Metaverse over wireless networks is an emerging use case of the sixth generation (6G) wireless systems, posing unprecedented challenges in terms of its multi-modal data transmissions with stringent latency and reliability requirements. Towards enabling this wireless metaverse, in this article we propose a novel semantic communication (SC) framework by decomposing the metaverse into human/machine agent-specific semantic multiverses (SMs). An SM stored at each agent comprises a semantic encoder and a generator, leveraging recent advances in generative artificial intelligence (AI). To improve communication efficiency, the encoder learns the semantic representations (SRs) of multi-modal data, while the generator learns how to manipulate them for locally rendering scenes and interactions in the metaverse. Since these learned SMs are biased towards local environments, their success hinges on synchronizing heterogeneous SMs in the background while communicating SRs in the foreground, turning the wireless metaverse problem into the problem of semantic multiverse communication (SMC). Based on this SMC architecture, we propose several promising algorithmic and analytic tools for modeling and designing SMC, ranging from distributed learning and multi-agent reinforcement learning (MARL) to signaling games and symbolic AI.
translated by 谷歌翻译
While witnessing the noisy intermediate-scale quantum (NISQ) era and beyond, quantum federated learning (QFL) has recently become an emerging field of study. In QFL, each quantum computer or device locally trains its quantum neural network (QNN) with trainable gates, and communicates only these gate parameters over classical channels, without costly quantum communications. Towards enabling QFL under various channel conditions, in this article we develop a depth-controllable architecture of entangled slimmable quantum neural networks (eSQNNs), and propose an entangled slimmable QFL (eSQFL) that communicates the superposition-coded parameters of eS-QNNs. Compared to the existing depth-fixed QNNs, training the depth-controllable eSQNN architecture is more challenging due to high entanglement entropy and inter-depth interference, which are mitigated by introducing entanglement controlled universal (CU) gates and an inplace fidelity distillation (IPFD) regularizer penalizing inter-depth quantum state differences, respectively. Furthermore, we optimize the superposition coding power allocation by deriving and minimizing the convergence bound of eSQFL. In an image classification task, extensive simulations corroborate the effectiveness of eSQFL in terms of prediction accuracy, fidelity, and entropy compared to Vanilla QFL as well as under different channel conditions and various data distributions.
translated by 谷歌翻译
Recent advances in Federated Learning (FL) have paved the way towards the design of novel strategies for solving multiple learning tasks simultaneously, by leveraging cooperation among networked devices. Multi-Task Learning (MTL) exploits relevant commonalities across tasks to improve efficiency compared with traditional transfer learning approaches. By learning multiple tasks jointly, significant reduction in terms of energy footprints can be obtained. This article provides a first look into the energy costs of MTL processes driven by the Model-Agnostic Meta-Learning (MAML) paradigm and implemented in distributed wireless networks. The paper targets a clustered multi-task network setup where autonomous agents learn different but related tasks. The MTL process is carried out in two stages: the optimization of a meta-model that can be quickly adapted to learn new tasks, and a task-specific model adaptation stage where the learned meta-model is transferred to agents and tailored for a specific task. This work analyzes the main factors that influence the MTL energy balance by considering a multi-task Reinforcement Learning (RL) setup in a robotized environment. Results show that the MAML method can reduce the energy bill by at least 2 times compared with traditional approaches without inductive transfer. Moreover, it is shown that the optimal energy balance in wireless networks depends on uplink/downlink and sidelink communication efficiencies.
translated by 谷歌翻译
信息指标的年龄无法正确描述状态更新的内在语义。在一个智能反映表面上的合作中继通信系统中,我们提出了语义年龄(AOS),用于测量状态更新的语义新鲜度。具体而言,我们专注于从源节点(SN)到目标的状态更新,该状态被称为马尔可夫决策过程(MDP)。 SN的目的是在最大发射功率约束下最大程度地提高AOS和能源消耗的预期满意度。为了寻求最佳的控制政策,我们首先在派利时间差异学习框架下推出了在线深层演员批评(DAC)学习方案。但是,实践实施在线DAC在SN和系统之间无限重复的互动中构成了关键的挑战,这可能是危险的,尤其是在探索过程中。然后,我们提出了一个新颖的离线DAC方案,该方案估算了先前收集的数据集的最佳控制策略,而无需与系统进行任何进一步的交互。数值实验验证了理论结果,并表明我们的离线DAC方案在平均效用方面显着优于在线DAC方案和最具代表性的基线,这表明了对数据集质量的强大鲁棒性。
translated by 谷歌翻译
在本文中,我们建议在分散的设置中解决一个正规化的分布鲁棒性学习问题,并考虑到数据分配的变化。通过将Kullback-Liebler正则化功能添加到可靠的Min-Max优化问题中,可以将学习问题降低到修改的可靠最小化问题并有效地解决。利用新配制的优化问题,我们提出了一个强大的版本的分散的随机梯度下降(DSGD),分布在分布方面具有强大的分散性随机梯度下降(DR-DSGD)。在一些温和的假设下,前提是正则化参数大于一个,我们从理论上证明DR-DSGD达到了$ \ MATHCAL {O} \ left的收敛速率$,其中$ k $是设备的数量,而$ t $是迭代次数。仿真结果表明,我们提出的算法可以提高最差的分配测试精度,最高$ 10 \%$。此外,DR-DSGD比DSGD更有效,因为它需要更少的沟通回合(最高$ 20 $ $倍)才能达到相同的最差分配测试准确性目标。此外,进行的实验表明,在测试准确性方面,DR-DSGD会导致整个设备的性能更公平。
translated by 谷歌翻译
量子联合学习(QFL)最近受到了越来越多的关注,其中量子神经网络(QNN)集成到联邦学习(FL)中。与现有的静态QFL方法相反,我们在本文中提出了可靠的QFL(SLIMQFL),这是一个动态QFL框架,可以应对时变的通信通道和计算能量限制。通过利用QNN的独特性质,可以分别训练并动态利用其角度参数,从而使其可行。模拟结果证实了SLIMQFL比香草QFL更高的分类精度,尤其是在较差的通道条件下。
translated by 谷歌翻译
经典的媒体访问控制(MAC)协议是可解释的,但是它们的任务不可能控制信号传导消息(CMS)不适合新兴任务 - 关键任务应用程序。相比之下,基于神经网络(NN)协议模型(NPM)学会生成特定于任务的CMS,但其理由和影响缺乏可解释性。为了填补这一空白,在本文中,我们首次提出了通过将NPM转换为概率逻辑编程语言(ProBlog)编写的可解释的符号图来构建的语义协议模型(SPM)。通过在将NPM视为CM发生器的同时提取和合并共同的CM及其连接,可以可行。通过广泛的模拟,我们证实了SPM在仅占据0.02%内存的同时紧密近似其原始NPM。通过利用其可解释性和记忆效率,我们演示了几种支持SPM的应用程序,例如SPM重新配置,以避免碰撞,并通过语义熵计算和存储多个SPM来比较不同的SPM,以应对非平稳环境。
translated by 谷歌翻译
本文为视觉变压器(VIT)体系结构提供了分布式学习解决方案。与卷积神经网络(CNN)架构相比,VIT通常具有较大的模型尺寸,并且计算昂贵,从而使联合学习(FL)不适合使用。拆分学习(SL)可以通过分裂模型并在拆分层上传达隐藏的表示形式(也称为粉碎的数据)来避开此问题。尽管如此,VIT的粉碎数据与输入数据一样大,在违反数据隐私时否定了SL的通信效率。为了解决这些问题,我们通过随机打孔和压缩原始粉碎的数据来提出一种新形式的切割数据。利用这一点,我们为VIT,CUTMIXSL开发了一个新颖的SL框架,并传达了切割的数据。 cutmixsl不仅降低了通信成本和隐私泄漏,而且固有地涉及cutmix数据增强,从而提高了准确性和可扩展性。模拟证实了cutmixsl的表现优于平行的SL等基线,并将其与SL集成在一起。
translated by 谷歌翻译
古典和集中的人工智能(AI)方法要求将数据从生产者(传感器,机器)移至饥饿的数据中心,从而在侵犯隐私的同时,由于计算和通信资源的需求而引起的环境问题。缓解这种高能源成本的新兴替代方案建议在通常低功率的设备上有效分发或联合跨设备的学习任务。本文提出了一个新的框架,用于分析分布式和联合学习(FL)中的能量和碳足迹。提出的框架量化了香草FL方法和基于共识的完全分散方法的能量足迹和碳当量排放。我们讨论支持绿色FL设计并支撑其可持续性评估的最佳界限和运营点。分析了新兴5G行业垂直行业的两项案例研究:它们量化了持续和强化学习设置的环境足迹,在这些培训过程中,定期重复训练过程以进行持续改进。对于所有情况,分布式学习的可持续性都取决于满足沟通效率和学习者人口规模的特定要求。考虑到目标工业应用的模型和数据足迹,还应将能源和测试精度交易。
translated by 谷歌翻译
牛顿型方法由于其快速收敛而在联合学习中很受欢迎。尽管如此,由于要求将Hessian信息从客户发送到参数服务器(PS),因此他们遭受了两个主要问题:沟通效率低下和较低的隐私性。在这项工作中,我们介绍了一个名为Fednew的新颖框架,其中无需将Hessian信息从客户传输到PS,因此解决了瓶颈以提高沟通效率。此外,与现有的最新技术相比,Fednew隐藏了梯度信息,并导致具有隐私的方法。 Fednew中的核心小说想法是引入两个级别的框架,并在仅使用一种交替的乘数方法(ADMM)步骤更新逆Hessian级别产品之间,然后使用Newton的方法执行全局模型更新。尽管在每次迭代中只使用一个ADMM通行证来近似逆Hessian梯度产品,但我们开发了一种新型的理论方法来显示Fednew在凸问题上的融合行为。此外,通过利用随机量化,可以显着减少通信开销。使用真实数据集的数值结果显示了与现有方法相比,在通信成本方面,Fednew的优越性。
translated by 谷歌翻译