Graph Neural Networks (GNNs) have demonstrated impressive performance across diverse graph-based tasks by leveraging message passing to capture complex node relationships. However, on large-scale real-world graphs, GNNs face two major challenges: (1) GNNs struggle to ensure scalability and efficiency as repeated aggregation of large neighborhoods incurs significant computational overhead; (2) GNNs suffer from over-smoothing, where excessive propagation makes node representations indistinguishable, hindering model expressiveness. To tackle these, we propose ScaleGNN, which adaptively fuses multi-hop node features for scalable and effective graph learning. We first compute per-hop pure-neighbor matrices to isolate exclusive structural signals, then apply lightweight fusion to balance low- and high-order information, preserving both local detail and global correlations. To curb redundancy and over-smoothing, we introduce Local Contribution Score (LCS)–based masking to prune low-relevance high-order neighbors, and impose learnable sparsity to selectively integrate valuable multi-hop features. Extensive experiments on real-world datasets show that ScaleGNN consistently outperforms state-of-the-art GNNs in both predictive accuracy and computational efficiency. The source code is available at https://github.com/lx970414/ScaleGNN.

Timely and efficient dissemination of service information is critical in compute-first networking systems, where user requests arrive dynamically and computing resources are constrained. In such systems, the access point (AP) plays a key role in forwarding user requests to a server based on its latest received service information. This paper considers a single-source, single-destination system and introduces a PPO–based reinforcement learning framework for efficient information updating, guided by a newly designed reward metric called Age-and-Value-Aware (AVA). Unlike traditional freshness-based metrics, AVA explicitly incorporates variations in server-side service capacity and AP’s forwarding decisions, allowing more context-aware update evaluation. Under this reward structure, the PPO agent autonomously learns when to trigger service information updates, achieving a dynamic balance between communication cost and decision accuracy. Extensive simulations under diverse user request patterns and varying service capacities demonstrate that AVA reduces the update frequency by over 90% on average compared to baselines, with reductions reaching 98% in certain configurations. This reduction is achieved without compromising the quality of decision making.

In compute-first networking, computing router (or access points, APs) rely on edge service-status information to decide whether to offload tasks or process them locally. Under limited synchronization resources, maintaining fresher status at all APs does not necessarily improve decision quality, since many updates may not change the offloading outcome while still consuming scarce update budget. To address this mismatch, we propose the Error Decision Processing Time (EDPT) metric, which explicitly quantifies the processing-time penalty induced by erroneous offloading decisions and shifts status updating from freshness-oriented optimization to decision correctness. We then formulate the multi-AP status updating problem as a Markov Decision Process (MDP) with a per-slot update constraint and develop a Multi-Head Dueling Double DQN (MH-D3QN) framework. MH-D3QN employs AP-specific action-value estimation together with a benefit-ranking-guided action selection mechanism to mitigate the combinatorial action explosion and enable fast online decisions. Simulation results demonstrate that compared with the freshness-prioritized baseline, MH-D3QN saves more than 35.4% of the update budget and reduces the decision error rate by over 6.5%, effectively translating these gains into a 4.9% reduction in average task processing time.

With the rise of social media and Location-Based Social Networks (LBSN), check-in data across platforms has become crucial for User Identity Linkage (UIL). These data not only reveal users' spatio-temporal information but also provide insights into their behavior patterns and interests. However, cross-platform identity linkage faces challenges like poor data quality, high sparsity, and noise interference, which hinder existing methods from extracting cross-platform user information. To address these issues, we propose a Correlation-Attention Masked Transformer for User Identity Link age Network (MT-Link), a transformer-based framework to enhance model performance by learning spatio-temporal co-occurrence patterns of cross-platform users. Our model effectively captures spatio-temporal co-occurrence in cross-platform user check-in sequences. It employs a correlation attention mechanism to detect the spatio-temporal co-occurrence between user check-in sequences. Guided by attention weight maps, the model focuses on co-occurrence points while filtering out noise, ultimately improving classification performance. Experimental results show that our model significantly outperforms state-of-the-art baselines by 12.92%-17.76% and 5.80%-8.38% improvements in terms of Macro-F1 and Area Under Curve (AUC).

Trajectory-user linking (TUL) aims to match anonymous trajectories to the most likely users who generated them, offering benefits for a wide range of real-world spatio-temporal applications. However, existing TUL methods are limited by high model complexity and poor learning of the effective representations of trajectories, rendering them ineffective in handling large-scale user trajectory data.In this work, we propose a novel Scalable Trajectory-User Linking with dual-stream representation networks for large-scale TUL problem, named ScaleTUL Specifically, ScaleTUL generates two views using temporal and spatial augmentations to exploit supervised contrastive learning framework to effectively capture the irregularities of trajectories. In each view, a dual-stream trajectory encoder consisting of a long-term encoder and a short-term encoder is designed to learn the unified representations of trajectories that fuses different temporal-spatial dependencies. Then, a TUL layer is used to associate the trajectories with the corresponding users in the representation space using a two-stage training model.Experimental results on check-in mobility datasets from three real-world cities and the nationwide U.S. demonstrate the superiority of ScaleTUL over state-of-the-art baselines for large-scale TUL tasks.

Graph anomaly detection (GAD) is a critical task in graph machine learning, with the primary objective of identifying anomalous nodes that deviate significantly from the majority. This task is widely applied in various real-world scenarios, including fraud detection and social network analysis. However, existing GAD methods still face two major challenges: (1) They are often limited to detecting anomalies in single-type interaction graphs and struggle with multiple interaction types in multiplex heterogeneous graphs. (2) In unsupervised scenarios, selecting appropriate anomaly score thresholds remains a significant challenge for accurate anomaly detection. To address the above challenges, we propose a novel Unsupervised Multiplex Graph Anomaly Detection method, named UMGAD. We first learn multi-relational correlations among nodes in multiplex heterogeneous graphs and capture anomaly information during node attribute and structure reconstruction through graph-masked autoencoder (GMAE). Then, to further extract abnormal information, we generate attribute-level and subgraph-level augmented-view graphs, respectively, and perform attribute and structure reconstruction through GMAE. Finally, we learn to optimize node attributes and structural features through contrastive learning between original-view and augmented-view graphs to improve the model's ability to capture anomalies. Meanwhile, we propose a new anomaly score threshold selection strategy, which allows the model to be independent of ground truth information in real unsupervised scenarios. Extensive experiments on six datasets show that our UMGAD significantly outperforms state-of-the-art methods, achieving average improvements of 12.25% in AUC and 11.29% in Macro-F1 across all datasets. The source code of our model is available at https://github.com/lx970414/UMGAD.

Temporal motifs are recurring subgraph patterns in temporal graphs, and are present in various domains such as social networks, fraud detection, and biological networks. Despite their significance, counting temporal motifs efficiently remains a challenge, particularly on moderately sized datasets with millions of motif instances. To address this challenge, we propose a novel algorithm called Scalable Motif Counting with Time-aware Topology Constraint (MoTTo). MoTTo focuses on accurately counting temporal motifs with up to three nodes and three edges. It first utilizes a topology constraint-based pruning strategy to eliminate nodes that cannot participate in forming temporal motifs before the counting process. Then, it adopts a time-aware topology constraint-based pruning strategy to split large-scale datasets into independent partitions and filter out the unrelated ones, ensuring that the counting results remain unaffected. By investigating the second pruning strategy, we also find that MoTTo can be implemented in a multi-thread manner, further accelerating the counting process significantly. Experimental results on several real-world datasets of varying sizes demonstrate that MoTTo outperforms state-of-the-art methods in terms of efficiency, achieving up to a nine-fold improvement in total temporal motif counting. Specifically, the efficiency of counting triangular temporal motifs is enhanced by up to 31 times compared to state-of-the-art baselines.

In edge computing scenarios, there is a need for modeling dedicated features and heterogeneous devices functions, as well as integrating multiple complex scenarios with diverse objectives and frequent interactions. However, existing platforms modeling for the whole device ignores the independence between functional components resulting in limited scenario support. We propose an open-source simulator named EasiEI. EasiEI addresses the need for higher level feature replaceability and independence in modeling complex edge scenarios through independent functional component-level modeling and microkernel architecture. This approach enables users to assemble independent functional components in a plug-and-play manner for heterogeneous devices or different application requirements. EasiEI is fully compatible with all the existing built-in modules in NS3 (a powerful network discrete event simulator). To verify the flexibility and extensibility of EasiEI, we implement several centralized and decentralized computing paradigms cases in a step-by-step way. These cases restore and simulate the performance state of various real devices in real time, meeting the requirements for verifying the edge computing ideas such as task scheduling in a distributed manner. Results show that the simulations have well reflected the characteristics of the real world and can construct complex environment flexibly.

Despite placing services and computing resources at the edge of the network for ultra-low latency, we still face the challenge of centralized scheduling costs, including delays from additional request forwarding and resource selection. To address this challenge, we propose SmartBuoy, a new computing paradigm. Our approach starts with a service coverage concept that assumes users within the coverage have high access availability. To enable users to perceive service status, we design a distributed metric table that synchronizes service status periodically and distributively. We propose coverage indicator updating principles to make the updating process more effective. We then implement two distributed methods, SmartBuoy-Time and SmartBuoy-Reliability, that enable users to perceive service capability directly and immediately. To determine the metric table update window size, we provide an analysis method based on user access patterns and offer a theoretical upper bound in a dynamic environment, making SmartBuoy easy to use. Finally, we implement the proposed methods distributively on an open-source edge computing simulator. Experiments on a real-world network topology dataset demonstrate the efficiency of SmartBuoy in reducing delays and improving the success rate.

Computation and/or communication-intensive collaborative services accompanied by several distributed tasks/components, such as the services in Internet of Things, can be anywhere nowadays. These services are usually used by users at the Internet edge, making cloud computing struggles with the high end-to-end latency. Thanks to edge computing which pushes resources to the edge, the goals with lower latency can be well satisfied. However, in actual scenarios especially under dynamic edge computing networks, changes exist in resources, including computing, bandwidth, and nodes. Meanwhile, data packets (or flow) among collaborative tasks/components of a service can also not be conserved. These characteristics lead the service reliability hard to be guaranteed and make existing reliability evaluation methods no longer accurate. To study the effect of distributed and collaborative service deployment strategies under such background, we propose a reliability evaluation method (REMR). We first look for the solution set which can meet the time constraints. Then, we calculate the reliability of service supported by the solution set based on the principle of inclusion–exclusion with distributions of available transmission bandwidth and computing resources. Finally, we provide an illustrative example with several real-world data sets to make REMR easy to follow. To make REMR more reliable, we also propose and implement a Monte Carlo simulation method. Experiments prove that the reliability calculated by REMR is nearly the same as the simulation results and both the latencies and the jitters are also at a lower level.

Named data networking (NDN) constructs a network by names, providing a flexible and decentralized way to manage resources within the edge computing continuum. This paper aims to solve the question, “Given a function with its parameters and metadata, how to select the executor in a distributed manner and obtain the result in NDN?” To answer it, we design R2 that involves the following stages. First, we design a name structure including data, function names, and other function parameters. Second, we develop a 2-phase mechanism, where in the first phase, the function request from a client-first reaches the data source and retrieves the metadata. Then the best node is selected while the metadata responds to the client. In the second phase, the chosen node directly retrieves the data, executes the function, and provides the result to the client. Furthermore, we propose a stop condition to intelligently reduce the processing time of the first phase and provide a simple proof and range analysis. Simulations confirm that R2 outperforms the current solutions in terms of resource allocation, especially when the data volume and the function complexity are high. In the experiments, when the data size is 100 KiB and the function complexity is$\mathcal {O}(n^{2})$, the speedup ratio is 4.61. To further evaluate R2, we also implement a general intermediate data processing logic named “Bolt” implemented on an app-level in ndnSIM. We believe that R2 shall help the researchers and developers to verify their ideas smoothly.