Multi-access edge computing provides localized resources within mobile networks to address the requirements of emerging latency-sensitive and computing-intensive applications. At the edge, dynamic requests necessitate sophisticated resource management for adaptive network slicing. This involves optimizing resource allocations, scaling functions, and load balancing to utilize only essential resources under constrained network scenarios. However, existing solutions largely assume static slice counts, ignoring the re-optimization overhead associated with management algorithms when slices fluctuate. Moreover, many approaches rely on simplified energy models that overlook intertemporal resource scheduling and are predominantly evaluated through simulations, neglecting critical practical considerations. This paper presents an incremental cooperative Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm for resource management in dynamic edge slicing. The proposed approach optimizes long-term slicing benefits by reducing delay and energy consumption while minimizing retraining overhead in response to slice variations. Furthermore, we implement an urban-wide edge computing testbed based on OpenStack and Kubernetes to validate the algorithm’s performance. Experimental results demonstrate that our incremental MADDPG method outperforms benchmark strategies in aggregated slicing utility and reduces training energy consumption by up to 50% compared to the re-optimization approach.

We present Continuous-Time Attention, a novel framework that infuses partial differential equations (PDEs) into the Transformer's attention mechanism to better handle long sequences.Instead of relying on a static attention matrix, we allow attention weights to evolve along a pseudo-time dimension governed by diffusion, wave, or reaction-diffusion dynamics.This dynamic process systematically smooths local noise, strengthens long-range dependencies, and improves gradient stability during training.Our theoretical analysis shows that PDE-driven attention mitigates the exponential decay of distant interactions and improves the optimization landscape.Empirically, Continuous-Time Attention achieves consistent performance gains over both standard and long-sequence Transformer variants across a range of tasks.These results suggest that embedding continuous-time dynamics into attention mechanisms is a promising direction for enhancing global coherence and scalability in Transformer models.Code is publicly available at: https://github.com/XueqingZhou/Continuous-Time-Attention

Integrating mobile networks with Non-3GPP networks provides a promising solution to mitigate the wireless RF spectrum scarcity. Despite the maturity of integration technologies, a comprehensive approach for radio resource allocation in highly dynamic and complex multiple Radio Access Technologies (multi-RAT) networks is still lacking. To tackle this challenge, this paper proposes an Access Traffic Management (ATM) system that enhances radio resource allocation during access, transmission, and handover processes. The system features a scalable and concise ATM-supported multi-RAT network architecture, supported by a Deep Deterministic Policy Gradient (DDPG) based Intelligent ATM (IATM) algorithm. To evaluate the proposed system, a Network Simulator 3 (NS3) based network simulation is built with realistic 5G and WiFi modules, interacting with the IATM algorithm in real time for decision making and policy improvement. Numerical improvements of our solution demonstrate its superiority over conventional steering modes. Our solution achieves an increase in resource utilization efficiency by 45% and 70% compared to the Active-Standby and Load-Balance steering modes, respectively. Moreover, it enhances link quality by a factor of three and doubles throughput without incurring any additional costs. Additionally, our solution significantly enhances session stability under conditions involving network size dynamics and UE mobility.

Electroencephalogram (EEG) is an important technology to explore the central nervous mechanism of tinnitus. However, it is hard to obtain consistent results in many previous studies for the high heterogeneity of tinnitus. In order to identify tinnitus and provide theoretical guidance for the diagnosis and treatment, we propose a robust, data-efficient multi-task learning framework called Multi-band EEG Contrastive Representation Learning (MECRL). In this study, we collect resting-state EEG data from 187 tinnitus patients and 80 healthy subjects to generate a high-quality large-scale EEG dataset on tinnitus diagnosis, and then apply the MECRL framework on the generated dataset to obtain a deep neural network model which can distinguish tinnitus patients from the healthy controls accurately. Subject-independent tinnitus diagnosis experiments are conducted and the result shows that the proposed MECRL method is significantly superior to other state-of-the-art baselines and can be well generalized to unseen topics. Meanwhile, visual experiments on key parameters of the model indicate that the high-classification weight electrodes of tinnitus' EEG signals are mainly distributed in the frontal, parietal and temporal regions. In conclusion, this study facilitates our understanding of the relationship between electrophysiology and pathophysiology changes of tinnitus and provides a new deep learning method (MECRL) to identify the neuronal biomarkers in tinnitus.