Temporal Knowledge Graph (TKG) reasoning remains challenging to characterize with conventional flat representations due to its intrinsic heterogeneous structure.Existing multigeometry approaches face two key bottlenecks: 1) the Riemannian depth barrier driven by numerical instability, which restricts models to shallow architectures; and 2) gate collapse, where adaptive fusion mechanisms suffer from gradient starvation and degenerate into singlegeometry solutions.To this end, we propose MAGIC (Multi-geometry Annealing Graph Interaction with Consensus).Our framework introduces a Tangent-Residual Engine in multigeometric spaces, which enables the first stable 8-layer geometric evolution and reveals a phenomenon termed Geometric Annealing, where manifold curvature spontaneously evolves from semantic flatness in shallow layers to structural complexity in deeper layers.We further design an explicit reasoning module with structural consensus, leveraging geometric invariants and structural priors to regulate gradient flow, prevent collapse, and ensure robust synergy across Hyperbolic, Spherical, and Euclidean spaces.Experiments show that MAGIC achieves stateof-the-art performance in TKG reasoning, improving MRR by up to 2.9 points.

Resilient operation of a wireless networked multirobot system (MRS) in a smart factory relies on the effective detection of physical anomalies from robots and cyber anomalies from wireless transmission errors or imprecise artificial intelligence decisions, which leads to a new technological frontier in data-driven industrial informatics: cyber-physical anomaly detection (AD). Furthermore, data patterns in a single smart factory are unlikely enough to train high-quality learning models for this new cyber-physical AD, which suggests the necessity to utilize operating data from multiple smart factories while keeping the privacy of each factory's data. To overcome the aforementioned technical challenges for cyber-physical AD in smart factories, this article proposes an integral mechanism of generative adversarial networks, federated learning, and fuzzy clustering acceleration. Generative adversarial networks facilitate data imputation to regenerate complete datasets alleviating anomalies caused by wireless communications. Federated learning enables rich privacy-preserving datasets to be jointly used among multiple collaborative factories. Furthermore, fuzzy clustering acceleration is embedded to speed up the factory selection algorithm such that efficient training and real-time physical AD in the large-scale operation of multiple smart factories can be achieved. Extensive computational experiments based on the KDD-99 dataset demonstrate the effective and efficient cyber-physical AD of wireless networked MRS in collaborative multiple smart factories.

In this paper, a novel joint energy and age of information (AoI) optimization framework for IoT devices in a non-stationary environment is presented. In particular, IoT devices that are distributed in the real-world are required to efficiently utilize their computing resources so as to balance the freshness of their data and their energy consumption. To optimize the performance of IoT devices in such a dynamic setting, a novel lifelong reinforcement learning (RL) solution that enables IoT devices to continuously adapt their policies to each newly encountered environment is proposed. Given that IoT devices have limited energy and computing resources, an unmanned aerial vehicle (UAV) is leveraged to visit the IoT devices and update the policy of each device sequentially. As such, the UAV is exploited as a mobile learning agent that can learn a shared knowledge base with a feature base in its training phase, and feature sets of a zero-shot learning method in its testing phase, to generalize between the environments. To optimize the trajectory and flying velocity of the UAV, an actor-critic network is leveraged so as to minimize the UAV energy consumption. Simulation results show that the proposed lifelong RL solution can outperform the state-of-art benchmarks by enhancing the balanced cost of IoT devices by 8.3% when incorporating warm-start policies for unseen environments. In addition, our solution achieves up to 49.38% reduction in terms of energy consumption by the UAV in comparison to the random flying strategy.

Proactive Mobile Network (PMN) has been proposed to support extremely low latency communications with multi-tier computing architectures, machine-centricity, and data-driven operation features. Nevertheless, the communication reliability of the PMN introduces new substantial technological challenges. As PMN employs unique proactive open-loop communication, any feedback-based control is avoided to enhance end-to-end latency. This paper focuses on machine-initiated uplink transmission in PMN and proposes a reliability-guaranteed resource management scheme. Without requiring feedback control information, our scheme uniquely decomposes conventional resource management into two collaborative decision processes: predictive resource allocation suggested by network anchor nodes (ANs) and proactive smart resource utilization by smart equipment (SE). These two decision-making processes are constructed as independent reinforcement learning (RL) problems, but implicitly share the states of radio resources according to operating environments. Different algorithms for different operating scenarios have been investigated for this dual-decision solution. Simulation results in various scenarios show that our scheme enables PMN’s reliability close to the theoretical optimal value and successfully serves radio resource utilization in the PMNs.

To achieve the minimal latency, proactive wireless communication has been proposed to facilitate proactive mobile networks. Due to lacking closed-loop control, random selection of radio resource units (RRUs) serves the only way to the critical radio resource allocation (RRA), which inevitably suffers collisions of simultaneous utilizing the same RRUs to result in loss of packets, particularly in the uplink. Macroscopic view on the uplink and downlink network operation cycle insightfully suggests that it is still possible to construct a delayed version of semi-closed-loop operation to predictively utilize radio resource in the uplink of proactive mobile network. A two-stage reinforcement learning mechanism to enable the recommendation of radio resource utilization from network infrastructure to mobile smart machines is proposed, which consists of the multi-armed bandit scheme for RRA and the neural network to learn historical utilization of RRUs. Simulations verify machine learning enables smart and predictive RRA with superior performance that can lead to the minimal latency of mobile networking.

Artificial intelligence (AI) and big data analytics enable autonomous vehicles (AVs) to dramatically change future intelligent transportation in smart cities. AVs are envisaged to evolve to a service rather than a product in the future. To provide best user experience of such services, three primary factors, namely, waiting time, travel time, and supply of AV services, are taken into consideration in a multiobjective optimization. Conventional optimization of services relies on traffic flow analysis over a queuing network model. However, due to the mobility of vehicles and the transfer uncertainty of road networks, the queuing network analysis is too complicated and practically intractable. For accuracy and convenient processing, network calculus (NC) is extended to model the queueing problem in this paper. The optimal number of available AVs can be identified by guaranteeing the waiting time of customers. The satisfaction of AV services can be viewed as a supply and demand problem, and optimized by bipartite graph matching. In order to reduce the average travel time, especially for rush hours with heavy traffic, we further propose a new online AVs fleet management scheme with congestion control for smart cities. It is shown that the intelligent management of AV fleet can be efficiently achieved, outperforming the cases of traditional vehicles. NC-assisted AI enables an efficient intelligent transportation paradigm in smart cities, while achieving substantial energy saving.

Identifying the hub nodes (the most influential users) in an information diffusion network is a central research topic in social influence analysis. In [2], we developed the Multi-task Sparse Linear Influence Model (MSLIM) to automatically select topic-sensitive influential nodes in an implicit network. Our method firstly needs to determine the active node set to model the global volume of the contagions of the entire network nodes. The active node set is chosen by a simple rule in [2]. However, different set leads to different model performance. Reference [4] proposed a new framework called Slow Intelligence System, which can continuously learn, search the appropriate method and propagate information according to the environment to improve the performance over time. In this paper, we develop a slow intelligence based active user definition system by utilizing user profile visualization to help interactively determine active node sets in MSLIM model. We apply our system on a set of 2.6 million tweets of 1000 users on twitter. We show that our system can efficiently utilize user's profile visualization techniques to facilitate determining the appropriate active node sets.

How to identify influential nodes is a central research topic in information diffusion analysis. Many existing methods rely on the assumption that the network structure is completely known by the model. However, in many applications, such a network is either unavailable or insufficient to explain the underlying information diffusion phenomena. To address this challenge, we develop a multi-task sparse linear influence model (MSLIM), which can simultaneously predict the volume for each contagion and automatically identify sets of the most influential nodes for different contagions. Our method is based on the linear influence model with two main advantages: 1) it does not require the network structure; 2) it can detect different sets of the most influential nodes for different contagions. To solve the corresponding convex optimization problem for learning the model, we adopt the accelerated gradient method (AGM) framework and show that there is an exact closed-form solution for the proximal mapping. Therefore, the optimization procedure achieves the optimal first-order convergence rate and can be scaled to very large datasets. The proposed model is validated on a set of 2.6 millions tweets from 1000 users of Twitter. We show that MSLIM can efficiently select the most influential users for specific contagions. We also present several interesting patterns of the selected influential users.

An important research area in computer vision is developing algorithms that can reconstruct the 3D surface of an object represented by a single 2D line drawing. Previous work on 3D reconstruction from single 2D line drawings focuses on objects with planar faces. In this paper, we propose a novel approach to the reconstruction of solid objects that have not only planar but also curved faces. Our approach consists of four steps: (1) identifying the curved faces and planar faces in a line drawing, (2) transforming the line drawing into one with straight edges only, (3) reconstructing the 3D wireframe of the curved object from the transformed line drawing and the original line drawing, and (4) generating the curved faces with Bezier patches and triangular meshes. With a number of experimental results, we demonstrate the ability of our approach to perform curved object reconstruction successfully.