As sixth-generation (6 G) networks evolve towards AI-native architectures, Federated Learning (FL) is becoming a cornerstone for enabling intelligent services by leveraging distributed data from diverse sources such as Integrated Sensing and Communication (ISAC) devices and edge clients. However, a critical challenge lies in efficiently handling data removal requests, mandated by regulations like the “right to be forgotten”. This problem is significantly exacerbated by the extreme data heterogeneity ( non-IID) inherent across diverse 6 G devices and the communication constraints of wireless networks. To address these challenges, this paper proposes SeFUL, a novel two-stage federated unlearning framework tailored for the security and privacy demands of 6 G systems. SeFUL first proactively mitigates data heterogeneity by partitioning clients into clusters based on their data distribution similarity. Subsequently, a lightweight, information-theoretic unlearning strategy is deployed. This method surgically erases information by optimizing a composite loss function which, in the latent space, pushes the feature representations of forgotten data away from their original class cluster and towards samples from other classes, while reinforcing knowledge from the retain set. Comprehensive experiments on benchmark datasets demonstrate that SeFUL achieves unlearning performance on par with the gold standard of complete model retraining. It successfully reduces forget-set accuracy to nearly random guess levels while preserving high retain-set accuracy, significantly outperforming existing state-of-the-art methods. Furthermore, Membership Inference Attacks (MIAs) confirm that SeFUL effectively reduces privacy risks to a level statistically indistinguishable from a fully retrained model, validating its efficacy as a robust privacy-preserving mechanism.

Federated Learning (FL) has emerged as a promising framework to address data privacy concerns associated with mobile devices, in contrast to conventional Machine Learning (ML). However, traditional FL encounters significant challenges due to the heterogeneities among different clients. Clustered Federated Learning (CFL) has demonstrated effectiveness in mitigating the data heterogeneity challenge, which significantly limits a broader application of FL. Nevertheless, existing CFL approaches often tightly couple the clustering process with the main FL process, affecting the flexibility and performance of CFL. In this paper, we propose a pre-clustering-based CFL approach, named SnapCFL, which decouples the CFL process into pre-clustering and main FL stages, considering both the impact of heterogeneity on CFL accuracy and the framework's flexibility. The pre-clustering stage models the measurement of data similarity as a two-sample hypothesis testing problem to more accurately group clients and alleviate data heterogeneity. In the main FL stage, a constraint-based client selection method is employed to address the system heterogeneity problem. We conduct extensive experiments using popular datasets with various heterogeneity settings. The results demonstrate that SnapCFL achieves excellent performance in terms of accuracy and efficiency. Compared to five other state-of-the-art approaches, SnapCFL can improve model accuracy by 0.7%$\sim$36.4%, and achieve the same level of accuracy with at least 0.08× the convergence time.

Contrastive unsupervised representation learning (CURL) is a technique that seeks to learn feature sets from unlabeled data. It has found widespread and successful application in unsupervised feature learning, with the design of positive and negative pairs serving as the type of data samples. While CURL has seen empirical successes in recent years, there is still room for improvement in terms of the pair data generation process. This includes tasks such as combining and re-filtering samples, or implementing transformations among positive/negative pairs. We refer to this as the sample selection process. In this article, we introduce an optimized pair-data sample selection method for CURL. This method efficiently ensures that the two types of sampled data (similar pair and dissimilar pair) do not belong to the same class. We provide a theoretical analysis to demonstrate why our proposed method enhances learning performance by analyzing its error probability. Furthermore, we extend our proof into PAC-Bayes generalization to illustrate how our method tightens the bounds provided in previous literature. Our numerical experiments on text/image datasets show that our method achieves competitive accuracy with good generalization bounds.

In meta-learning, the learner extracts knowledge from the observed tasks and quickly adapts to unseen future tasks. We provide a novel and rigorous-analyzed probably approximately correct Bayes (PAC-Bayes) meta-learning method with parameterized bounds, which learns a posterior distribution from given priors and the data samples. The proposed method is designed to improve generalization stabilities with tighter bound guarantees. We prove that the proposed PAC-Bayes bound of the meta-learner is tighter than previous work under a given condition in a rigorous theoretical way. An explicit theoretical analysis of the generalization errors is also given based on the proposed meta-learning method. Using the proposed bound in our work, we deduce an optimal objective function of the meta-learner that should be minimized during the meta-training process. We validate our theoretical hypothesis by conducting synthetic and real-world environments for meta-learning. Both rigorous proofs and experimental results reveal that our method yields state-of-the-art performances under a variety of meta-learning tasks in terms of accuracy and uncertainty robustness.

Collaborative Inference is a prospective paradigm for accelerating Deep Neural Network (DNN) inference by harnessing the computational resources of multiple devices. However, in highly lossy network environments, such as those encountered in wireless communication systems, the transmission loss of intermediate feature maps between devices can result in significant degradation of co-inference accuracy. In this paper, we first conduct a comprehensive investigation into the impact of intermediate feature map loss in real-world wireless scenarios and provide an in-depth analysis of loss patterns under UDP transmission. Motivated by these observations, we introduce Robust Co-inference Framework (RCIF), a novel framework that employs a hierarchical mask strategy to selectively drop activations at two different scales of feature maps. This approach enhances the robustness of DNN co-inference in the presence of network losses. Our evaluation on a variety of datasets and network architectures demonstrates that RCIF significantly enhances the accuracy and robustness of distributed DNN co-inference under highly lossy network conditions. Specifically, our results show that RCIF can achieve up to a 659% increase in accuracy compared to the original model under particularly poor network conditions.

Federated Learning (FL) is a widely utilized distributed learning methodology that facilitates real-time continuous learning while preserving client privacy. In most FL implementations, it is assumed that all edge clients possess sufficient computational capabilities to participate in the training of a Deep Neural Network (DNN) model. However, in practical applications, some clients may have limited resources and can only train a significantly smaller local model. To address system heterogeneity, this paper introduces Fed-SDS, an approach that adaptively tailors sparsity strategies for local models. In comparison to existing sparse FL schemes, Fed-SDS improves convergence and enhances model accuracy through a novel channel-wise sparsity metric, namely Mean Weight Magnitude with Gradient (MWMG). In our experiments, we compared Fed-SDS with other sparse FL methods. Empirical results demonstrate that while other sparse methods can significantly impact convergence, Fed-SDS can achieve the highest task accuracies and convergence speed in various system and data heterogeneity scenarios.

With the rapid growth of the number of devices generating and collecting data, there has been a surge in the large-scale emergence of artificial intelligence (AI) applications predicated on Internet of Things (IoT) networks and terminals. Collaborative Inference is a prospective paradigm for accelerating Deep Neural Network (DNN) inference by harnessing the computational resources of multiple IoT devices. However, in highly lossy network environments, such as those encountered in wireless communication systems, the transmission loss of intermediate feature maps between devices can result in significant degradation of co-inference accuracy. In this paper, we first conduct a comprehensive investigation into the impact of intermediate feature map loss in real-world wireless scenarios and provide an in-depth analysis of loss patterns under UDP transmission. Motivated by these observations, we introduce Robust Co-inference Framework (RCIF), a novel framework that employs a hierarchical mask strategy to selectively drop activations at two different scales of feature maps. This approach enhances the robustness of DNN co-inference in the presence of network losses. Our evaluation on a variety of datasets and network architectures demonstrates that RCIF significantly enhances the accuracy and robustness of distributed DNN co-inference under highly lossy network conditions. Specifically, our results show that RCIF can achieve up to a 659% increase in accuracy compared to the original model under particularly poor network conditions.

Human whole-body pose estimation is a challenging task since the model needs to learn more keypoints than the body-only case. To meet the needs of real-time performance while maintaining accuracy is also a hard issue in whole-body pose estimation due to the learning capability of lightweight networks. In order to solve the above problems to a large extent, we propose a light whole-body pose estimation method with an optimized training strategy. The model is designed based on bottom-up architecture as a base network followed by a refinement network. We propose a two-stage training process, which learns rough features in the first stage and then improves estimation precision in the second stage. An online data augmentation procedure is proposed in the second stage to improve refinement performance. We also introduce a separate learning refinement structure that fine-tunes for body, foot, and hand part independently. Experimental results show that our method improves over 8%–10% average precision compared with other lightweight state-of-the-art approaches in the whole-body pose estimation task, with nearly a quarter (25%) size of model parameters saved.

Wireless control system for industrial automation has been gaining increasing popularity in recent years thanks to their ease of deployment and the low cost of their components. However, traditional low sample rate industrial wireless sensor networks cannot support high-speed application, while high-speed IEEE 802.11 networks are not designed for real-time application and not able to provide deterministic feature. Thus, in this paper, we propose Det-WiFi, a real-time TDMA MAC implementation for high-speed multihop industrial application. It is able to support high-speed applications and provide deterministic network features since it combines the advantages of high-speed IEEE802.11 physical layer and a software Time Division Multiple Access (TDMA) based MAC layer. We implement Det-WiFi on commercial off-the-shelf hardware and compare the deterministic performance between 802.11s and Det-WiFi under the real industrial environment, which is full of field devices and industrial equipment. We changed the hop number and the packet payload size in each experiment, and all of the results show that Det-WiFi has better deterministic performance.