Causal structure learning on event sequences is essential in critical systems such as communications, transportation, and industrial monitoring, where precise modeling of causal dependencies among event types significantly impacts tasks like root-cause alarm localization. Existing approaches often rely on Hawkes processes augmented with static network topology to eliminate the independent and identically distributed (i.i.d.) assumption, yet their dependence on predefined fixed structures and manually chosen kernels limits adaptability to dynamic network systems. The key challenge is to automatically infer accurate causal graphs from event sequences where both temporal evolution and network topology change over time, while accounting for nonlinear dependencies. To address this challenge, we propose Adaptive Neural Hawkes Processes (ANHP), a novel neural point process framework comprising three core modules: (1) Adaptive Event-Graph Learning, which constructs dynamic topology directly from event embeddings; (2) Neural Topological Hawkes Process, which replaces traditional linear excitation kernels with neural parameterization to capture nonlinear, time-varying conditional intensities; and (3) Masked Sparse Causal Structure, which balances likelihood maximization and model complexity via kernel-parameters masking and Bayesian Information Criterion (BIC) penalization to suppress redundant edges. Experimental results on real-world communication network alarm datasets from Huawei Shennong Intelligent Maintenance and Operation Center (IMOC) and synthetic datasets demonstrate that ANHP significantly outperforms state-of-the-art methods in accuracy, robustness, and scalability. The code is available at https://github.com/ChngYJ/ANHP.

Modern communication networks are increasingly equipped with in-network computational capabilities and services. Routing in such networks is significantly more complicated than the traditional routing. A legitimate route for a flow not only needs to have enough communication and computation resources, but also has to conform to various application-specific routing constraints. This paper presents a comprehensive study on routing optimization problems in networks with embedded computational services. We develop a set of routing optimization models and derive low-complexity heuristic routing algorithms for diverse computation scenarios. For dynamic demands, we also develop an online routing algorithm with performance guarantees. Through evaluations over emerging applications on real topologies, we demonstrate that our models can be flexibly customized to meet the diverse routing requirements of different computation applications. Our proposed heuristic algorithms significantly outperform baseline algorithms and can achieve close-to-optimal performance in various scenarios.

Reconfigurable intelligent surface (RIS) is a radical and cost-efficient technology to improve energy efficiency and mitigate interference in the heterogeneous network. In this paper, the resource allocation problem of sub-channels, transmit power and RIS coefficients is investigated in the RIS-aided heterogeneous network. To solve the formulated mixed integer nonlinear programming problem, a two-step centralized resource allocation algorithm and a two-step distributed resource allocation algorithm are proposed based on the alternating optimization method. In the centralized algorithm, the sub-channel allocation, transmit power and RIS coefficients are optimized by the macro base station solely, where the non-convex power optimization problem is transformed into a convex one based on the convex approximation method. In the distributed algorithm, which aims to alleviate the computational burden of the macro base station, the sub-channel allocation and transmit power are optimized by using the cooperation of all the small base stations and the macro base station. Finally, numerical results are presented to demonstrate the convergence of the proposed algorithms and the effectiveness of the sub-channel transfer. More importantly, it is shown that the centralized algorithm can achieve the higher total throughput, while the distributed algorithm greatly decreases the resource allocation time.