Large language model (LLM) services increasingly rely on distributed inference across multiple GPU servers to sustain concurrent requests under limited compute, memory, and bandwidth resources. In such settings, a partitioned LLM can be represented as an inference chain (InFC), where the deployment decision determines both the sustainable concurrency ceiling (SCC) on the revenue side and the memory and communication overhead on the cost side. This paper studies the profit-aware inference chain deployment (InFCD) problem in heterogeneous data center networks. We show that increasing the InFC length does not monotonically improve profit: finer partitioning can relieve per-GPU resource bottlenecks and improve SCC, but may also increase deployment spread, inference path length, and internal traffic. To capture this tradeoff, we formulate profit-aware InFCD by jointly modeling static-weight vRAM occupation, per-user KV-cache occupation, user-side traffic, internal boundary traffic, and resource-coupled SCC, and prove its NP-hardness. We then propose the Maximum Sub-module Deployment Gain (MSDG) score and design an MSDG-based greedy algorithm. Theoretical analysis characterizes its online complexity and establishes a conditional positive-profit preservation property. Simulations show that MSDG improves total profit over SCC-oriented, cost-oriented, and local-profit-oriented baselines, characterize empirical optimality gaps and SLO sensitivity.

Existing ciphertext-policy attribute-based encryption (CP-ABE) schemes primarily determine who is authorized to decrypt, yet they do not guarantee privacy once ciphertexts are decrypted. Differential privacy (DP) protects released results through noise perturbation, but its privacy budget ε is usually configured independently of access attributes, which hinders fine-grained multi-level privacy protection in hierarchical IoT data sharing. To bridge this gap, a single-encryption multi-level output framework is proposed, where an attribute-driven noise key derivation function establishes a chained mapping among access attributes, noise keys, and noise intensity, enabling one ciphertext to yield differently perturbed outputs at distinct ε levels for users with varying privileges. Authenticated encryption with associated data (AEAD) is further incorporated to enforce strong cross-version and cross-policy binding, preventing low-noise outputs from being forged or replayed across authorization levels. Theoretical analysis proves that the framework achieves IND-CPA confidentiality, ε-differential privacy and tamper-resistant noise binding, while experiments demonstrate superior privacy–utility trade-offs, multi-level adaptability, and tamper resistance, indicating that the framework is well suited for practical IoT data sharing scenarios.

The distribution of the labeled data can greatly affect the performance of a semi-supervised learning (SSL) model. Most existing SSL models select the labeled data randomly and equally allocate the labeling quota among the classes, leading to considerable unstableness and degeneration of performance. This study unsupervisedly constructs a leading forest that forms another metric space, based on which it is convenient to define the fuzzy membership function to characterize central and divergent samples and select both types with fuzzy Xor logic. The labeling quota can thus be allocated adaptively among different classes. The proposed determinate labeling strategy can generally improve the performance for most SSLs. Especially, when combined with the kernelized large margin component analysis, it produces a novel semi-supervised classification model. In addition, the multi-modal issue in SSL is effectively addressed by the multi-granular structure of leading forest that readily facilitates multiple local metrics learning. Extensive experimental results demonstrate that the proposed method achieved competitive efficiency and encouraging accuracy when compared with the state-of-the-art methods

Semantic communication is an emerging paradigm for digital twin (DT) synchronization in unmanned aerial vehicle (UAV)-assisted edge computing environments, where machine learning (ML) models are deployed on edge servers and UAVs as semantic encoders and decoders to perform real-time synchronization. However, with limited system resources, additional computation workloads are still brought to all participants for semantic information extraction and recovery. In this work, we propose an optimized tiny ML-based DT synchronization framework to minimize the synchronization latency in UAV-assisted edge computing environments, considering time-average constraints on virtual energy deficit queue stability. Due to the coexistence of tiny ML-based semantic communications, a semantic extraction factor is introduced to formulate the DT synchronization problem as a time-average time minimization problem. By leveraging the Lyapunov optimization framework, the multi-stage DT synchronization problem is transformed into several per-slot resource allocation problems. To solve the per-slot optimization problem efficiently, a deep reinforcement learning-based synchronization (DRLS) algorithm is proposed, where an actor-critic structure is adopted to generate synchronization actions with low time complexity. Finally, we conduct simulation experiments to evaluate the performance of the proposed DRLS scheme. Numerical results demonstrate that our DRLS algorithm can reduce 8.23% of DT synchronization delay and 15.31% of synchronization data dropping rates on average by comparing it with the UAV-edge collaborative synchronization scheme without semantic communications. Besides, the DRLS algorithm can achieve up to 57.14% synchronization energy reduction compared with representative synchronization policies.

Constructing information granules (IGs) has been of significant interest to the discipline of granular computing. The principle of justifiable granularity has been proposed to guide the design of IGs, opening an avenue of pursuits of building IGs carried out on a basis of well-defined and intuitively appealing principles. However, how to improve the efficiency and accuracy of the resulting constructs is an open issue. In this paper, we present a local-density-based optimal granulation model (LoDOG), exhibiting evident advantages: 1) it can detect arbitrarily-shaped IGs and 2) it finds the optimal granulation solutions with O(N) complexity, once the leading tree structure has been constructed. We describe IGs of arbitrary shapes using a small collection of landmark points positioned on the skeleton of the underlying manifold, which contribute to approximate reconstruction capabilities of the original dataset. A dissimilarity metric is developed to evaluate the quality of the obtained reconstruction. The interpretability of LoDOG IGs is discussed. Theoretical analysis and empirical evaluations are covered to demonstrate the effectiveness of LoDOG and the manifold description.