MERLOT: A Distilled LLM-based Mixture-of-Experts Framework for Scalable Encrypted Traffic Classification

We present MERLOT, a scalable mixture-of-expert (MoE) based refinement of distilled large language model optimized for encrypted traffic classification. By applying model distillation techniques in a teacher-student paradigm, compact models derived from GPT-2-base retain high classification accuracy while minimizing computational costs. These models function as specialized experts in an MoE architecture, dynamically assigned via a gating network. Unlike generation-based methods, our approach directly classifies encrypted traffic using the final decoder token with contextual feature embedding as input. Experiments on 10 datasets show superior or competitive performance over the state-of-the-art models while significantly reducing resource demands, underscoring its effectiveness and robustness.

Adaptive Layer Splitting for Wireless LLM Inference in Edge Computing: A Model-Based Reinforcement Learning Approach

Optimizing the deployment of large language models (LLMs) in edge computing environments is critical for enhancing privacy and computational efficiency. Toward efficient wireless LLM inference in edge computing, this study comprehensively analyzes the impact of different splitting points in mainstream open-source LLMs. On this basis, this study introduces a framework taking inspiration from model-based reinforcement learning (MBRL) to determine the optimal splitting point across the edge and user equipment (UE). By incorporating a reward surrogate model, our approach significantly reduces the computational cost of frequent performance evaluations. Extensive simulations demonstrate that this method effectively balances inference performance and computational load under varying network conditions, providing a robust solution for LLM deployment in decentralized settings.

Snake Learning: A Communication- and Computation-Efficient Distributed Learning Framework for 6G

In the evolution towards 6G, integrating Artificial Intelligence (AI) with advanced network infrastructure emerges as a pivotal strategy for enhancing network intelligence and resource utilization. Existing distributed learning frameworks like Federated Learning and Split Learning often struggle with significant challenges in dynamic network environments including high synchronization demands, costly communication overheads, severe computing resource consumption, and data heterogeneity across network nodes. These obstacles hinder the applications of ubiquitous computing capabilities of 6G networks, especially in light of the trend of escalating model parameters and training data volumes. To address these challenges effectively, this paper introduces "Snake Learning", a cost-effective distributed learning framework. Specifically, Snake Learning respects the heterogeneity of inter-node computing capability and local data distribution in 6G networks, and sequentially trains the designated part of model layers on individual nodes. This layer-by-layer serpentine update mechanism contributes to significantly reducing the requirements for storage, memory and communication during the model training phase, and demonstrates superior adaptability and efficiency for both Computer Vision (CV) training and Large Language Model (LLM) fine-tuning tasks across homogeneous and heterogeneous data distributions.

Multi-Agent Probabilistic Ensembles with Trajectory Sampling for Connected Autonomous Vehicles

Autonomous Vehicles (AVs) have attracted significant attention in recent years and Reinforcement Learning (RL) has shown remarkable performance in improving the autonomy of vehicles. In that regard, the widely adopted Model-Free RL (MFRL) promises to solve decision-making tasks in connected AVs (CAVs), contingent on the readiness of a significant amount of data samples for training. Nevertheless, it might be infeasible in practice and possibly lead to learning instability. In contrast, Model-Based RL (MBRL) manifests itself in sample-efficient learning, but the asymptotic performance of MBRL might lag behind the state-of-the-art MFRL algorithms. Furthermore, most studies for CAVs are limited to the decision-making of a single AV only, thus underscoring the performance due to the absence of communications. In this study, we try to address the decision-making problem of multiple CAVs with limited communications and propose a decentralized Multi-Agent Probabilistic Ensembles with Trajectory Sampling algorithm MA-PETS. In particular, in order to better capture the uncertainty of the unknown environment, MA-PETS leverages Probabilistic Ensemble (PE) neural networks to learn from communicated samples among neighboring CAVs. Afterwards, MA-PETS capably develops Trajectory Sampling (TS)-based model-predictive control for decision-making. On this basis, we derive the multi-agent group regret bound affected by the number of agents within the communication range and mathematically validate that incorporating effective information exchange among agents into the multi-agent learning scheme contributes to reducing the group regret bound in the worst case. Finally, we empirically demonstrate the superiority of MA-PETS in terms of the sample efficiency comparable to MFBL.

Noise Distribution Decomposition based Multi-Agent Distributional Reinforcement Learning

Generally, Reinforcement Learning (RL) agent updates its policy by repetitively interacting with the environment, contingent on the received rewards to observed states and undertaken actions. However, the environmental disturbance, commonly leading to noisy observations (e.g., rewards and states), could significantly shape the performance of agent. Furthermore, the learning performance of Multi-Agent Reinforcement Learning (MARL) is more susceptible to noise due to the interference among intelligent agents. Therefore, it becomes imperative to revolutionize the design of MARL, so as to capably ameliorate the annoying impact of noisy rewards. In this paper, we propose a novel decomposition-based multi-agent distributional RL method by approximating the globally shared noisy reward by a Gaussian mixture model (GMM) and decomposing it into the combination of individual distributional local rewards, with which each agent can be updated locally through distributional RL. Moreover, a diffusion model (DM) is leveraged for reward generation in order to mitigate the issue of costly interaction expenditure for learning distributions. Furthermore, the optimality of the distribution decomposition is theoretically validated, while the design of loss function is carefully calibrated to avoid the decomposition ambiguity. We also verify the effectiveness of the proposed method through extensive simulation experiments with noisy rewards. Besides, different risk-sensitive policies are evaluated in order to demonstrate the superiority of distributional RL in different MARL tasks.

Self-Critical Alternate Learning based Semantic Broadcast Communication

Semantic communication (SemCom) has been deemed as a promising communication paradigm to break through the bottleneck of traditional communications. Nonetheless, most of the existing works focus more on point-to-point communication scenarios and its extension to multi-user scenarios is not that straightforward due to its cost-inefficiencies to directly scale the JSCC framework to the multi-user communication system. Meanwhile, previous methods optimize the system by differentiable bit-level supervision, easily leading to a "semantic gap". Therefore, we delve into multi-user broadcast communication (BC) based on the universal transformer (UT) and propose a reinforcement learning (RL) based self-critical alternate learning (SCAL) algorithm, named SemanticBC-SCAL, to capably adapt to the different BC channels from one transmitter (TX) to multiple receivers (RXs) for sentence generation task. In particular, to enable stable optimization via a nondifferentiable semantic metric, we regard sentence similarity as a reward and formulate this learning process as an RL problem. Considering the huge decision space, we adopt a lightweight but efficient self-critical supervision to guide the learning process. Meanwhile, an alternate learning mechanism is developed to provide cost-effective learning, in which the encoder and decoders are updated asynchronously with different iterations. Notably, the incorporation of RL makes SemanticBC-SCAL compliant with any user-defined semantic similarity metric and simultaneously addresses the channel non-differentiability issue by alternate learning. Besides, the convergence of SemanticBC-SCAL is also theoretically established. Extensive simulation results have been conducted to verify the effectiveness and superiorness of our approach, especially in low SNRs.

Imitation Learning based Alternative Multi-Agent Proximal Policy Optimization for Well-Formed Swarm-Oriented Pursuit Avoidance

Multi-Robot System (MRS) has garnered widespread research interest and fostered tremendous interesting applications, especially in cooperative control fields. Yet little light has been shed on the compound ability of formation, monitoring and defence in decentralized large-scale MRS for pursuit avoidance, which puts stringent requirements on the capability of coordination and adaptability. In this paper, we put forward a decentralized Imitation learning based Alternative Multi-Agent Proximal Policy Optimization (IA-MAPPO) algorithm to provide a flexible and communication-economic solution to execute the pursuit avoidance task in well-formed swarm. In particular, a policy-distillation based MAPPO executor is firstly devised to capably accomplish and swiftly switch between multiple formations in a centralized manner. Furthermore, we utilize imitation learning to decentralize the formation controller, so as to reduce the communication overheads and enhance the scalability. Afterwards, alternative training is leveraged to compensate the performance loss incurred by decentralization. The simulation results validate the effectiveness of IA-MAPPO and extensive ablation experiments further show the performance comparable to a centralized solution with significant decrease in communication overheads.

Rethinking Collaborative Perception from the Spatial-Temporal Importance of Semantic Information

Collaboration by the sharing of semantic information is crucial to enable the enhancement of perception capabilities. However, existing collaborative perception methods tend to focus solely on the spatial features of semantic information, while neglecting the importance of the temporal dimension in collaborator selection and semantic information fusion, which instigates performance degradation. In this article, we propose a novel collaborative perception framework, IoSI-CP, which takes into account the importance of semantic information (IoSI) from both temporal and spatial dimensions. Specifically, we develop an IoSI-based collaborator selection method that effectively identifies advantageous collaborators but excludes those that bring negative benefits. Moreover, we present a semantic information fusion algorithm called HPHA (historical prior hybrid attention), which integrates a multi-scale transformer module and a short-term attention module to capture IoSI from spatial and temporal dimensions, and assigns varying weights for efficient aggregation. Extensive experiments on two open datasets demonstrate that our proposed IoSI-CP significantly improves the perception performance compared to state-of-the-art approaches. The code associated with this research is publicly available at https://github.com/huangqzj/IoSI-CP/.

NetGPT: A Native-AI Network Architecture Beyond Provisioning Personalized Generative Services

Large language models (LLMs) have triggered tremendous success to empower daily life by generative information, and the personalization of LLMs could further contribute to their applications due to better alignment with human intents. Towards personalized generative services, a collaborative cloud-edge methodology sounds promising, as it facilitates the effective orchestration of heterogeneous distributed communication and computing resources. In this article, after discussing the pros and cons of several candidate cloud-edge collaboration techniques, we put forward NetGPT to capably deploy appropriate LLMs at the edge and the cloud in accordance with their computing capacity. In addition, edge LLMs could efficiently leverage location-based information for personalized prompt completion, thus benefiting the interaction with cloud LLMs. After deploying representative open-source LLMs (e.g., GPT-2-base and LLaMA model) at the edge and the cloud, we present the feasibility of NetGPT on the basis of low-rank adaptation-based light-weight fine-tuning. Subsequently, we highlight substantial essential changes required for a native artificial intelligence (AI) network architecture towards NetGPT, with special emphasis on deeper integration of communications and computing resources and careful calibration of logical AI workflow. Furthermore, we demonstrate several by-product benefits of NetGPT, given edge LLM's astonishing capability to predict trends and infer intents, which possibly leads to a unified solution for intelligent network management \& orchestration. In a nutshell, we argue that NetGPT is a promising native-AI network architecture beyond provisioning personalized generative services.

Decentralized Adaptive Formation via Consensus-Oriented Multi-Agent Communication

Adaptive multi-agent formation control, which requires the formation to flexibly adjust along with the quantity variations of agents in a decentralized manner, belongs to one of the most challenging issues in multi-agent systems, especially under communication-limited constraints. In this paper, we propose a novel Consensus-based Decentralized Adaptive Formation (Cons-DecAF) framework. Specifically, we develop a novel multi-agent reinforcement learning method, Consensus-oriented Multi-Agent Communication (ConsMAC), to enable agents to perceive global information and establish the consensus from local states by effectively aggregating neighbor messages. Afterwards, we leverage policy distillation to accomplish the adaptive formation adjustment. Meanwhile, instead of pre-assigning specific positions of agents, we employ a displacement-based formation by Hausdorff distance to significantly improve the formation efficiency. The experimental results through extensive simulations validate that the proposed method has achieved outstanding performance in terms of both speed and stability.