Task-oriented video compression aims to eliminate redundancy while preserving task-critical information. However, existing spatial domain methods incur high computational overhead, whereas temporal domain approaches often rely on black-box confidence scores that may discard taskrelevant frames. These methods follow an implicit informationpreservation paradigm that entangles redundancy and relevance, yielding opaque decision-making. In this paper, we therefore reformulate it as an explicit and explainable frame filtering method. Instead of relying on black-box confidence scores, task relevance is quantified by an explainable saliency score grounded in explicit model attribution and statistical aggregation, providing a transparent criterion for frame filtering. This offline-defined saliency metric supervises a lightweight online regressor, so that each online decision inherits the same explainable semantic meaning while avoiding heavy computation at the edge. Specifically, frame filtering is decomposed into two sequential and explainable steps: a similarity detector first removes structurally redundant frames, and a saliency-guided filter then discards frames with limited contribution to the downstream task. Experimental results demonstrate the effectiveness of the proposed method.

Federated learning emerges as a key enabler toward pervasive intelligence across IoT ecosystems with provable privacy guarantees. While recent efforts on client selection have been made for optimizing its communication efficiency in iterative model aggregation over resource-constrained networks, their scalability fundamentally breaks down in dense deployments. This limitation stems from the NP-hard complexity of congestion-aware scheduling, where co-channel interference creates exponentially growing solution spaces. In this context, we present a novel client selection framework with asymptotic scalability in massive IoT, which leverages the intrinsic graph topology with insights from statistical physics. First, this work formulate a universal client selection problem, capturing both positive network externalities derived from collaborative knowledge exchange and congestion effects induced by co-channel interference. This formulation is then transformed into a node classification task via Ising spin Hamiltonian mapping, establishing an explicit connection between federated learning, statistical physics, and graph optimization. Building on this foundation, we develop a lightweight graph neural solver that adaptively selects clients via recognizing node state with iterative neighbor aggregation of learnable embeddings. Comprehensive experiments validate that our approach maintains state-of-the-art scheduling performance, while scaling to network sizes orders of magnitude beyond what conventional methods can handle.

Task-oriented communications for multi-modal applications emerge with the intelligence-oriented evolution of Internet of Things, where massive computation offloading with heterogeneous streaming requirements greatly challenges the existing mobile networks. Compared with semantic coding which reduces intra-modality redundancy by feature extraction, cross-modal coding further exploits inter-modality association and thus acts as a promising solution. However, unresolved information-theoretic issues hinder its full promise: 1) how to characterize the achievable region of cross-modal coding for task-oriented communications, and 2) to what extent can task-oriented communications benefit from exploiting inter-modality association. Therefore, this work first establishes a cross-modal rate-distortion function for task-oriented communications, and proves the feasibility of optimizing its information-bottleneck inspired transformation for guiding the design of learnable codec. In particular, the optimal feature representation is specified by a converging iterative solver under perfect statistical knowledge. Second, we prove a new bound on compression gains of cross-modal coding in task-oriented communications, based on a sufficient condition for cross-modal representation to be effective. Furthermore, a typical learnable codec is designed, whose loss function can be theoretically interpreted by our derived results. Finally, experimental evaluations verify the positive correlation between cross-modal coding gains and inter-modality association levels.

Multi-modal visual signals are prevalent in emergency communications. To ensure high reliability of signal transmission under bandwidth constraints, it is crucial to compress redundant information both within and between modalities as much as possible, and ensure the fidelity of the reconstructed signals. Most existing studies depend exclusively on single-modal coding schemes and fail to effectively leverage the semantic correlations between modalities. In this paper, we introduce an end-to-end general cross-modal visual coding scheme, namely CMVC, which aims to jointly compress multi-modal visual signals (such as visible and infrared signals). First, we propose a cross-modal asynchronous entropy module that extracts common features using a cross-attention mechanism. Additionally, we enhance the accuracy of common features extraction by maximizing mutual information loss. This module further compresses multi-modal visual signals by compressing only the residual features between modalities. Second, we propose a cascaded enhancement module based on cross-modal Mamba that fuses complementary information to enhance the reconstruction quality of multi-modal visual signals. Finally, extensive experimental results demonstrate that our scheme significantly outperforms other advanced methods on visible-infrared datasets. Even at low bitrates, multi-modal visual signals can still achieve excellent reconstruction quality. Additionally, our scheme exhibits outstanding compression and reconstruction performance when applied to visible-depth signals, effectively demonstrating its robustness and generalizability.

Various distributed learning approaches emerge for enabling ubiquitous intelligence in Internet of Things (IoT) without sacrificing data privacy. To improve communication efficiency in frequent knowledge exchange over resource-constrained IoT, different techniques for client selection have been proposed. However, the intractable scalability issues remain to be addressed in massive IoT, since highly-coupled co-channel interference adds exponential complexity to combinatorial client selection. In this work, we develop a client selection framework highly-scalable to large-scale networks with thousands of devices, which exploits the inherent graph structure derived from knowledge exchange and co-channel interference. Specifically, we first model a client selection problem for jointly optimizing learning performance and system cost under volatile network conditions. The formulated problem is encoded into a node classification problem by a directed graph. Subsequently, a general yet simple solver is designed based on graph neural networks, which selects clients by classifying node status with recursive neighborhood aggregation of node representations. Finally, extensive experimental results demonstrate that the proposed approach can perform on par with state-of-the-art methods, while scaling to networks whose size is orders of magnitude larger than they can handle.

With the development of human–machine interactions, users are increasingly evolving toward an immersion experience with multidimensional stimuli. Facing this trend, cross-modal collaborative communication is considered an effective technology in the Industrial Internet of Things (IIoT). In this article, we focus on open issues about resource reuse, pair interactivity, and user assurance in cross-modal collaborative communication to improve Quality of Service (QoS) and users’ satisfaction. Therefore, we propose a novel architecture of modal-aware resource allocation to solve these contradictions. First, taking all the characteristics of multimodal into account, we introduce network slices to visualize resource allocation, which is modeled as a Markov decision process (MDP). Second, we decompose the problem by the transformation of probabilistic constraint and Lyapunov Optimization. Third, we propose a deep reinforcement learning (DRL) decentralized method in the dynamic environment. Meanwhile, a federated DRL framework is provided to overcome the training limitations of local DRL models. Finally, numerical results demonstrate that our proposed method performs better than other decentralized methods and achieves superiority in cross-modal collaborative communications.

Digital twin (DT) has emerged as a key enabler for the intelligent-oriented evolution of mobile networks. With the rise of privacy concerns for enabling intelligent applications in DT-empowered mobile networks (DTMNs), federated learning has garnered wide attention due to its potential on breaking down data silos. However, the data privacy of federated learning is greatly threatened by emerging gradient leakage attacks, and the need for frequent knowledge exchange limits its training efficiency over resource-constrained DTMNs. To circumvent such dilemmas, this work first proposes a privacy-enhanced federated learning framework based on cloud-edge-client collaborations. Particularly, model splitting between clients and edge servers makes gradient leakage attacks computationally prohibitive, and cloud-side partial model aggregation provides hierarchical data utility. To improve the training efficiency of the proposed learning framework, we further establish its communication and computation cost models, and develop a DT-assisted multi-agent deep reinforcement learning-based resource scheduler for joint client association and channel assignment. Finally, as a case study of intelligent applications in DTMNs, a human-robot collaborative nursing task is designed to evaluate the practical performance of our proposed scheduler. Experimental results show its superiority in saving training costs and preserving learning accuracy.

Personalized content sharing will inevitably become one of the core applications of mobile Internet of Things. However, the existing strategies for content sharing are far from effective content personalization, since they either fail to protect the diversity of shared content or harm the enthusiasm of users to participate in cooperation. How to optimize the tradeoff between content personalization and sharing efficiency thus becomes an extremely challenging problem. To circumvent this dilemma, we propose a social-aware personalized content-sharing strategy based on mobile crowdsensing (MCS), which specially introduces positive network externalities derived from MCS and the social network. Specifically, we design a two-stage pricing-participation game to model the interactions between mobile users and a profit-making service provider. By solving the subgame-perfect Nash equilibrium (NE) of the proposed game, an efficient participation mechanism and an optimal-pricing strategy are developed. First, users’ decision selection of whether to join MCS is modeled as a social-aware MCS participation game (SA-MPG), and two algorithms for solving the Pareto-optimal NE of SA-MPG are designed. Subsequently, the pricing issue for network operators is investigated by exploiting the supermodularity of SA-MPG. Stochastic network model and real-world data set-based simulations corroborate the significant gain of our proposed strategy.

Machine-type communication (MTC) has been considered as one of the key enablers for intelligent Internet of Things (IoT) applications. However, existing evaluating metrics, no matter the Quality of Service (QoS) or Quality of Experience (QoE), cannot truly and accurately reflect the quality of MTC when it serves machine decision making. To address this problem, this work proposes a new performance index, Quality of Decision (QoD), to elegantly capture the essence of MTC and precisely depict the corresponding functionality. First, the physical components and logical processes that affect the quality of MTC in analytics-oriented scenarios are carefully studied. Second, through jointly considering the factors of the commonness and individuality, we propose a layered QoD framework capable of independently evaluating and monitoring the quality of data to be acquired, delivered, and processed for enabling machine decision making. Third, we design a typical QoD-driven transmission scheme for video analytics by avoiding over provisioning of sensing and communication capabilities, which shows super efficiency compared to traditional human-perception-oriented approaches. We believe that the utilization of QoD will significantly promote the application of MTC in building various intelligent IoT systems.

Integrated sensing, communication, and computation (ISCC) will become a key enabler for automation applications. However, since the performance region of ISCC has a higher dimension than those of traditional wireless networks, existing schedulers typically fail to simultaneously meet the heterogeneous requests in ISCC. In this work, we propose a novel wireless scheduling architecture to explore the coordination gains of sensing, communication, and computation from a perspective of joint optimization. Specifically, we first construct an implementation framework of ISCC by combining the mobile edge computing paradigm with the integrated sensing and communication technology, where the inherent tradeoff between sensing, communication, and computation performance is characterized. Next, a joint device association and subchannel assignment problem is formulated to capture the network externalities induced by resource competition among mobile devices with multi-functional requirements. Due to its intractability, we then reformulate it in the matching theoretical manner. To obtain a mutually satisfactory solution under externalities, an iterative matching algorithm is developed by introducing pairwise stability and proved to be convergent and stable. The extensive simulations elucidate the significant superiority of our proposed scheme over those externality-unaware wireless schedulers.

Mobile crowdsensing (MCS) has become a promising solution to support the location-based content sharing applications. To meet users' demand on personalized content sharing, a general region of interest (RoI) distribution model that allows each user to have its specific RoI needs to be considered. In this context, how to deal with the asymmetry of cooperation caused by different RoI distribution is of significance for achieving the full benefits of personalized content sharing. Thus motivated, we propose an intelligent content sharing scheme based on cooperative crowdsensing, which ensures both efficiency and fairness. Specifically, users' decision-making of whether to participate in MCS is cast as a MCS participation game (MPG). The game captures the impact of different RoI distributions on the collective cooperation of MCS. By computing the Nash equilibrium of MPG with desirable properties, we develop a cooperation scheme that maximizes the overall system utility and is acceptable to all users. The system efficiency of the proposed scheme is further quantified by numerical simulations over various parameters.

Scalable Video Coding (SVC) streaming multicast is considered as a promising solution to cope with video traffic overload and multicast channel differences. To solve the challenge of delivering high‐definition SVC streaming over burst‐loss prone channels, we propose a social‐aware cooperative SVC streaming multicast scheme. The proposed scheme is the first attempt to enable D2D cooperation for SVC streaming multicast to conquer the burst‐loss, and one salient feature of it is that it takes fully into account the hierarchical encoding structure of SVC in scheduling cooperation. By using our scheme, users form groups to share video packets among each other to restore incomplete enhancement layers. Specifically, a cooperative group formation method is designed to stimulate effective cooperation, based on coalitional game theory; and an optimal D2D links scheduling scheme is devised to maximize the total decoded enhancement layers, based on potential game theory. Extensive simulations using real video traces corroborate that the proposed scheme leads to a significant gain on the received video quality.