). To this end, this paper proposes a novel prototype-based edge-end heterogeneous collaborative learning method and an optimization algorithm, which improves model performance and reduces training costs. We first use prototypes to perform collaborative learning and analyze the convergence. Prototypes are computed as mean feature vectors from different classes. The aggregated prototypes help capture class information on end devices and generate data on edge servers. Then, we study how to determine prototype selection and edge association to minimize training time, energy consumption, and prototype approximation error under a limited reward budget, which is proven to be NP-hard. We split the original problem into two subproblems. The first is solved in the closed form. Through approximation and reformulation, the second is transformed into a submodular maximization problem with knapsack and matroid constraints. On this basis, we propose an approximation algorithm with a theoretical guarantee. Finally, by simulation and field experiments, our method takes 3.61% of communication costs to improve heterogeneous edge and end models' accuracy by at least 5.16% and 2.77% compared with five baselines. The proposed algorithm outperforms others by at least 9.78% in terms of global cost.

Edge-end collaborative learning greatly reduces latency by eliminating the need for processing on the cloud side, showing promising results in machine learning applications due to collaborating on training tasks through the computational resources of edge servers and end devices. However, current edge-end collaborative learning methods suffer from unbearable latency which result from heavy transmission burden and long synchronization time. We propose a new Prototype-based Semi-Asynchronous Edge-end Collaborative Learning approach (ProSACL) that carefully integrates prototype-based end-side training and edge clustering, allowing any end device to synchronize knowledge, significantly reducing the time spent on training latency. Our approach includes (1) prototype training and asynchronous prototype transfer on end devices: Unlike traditional training methods, we use the average of the same class of feature vectors, i.e., the prototype, as the knowledge transfer means, which significantly reduces the transfer burden and eliminates the need for end devices to wait for other devices to finish. (2) prototype-based clustering and asynchronous aggregation on the edge server: The end devices are segmented by prototype-based clustering to obtain unbiased prototypes for performance enhancement, and prototypes from different rounds are aggregated for fine-grained knowledge transfer. We evaluate the proposed approach by training on three datasets, which show substantial performance improvement compared to previous work.

ABSTRACT Context The rise of artificial intelligence of things (AloT) has enabled smart cities and industries, and UAV‐assisted edge computing networks are an important technology to support the above scenarios. UAV‐assisted refers to leveraging UAVs as a dynamic, flexible infrastructure to assist edge network data processing and communication tasks. Multiple UAVs can use their own resources, and collaborate edge servers to train artificial intelligence (Al) models. Objective Compared with cloud‐based collaborative computing scenarios, UAV‐assisted edge collaborative learning can reduce training and inference delays and improve user satisfaction. However, UAV‐assisted edge networks scenario brings new challenges in terms of transmission burden and energy consumption. Method This paper proposes a prototype‐based joint optimization and training software system. The system consists of an optimization module and a training module. The optimization module first models an optimization problem including energy consumption and prototype error. Then it solves the optimization problem by problem transformation and plans the location of each UAV given the objects' position. After UAVs fly to the designated area and complete data collection, UAVs and the edge server train a model according to the proposed prototype‐based collaborative training module. Our training module enables multiple UAVs and an edge server to collaboratively train a model by lightweight prototype transmission and prototype aggregation. We also prove the convergence of the proposed collaborative training method. Results Results show our method reduces prototype error and energy consumption by at least 12.31% and improves model accuracy by 3.62% with a little communication burden. Conclusion Finally, we verify system performance through experiments.

For Unmanned Aerial Vehicles (UAVs) monitoring tasks, capturing high quality images of target objects is important for subsequent recognition. Concerning the problem, many prior works study placement/trajectory planning for UAVs to maximize the quality of captured images. However, all of them overlook a fact thatUAV monitoring may cause a huge risk/annoyance on living objects.In this paper, we investigate the novel problem of oPtimizing uncrewed aErial vehicles plAcement byConsidering both monitoring utility and adverseEffects (PEACE). We propose an approach to solve PEACE, which is proved to be NP-hard. Overall, our approach achieves a$1- \frac{1}{e}-\varepsilon$approximation ratio. First, we approximate the original problem of PEACE as a classical problem of Monotone Submodular function Maximization under a Uniform Matroid constraint (MSMUM) with a controlled gap. Then, for MSMUM, we propose a combination of algorithms achieving a$1-\frac{1}{e}$approximation and$O(n\log n)$time complexity considering the correlation among the UAV monitoring strategies. The proposed algorithms outperform existing algorithms for MSMUM through theoretical analysis and experimental results. Extensive simulations and field experiments demonstrate the effectiveness of our approach, achieving performance gains of 9.0% to 1434.5% compared to existing methods.