Federated learning (FL) is promising for privacy-sensitive fault diagnosis in the Industrial Internet of Things (IIoT). However, real-world deployments must address the coexistence of class-incremental fault evolution and dynamic edge participation, which leads to fragmented class exposure, catastrophic forgetting, and aggregation bias. To address this issue, we propose FedDiDy, a unified framework for federated class-incremental fault diagnosis under dynamic participation. FedDiDy combines a multi-head classifier for task decoupling, a raw-data-free conditional generator for historical knowledge replay, and a perception-aware aggregation mechanism for bias mitigation. Experiments on four datasets under Bernoulli, Cyclic, and Markov participation patterns show that FedDiDy consistently outperforms the compared baselines, with up to 15.1% absolute improvement in average accuracy and 14.44% reduction in forgetting rate.

Class-incremental continual learning on hypergraphs is challenging under limited replay memory. Buffered samples do not contribute equally to preserving historical higher-order structures. Existing replay methods mainly use random selection or loss-based selection. However, they often ignore structural cohesiveness. As a result, structurally important samples may be missed. We propose KTR ( K nowledge-preserving T russ-based R eplay), a structure-aware replay framework for continual learning on hypergraphs. KTR prioritizes buffered samples by combining hypertuss-based structural importance with current loss-based utility. It further performs constrained replay through structural filtering and probabilistic sampling. The framework supports both node classification and hyperedge classification. Experiments on four continual hypergraph benchmarks show that KTR improves replay performance under limited-memory settings, with the clearest gains on temporal hyperedge-classification benchmarks. Under the HGNN+ backbone with memory budget b = 0.1 , KTR improves ACC by up to 20.32 percentage points and reduces forgetting by up to 24.07 percentage points relative to PBR on MAG-Top20K. On node-classification benchmarks, KTR remains competitive with strong replay baselines, but it does not uniformly dominate all methods on every dataset. These results support the use of structure-aware replay in continual hypergraph learning, especially when higher-order structural cohesion provides informative replay signals.

With the rapid development of mobile internet technology and increasing concerns over data privacy, Federated Learning (FL) has emerged as a significant framework for training machine learning models. Given the advancements in technology, User Equipment (UE) can now process multiple computing tasks simultaneously, and since UEs can have multiple data sources that are suitable for various FL tasks, multiple tasks FL could be a promising way to respond to different application requests at the same time. However, running multiple FL tasks simultaneously could lead to a strain on the device’s computation resource and excessive energy consumption, especially the issue of energy consumption challenge. Due to factors such as limited battery capacity and device heterogeneity, UE may fail to efficiently complete the local training task, and some of them may become stragglers with high-quality data. Aiming at alleviating the energy consumption challenge in a multi-task FL environment, we design an automatic Multi-Task FL Deployment (MFLD) algorithm to reach the local balancing and energy consumption goals. The MFLD algorithm leverages Deep Reinforcement Learning (DRL) techniques to automatically select UEs and allocate the computation resources according to the task requirement. Extensive experiments validate our proposed approach and showed significant improvements in task deployment success rate and energy consumption cost.

The distinct attributes of Internet of Things (IoTs) devices, including the disparity between training and testing data distributions and limited availability of training data, pose challenges for deep learning models in effectively addressing unseen domain segmentation tasks. Federated Learning (FL) can increase the participation of various data contributors, thus has great potential to develop a unified framework to shed light on the relationship between unseen domains and generalized domains. In this paper, we proposed an FL-based unseen domain segmentation model. The architecture includes (1) an external memory module as an object feature guide to reduce the feature ambiguity of unseen domain objects. (2) A re-attention activation mechanism for better completing localization of unseen domain objects, enhancing the features of potential targets and suppressing interference features. (3) A self-supervised learning paradigm for achieving specific object feature exploration. Based on flexible splitting and combining, our model is able to capture both personalization and generalization capabilities, the client side retains a strong personalization ability, while the server side has a strong generalization ability. Moreover, taking into account the inherent limitations in computing and storage resources commonly associated with IoT devices, the introduced model leverages the concept of optional dependencies to enable efficient inference within resource-constrained client environments. Our proposed model is validated through extensive experiments. The approach proposed in this paper outperforms the generalization capabilities of state-of-the-art work on several benchmarks.

Today's business environment is characterized by uncertainty and competition, so the capability to adapt to the evolving era and unforeseen challenges is essential in business strategies. Recent studies on extended enterprise indicate that collaboration among different stakeholders is beneficial for surviving these unexpected changes. However, the barriers such as market uncertainty, privacy and trust concerns, and individual contribution evaluation limit the implementation and application of the extended enterprise concept. Federated learning (FL), in which multiple enterprise entities can use a shared model while retaining all training data locally, has emerged as a promising artificial intelligence (AI) solution for accumulating insights from multiple stakeholders and providing collaborative decision-making. Furthermore, the enhanced privacy-protection benefits of FL remove the barriers to implementing extended enterprise collaboration. In particular, an FL central server manages the local updates of multiple enterprise entities (FL clients) and aggregates their contributions to improve the global model training. Meanwhile, to address the time-series graph learning problem in most business environments, we incorporate temporal convolutional network, graph convolutional neural network, and gated recurrent unit architecture into FL to capture the temporal-spatial dependencies in individual data sources. Furthermore, we use traffic flow forecasting as the use case of our proposed framework to verify its effectiveness. Finally, the experimental results on a real traffic flow dataset and the comparison results with the state-of-the-art baseline methods show that our proposed solution achieves superior performance.

More and more applications are promoting cus-tomized or personalized services. In order for these applications to provide meaningful output, it collects users’ personal information over time. Some personal information (e.g. education level or income level) can only be captured by users actively updating their profile to reflect these changes. We refer to these as long-term time series data, as they do not change frequently. If applications can keep up to date on a diverse and large set of personal features, they can provide higher quality service. However, this quality of service comes at the cost of the user sacrificing their privacy. There has been numerous research on protecting privacy of time series data for context aware services, but the privacy leakage of personal information updates during the whole life-cycle of the series has received only scant attention.Motivated users concerned about their privacy, we discuss in detail the privacy leakage risk, focusing on long-term time-series data from the perspective of game theory. Then, we propose a reward-privacy model, targeting the privacy-aware data-updates for the entire life-cycle in context-aware services by leveraging a three-party Stackelberg game. We theoretically prove that a Nash Equilibrium exists in the proposed model, and then use simulations to validate that a Nash Equilibrium exists for different parameters of the productivity function. By using our proposed framework, users have guidance to decide not only the timing of submitting personal updates, but also the granularity or obscurity level for their data.

The ubiquity of devices in Internet of Things (IoT) has opened up a large source for IoT data. Machine learning (ML) models with big IoT data is beneficial to our daily life in monitoring air condition, pollution, climate change, etc. However, centralized conventional ML models rely on all clients' data at a central server, which seriously threatens user privacy. Federated learning (FL) emerges as a promising solution aiming to protect user privacy by enabling model training on a large corpus of decentralized data. The recent studies indicate FL suffers from the heterogeneity issue as it treats all clients' data equally, that is, FL might sacrifice the performance of the majority of clients to accommodate the performance of the minority of clients with low usability data. In order to overcome this issue, a reinforcement learning (RL)-based intelligent central server with the capability of recognizing heterogeneity is implemented, which can help lead the trend toward better performance for majority of clients. To be specific, an FL central server analyses the benefits of different collaboration by capturing the intricate patterns in heterogeneous clients based on rating feedback and then updates clients' weights iteratively, until it establishes a coalition of clients with quasioptimal performance. The experimental results on three real data sets under various heterogeneity levels demonstrate the superior performance of the proposed solution.

As the next‐generation power grid system, the smart grid can realize the balance of supply and demand and help in communication security and privacy protection. However, real‐time power consumption data collection might expose the users’ privacy information, such as their living habits and economic conditions. In addition, during the process of data transmission, it may lead to data inconsistency between the user side and the storage side. Blockchain provides tamper‐resistant and traceable characteristics for solving these problems, and ring signature schemes provide an anonymous authentication mechanism. Therefore, in this work, we consider the applications of ring signature scheme in smart grid based on blockchain. We introduce the notion of multi‐authority traceable ring signature (MA‐TRS) scheme for distributed setting. In our scheme, there is an auditing node that can distinguish the identity of the real signer from the ring without any secret information. Last but not least, we prove that the proposed scheme is unforgeable, anonymous, and traceable.

The IoT era observes the increasing demand for data to support various applications and services. The Mobile Crowdsensing (MCS) system then emerged. By utilizing the hybrid intelligence of humans and sensors, it is significantly beneficial to keep collecting high‐quality sensing data for all kinds of IoT applications, such as environmental monitoring, intelligent healthcare services, and traffic management. However, the service quality of MCS systems relies on a dedicated designed task allocation framework, which needs to consider the participant resource bottleneck and system utility at the same time. Recent studies tend to use a different solution to solve the two challenges. The incentive mechanism is for resolving the participant shortage problem, and task assignment methods are studied to find the best match of participants and system utility goal of MCS. Thus, existing task allocation frameworks fail to consider the participant’s expectations deeply. We propose a semiopportunistic concept‐based solution to overcome this issue. Similar to the “shared mobility” concept, our proposed task allocation framework can offer the participants routing advice without disturbing their original travel plan. The participant can accomplish the sensing request on his route. We further consider the system constraints to determine a subgroup of participants that can obtain the utility optimization goal. Specifically, we use the Graph Attention Network (GAT) to produce the target sensing area’s virtual representation and provide the participant with a payoff‐maximized route. Such a method makes our solution adapt to most of MCS scenarios’ conditions instead of using fixed system settings. Then, a reinforcement learning‐ (RL‐) based task assignment is adopted, which can help the MCS system towards better performance improvements while support different utility functions. The simulation results on various conditions demonstrate the superior performance of the proposed solution.