Zhicheng Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zhicheng Liu has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Chao Qiu
Tianjin University
10 shared publications - Xiaofei Wang
Tianjin University
10 shared publications - Yunfeng Zhao
Tianjin University
6 shared publications - Cheng Zhang
Tianjin University of Finance and Economics, Tianjin, China
3 shared publications Jinduo Song
Tianjin Key Laboratory of Advanced Networking, College of Intelligence and Computing, Tianjin University, Tianjin, China
2 shared publications- Meng Tian
College of Intelligence and Computing, Tianjin University, Tianjin, China
2 shared publications
Latest Publications
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (11) , 22155-22171
Communication-Budgeted Chunk-Aware Mixed Model Parallelism for Collaborative Inference
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (11) , 22155-22171
Communication-Budgeted Chunk-Aware Mixed Model Parallelism for Collaborative Inference
- 15 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 24 (12) , 12784-12801
Enabling Real-Time Video Detection With Adaptive and Distributed Scheduling in Mobile Edge Computing
Real-time video detection is essential for many mobile visual applications, which brings the heavy computational burden of deep neural networks. Mobile edge computing offers a promising solution by deploying computational resources near mobile devices. However, achieving efficient video detection on mobile devices requires addressing challenges such as different performance requirements, diverse computing and network conditions, and system dynamics. We propose a real-time video detection framework in mobile edge computing, where multiple video streams from mobile devices are processed while balancing key performance metrics with consideration of grouping. A joint optimization problem of task scheduling, model selection, and resource provisioning is formulated for the system, where decisions are made on two timescales. To this end, we propose a window controller to unify decision-making at the time-slot level. We design an online scheduling algorithm based on multi-agent deep reinforcement learning to enable adaptive and distributed scheduling, while a masking-enhanced attention mechanism enables efficient explicit information exchange between mobile devices. Experimental evaluations across different numbers of mobile devices demonstrate that, in terms of average reward, the proposed algorithm outperforms local processing by 14.600%, fixed offloading by 10.007%, and four learning-based scheduling baselines by an average of 2.267%.
- 15 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 24 (12) , 12784-12801
Enabling Real-Time Video Detection With Adaptive and Distributed Scheduling in Mobile Edge Computing
Real-time video detection is essential for many mobile visual applications, which brings the heavy computational burden of deep neural networks. Mobile edge computing offers a promising solution by deploying computational resources near mobile devices. However, achieving efficient video detection on mobile devices requires addressing challenges such as different performance requirements, diverse computing and network conditions, and system dynamics. We propose a real-time video detection framework in mobile edge computing, where multiple video streams from mobile devices are processed while balancing key performance metrics with consideration of grouping. A joint optimization problem of task scheduling, model selection, and resource provisioning is formulated for the system, where decisions are made on two timescales. To this end, we propose a window controller to unify decision-making at the time-slot level. We design an online scheduling algorithm based on multi-agent deep reinforcement learning to enable adaptive and distributed scheduling, while a masking-enhanced attention mechanism enables efficient explicit information exchange between mobile devices. Experimental evaluations across different numbers of mobile devices demonstrate that, in terms of average reward, the proposed algorithm outperforms local processing by 14.600%, fixed offloading by 10.007%, and four learning-based scheduling baselines by an average of 2.267%.
- 10 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cloud Computing
- Vol. 13 (3) , 1011-1025
Accelerating AI-Generated Content Collaborative Inference Via Transfer Reinforcement Learning in Dynamic Edge Networks
While diffusion models have demonstrated remarkable success in computer vision tasks, their deployment in Internet of Things environments remains challenging. Edge devices face significant constraints in computational resources and must adapt to dynamic operating conditions. To address these limitations, we propose a novel system that accelerates AIgenerated content (AIGC) collaborative inference in dynamic edge networks. The proposed system introduces a multi-exit vision transformer-based U-Net architecture that enables efficient processing through adaptive exit point selection during the diffusion process, optimizing the trade-off between inference accuracy and computational efficiency. To optimize device-level operations, we develop an innovative generative AI-assisted reinforcement learning framework that determines optimal exit selection and offloading strategies to maximize generation quality and inference speed. Furthermore, we design a fine-tuning approach with policy reuse mechanisms that facilitates rapid reinforcement learning algorithm deployment across diverse environments. Extensive experimental evaluations demonstrate that our system outperforms existing algorithms in terms of balancing inference latency and generation quality, while also exhibiting improved adaptability to environmental variations.
- 10 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cloud Computing
- Vol. 13 (3) , 1011-1025
Accelerating AI-Generated Content Collaborative Inference Via Transfer Reinforcement Learning in Dynamic Edge Networks
While diffusion models have demonstrated remarkable success in computer vision tasks, their deployment in Internet of Things environments remains challenging. Edge devices face significant constraints in computational resources and must adapt to dynamic operating conditions. To address these limitations, we propose a novel system that accelerates AIgenerated content (AIGC) collaborative inference in dynamic edge networks. The proposed system introduces a multi-exit vision transformer-based U-Net architecture that enables efficient processing through adaptive exit point selection during the diffusion process, optimizing the trade-off between inference accuracy and computational efficiency. To optimize device-level operations, we develop an innovative generative AI-assisted reinforcement learning framework that determines optimal exit selection and offloading strategies to maximize generation quality and inference speed. Furthermore, we design a fine-tuning approach with policy reuse mechanisms that facilitates rapid reinforcement learning algorithm deployment across diverse environments. Extensive experimental evaluations demonstrate that our system outperforms existing algorithms in terms of balancing inference latency and generation quality, while also exhibiting improved adaptability to environmental variations.
- 11 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Services Computing
- Vol. 18 (1) , 270-287
Multi-Granularity Weighted Federated Learning for Heterogeneous Edge Computing
Federated learning (FL), an advanced variant of distributed machine learning, enables clients to collaboratively train a model without sharing raw data, thereby enhancing privacy, security, and reducing communication overhead. However, in edge computing scenarios, there is an increasing trend towards diversity, heterogeneity, and complexity in clients' data and models. The fundamental challenges, such as non-independent and identically distributed (non-IID) data and multi-granularity data accompanied by model heterogeneity, have become more evident and pose challenges to collaborative training among clients. In this paper, we refine the FL framework and propose the Multi-granularity Weighted Federated Learning (MGW-FL), emphasizing efficient collaborative training among clients with varied data granularities and diverse model scales across distinct data distributions. We introduce a distance-based FL mechanism designed for homogeneous clients, providing personalized models to mitigate the negative effects that non-IID data might have on model aggregation. Simultaneously, we propose an attention-weighted FL mechanism enhanced by a prior attention mechanism, facilitating knowledge transfer across clients with heterogeneous data granularities and model scales. Furthermore, we provide theoretical analyses of the convergence properties of the proposed MGW-FL method for both convex and non-convex models. Experimental results on five benchmark datasets demonstrate that, compared to baseline methods, MGW-FL significantly improves accuracy by almost 150% and convergence efficiency by nearly 20% on both IID and non-IID data.
- 11 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Services Computing
- Vol. 18 (1) , 270-287
Multi-Granularity Weighted Federated Learning for Heterogeneous Edge Computing
Federated learning (FL), an advanced variant of distributed machine learning, enables clients to collaboratively train a model without sharing raw data, thereby enhancing privacy, security, and reducing communication overhead. However, in edge computing scenarios, there is an increasing trend towards diversity, heterogeneity, and complexity in clients' data and models. The fundamental challenges, such as non-independent and identically distributed (non-IID) data and multi-granularity data accompanied by model heterogeneity, have become more evident and pose challenges to collaborative training among clients. In this paper, we refine the FL framework and propose the Multi-granularity Weighted Federated Learning (MGW-FL), emphasizing efficient collaborative training among clients with varied data granularities and diverse model scales across distinct data distributions. We introduce a distance-based FL mechanism designed for homogeneous clients, providing personalized models to mitigate the negative effects that non-IID data might have on model aggregation. Simultaneously, we propose an attention-weighted FL mechanism enhanced by a prior attention mechanism, facilitating knowledge transfer across clients with heterogeneous data granularities and model scales. Furthermore, we provide theoretical analyses of the convergence properties of the proposed MGW-FL method for both convex and non-convex models. Experimental results on five benchmark datasets demonstrate that, compared to baseline methods, MGW-FL significantly improves accuracy by almost 150% and convergence efficiency by nearly 20% on both IID and non-IID data.
- 15 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 23 (10) , 9437-9450
MoEI: Mobility-Aware Edge Inference Based on Model Partition and Service Migration
Deep neural networks are the cornerstone of many mobile intelligent systems, and their inference processes bring about computation-intensive tasks. Device-edge cooperative inference in mobile edge computing provides a fine-grained processing method to migrate the burden of inference computation. However, the geographical dispersion of resources and the mobility pattern of devices pose scheduling issues to be considered. In this paper, we propose a task scheduling framework for such device-edge systems to improve the pipeline time of model inference. First, we consider the resource provisioning strategy with a pre-fetching service migration setting in the environment of multiple mobile devices and edge nodes. Then, we leverage game theory to analyze the property of the decision-making process and propose an offline algorithm under complete information. Next, we propose an algorithm based on proximal policy optimization to enable mobile devices to make decisions in a distributed online manner. Further, we adopt a memory mechanism into the online algorithm to improve the decision-makers' understanding of the system environment. Experiments demonstrate the effectiveness of the two algorithms. The average pipeline time of the proposed online algorithm is only 61.44% of that of local processing, which is 1.196 times that of the proposed offline algorithm.
- 15 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 23 (10) , 9437-9450
MoEI: Mobility-Aware Edge Inference Based on Model Partition and Service Migration
Deep neural networks are the cornerstone of many mobile intelligent systems, and their inference processes bring about computation-intensive tasks. Device-edge cooperative inference in mobile edge computing provides a fine-grained processing method to migrate the burden of inference computation. However, the geographical dispersion of resources and the mobility pattern of devices pose scheduling issues to be considered. In this paper, we propose a task scheduling framework for such device-edge systems to improve the pipeline time of model inference. First, we consider the resource provisioning strategy with a pre-fetching service migration setting in the environment of multiple mobile devices and edge nodes. Then, we leverage game theory to analyze the property of the decision-making process and propose an offline algorithm under complete information. Next, we propose an algorithm based on proximal policy optimization to enable mobile devices to make decisions in a distributed online manner. Further, we adopt a memory mechanism into the online algorithm to improve the decision-makers' understanding of the system environment. Experiments demonstrate the effectiveness of the two algorithms. The average pipeline time of the proposed online algorithm is only 61.44% of that of local processing, which is 1.196 times that of the proposed offline algorithm.
- 20 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 11 (3) , 2610-2620
ENASFL: A Federated Neural Architecture Search Scheme for Heterogeneous Deep Models in Distributed Edge Computing Systems
With the development of edge computing, deep neural networks (DNNs) are deployed in heterogeneous edge devices, which have considerable differences in equipment attributes. This makes it necessary to design and train model structures to ensure each deployment's accuracy, even when dealing with the same image recognition task. Such a huge project will consume a lot of human and computing resources. To automate the design, Neural Architecture Search (NAS) is proposed to explore the possibly efficient structure. To maintain parameters in situ, Federated Learning (FL) can train models cooperatively without disclosing the original data. However, combining NAS and FL is still in its infancy. This paper proposes an Edge-empowered Neural Architecture Search Scheme with Federated Learning (ENASFL), which can serve edge devices with different lightweight models. For the reusability of blocks in different models, our work searches for a multi-exit model, then selects the appropriate branch for each edge device. Further, we design a novel aggregation strategy for the cooperative training of these branches, which enables devices to work cooperatively and improve training efficiency. Experimental evaluations based on three real datasets demonstrate that the accuracy is improved by 3% on average when the model has compressed to $4\times$ the baseline network.
- 20 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 11 (3) , 2610-2620
ENASFL: A Federated Neural Architecture Search Scheme for Heterogeneous Deep Models in Distributed Edge Computing Systems
With the development of edge computing, deep neural networks (DNNs) are deployed in heterogeneous edge devices, which have considerable differences in equipment attributes. This makes it necessary to design and train model structures to ensure each deployment's accuracy, even when dealing with the same image recognition task. Such a huge project will consume a lot of human and computing resources. To automate the design, Neural Architecture Search (NAS) is proposed to explore the possibly efficient structure. To maintain parameters in situ, Federated Learning (FL) can train models cooperatively without disclosing the original data. However, combining NAS and FL is still in its infancy. This paper proposes an Edge-empowered Neural Architecture Search Scheme with Federated Learning (ENASFL), which can serve edge devices with different lightweight models. For the reusability of blocks in different models, our work searches for a multi-exit model, then selects the appropriate branch for each edge device. Further, we design a novel aggregation strategy for the cooperative training of these branches, which enables devices to work cooperatively and improve training efficiency. Experimental evaluations based on three real datasets demonstrate that the accuracy is improved by 3% on average when the model has compressed to $4\times$ the baseline network.
- 1 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 23 (1) , 535-548
Hastening Stream Offloading of Inference via Multi-Exit DNNs in Mobile Edge Computing
As the primary driver of intelligent mobile applications, deep neural networks (DNNs) have gradually deployed to millions of mobile devices, producing massive latency-sensitive and computation-intensive tasks daily. Mobile edge computing facilitates the deployment of computing resources at the edge, which enables fine-grained offloading of DNN inference tasks from mobile devices to edge nodes. However, most existing studies have not systematically considered three crucial performance aspects: scheduling multiple streams of DNN inference tasks, leveraging multi-exit models to hasten task processing, and partitioning inference models for partial offloading. To this end, this paper proposes an adaptive inference framework in mobile edge computing, which can dynamically select the exit point and partition point for multiple inference task streams. We design a dynamic programming algorithm to obtain an efficient solution under the ideal condition that task arrival information is known. Further, we design a learning-based algorithm for online scheduling, whose training efficiency is improved based on historical experience initialization and priority experience replay. Experimental results show that compared with the Greedy algorithm, the online algorithm improves the performance on two environmental parameters by an average of 5.9% and 32%, respectively.
- 1 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 23 (1) , 535-548
Hastening Stream Offloading of Inference via Multi-Exit DNNs in Mobile Edge Computing
As the primary driver of intelligent mobile applications, deep neural networks (DNNs) have gradually deployed to millions of mobile devices, producing massive latency-sensitive and computation-intensive tasks daily. Mobile edge computing facilitates the deployment of computing resources at the edge, which enables fine-grained offloading of DNN inference tasks from mobile devices to edge nodes. However, most existing studies have not systematically considered three crucial performance aspects: scheduling multiple streams of DNN inference tasks, leveraging multi-exit models to hasten task processing, and partitioning inference models for partial offloading. To this end, this paper proposes an adaptive inference framework in mobile edge computing, which can dynamically select the exit point and partition point for multiple inference task streams. We design a dynamic programming algorithm to obtain an efficient solution under the ideal condition that task arrival information is known. Further, we design a learning-based algorithm for online scheduling, whose training efficiency is improved based on historical experience initialization and priority experience replay. Experimental results show that compared with the Greedy algorithm, the online algorithm improves the performance on two environmental parameters by an average of 5.9% and 32%, respectively.
- Top Cited Papers
- 13 October 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Selected Areas in Communications
- Vol. 40 (12) , 3325-3342
InFEDge: A Blockchain-Based Incentive Mechanism in Hierarchical Federated Learning for End-Edge-Cloud Communications
Advances in communications and networking technologies are driving the computing paradigm toward the end-edge-cloud collaborative architecture to leverage ubiquitous data and resources. Opposite to centralized intelligence, Hierarchical Federated Learning (HFL) relieves overwhelmed communication overhead and enjoys the advantages of high bandwidth as well as abundant computing resources while retaining privacy-preserving benefits of Federated Learning (FL). It is difficult to balance system overhead and model performance in the HFL framework, while it could be solved by introducing an incentive mechanism. Although the incentive mechanism can alleviate the above anxiety by compensating relevant participants, some limitations ( multi-dimensional properties, incomplete information and unreliable participants ) will significantly degrade the performance and efficiency of the designed mechanism. To address the challenges caused by the above limitations, we propose InFEDge, a blockchain-based incentive mechanism in the HFL. The InFEDge considers 1) multi-dimensional individual properties to model system participants and proves the uniqueness of Nash equilibrium with the closed-form solution. Meanwhile, 2) we transform the problem under incomplete information into a contract game where we obtain the optimal solution. Moreover, 3) we also leverage the blockchain to provide economic incentives, prevent unreliable participants ’ disturbance and further ensure data privacy by implementing the mechanism in the smart contract to offer a credible, faster, and transparent resource trading system. Experimental evaluations on a proof-of-concept testbed along with real traces demonstrate the superiority of our mechanism. Further, our method solves a real-world user allocation problem for future communications and networking.
- 13 October 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Selected Areas in Communications
- Vol. 40 (12) , 3325-3342
Top Cited PapersInFEDge: A Blockchain-Based Incentive Mechanism in Hierarchical Federated Learning for End-Edge-Cloud Communications
Advances in communications and networking technologies are driving the computing paradigm toward the end-edge-cloud collaborative architecture to leverage ubiquitous data and resources. Opposite to centralized intelligence, Hierarchical Federated Learning (HFL) relieves overwhelmed communication overhead and enjoys the advantages of high bandwidth as well as abundant computing resources while retaining privacy-preserving benefits of Federated Learning (FL). It is difficult to balance system overhead and model performance in the HFL framework, while it could be solved by introducing an incentive mechanism. Although the incentive mechanism can alleviate the above anxiety by compensating relevant participants, some limitations ( multi-dimensional properties, incomplete information and unreliable participants ) will significantly degrade the performance and efficiency of the designed mechanism. To address the challenges caused by the above limitations, we propose InFEDge, a blockchain-based incentive mechanism in the HFL. The InFEDge considers 1) multi-dimensional individual properties to model system participants and proves the uniqueness of Nash equilibrium with the closed-form solution. Meanwhile, 2) we transform the problem under incomplete information into a contract game where we obtain the optimal solution. Moreover, 3) we also leverage the blockchain to provide economic incentives, prevent unreliable participants ’ disturbance and further ensure data privacy by implementing the mechanism in the smart contract to offer a credible, faster, and transparent resource trading system. Experimental evaluations on a proof-of-concept testbed along with real traces demonstrate the superiority of our mechanism. Further, our method solves a real-world user allocation problem for future communications and networking.
- 21 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 9 (5) , 3136-3151
Learn to Coordinate for Computation Offloading and Resource Allocation in Edge Computing: A Rational-Based Distributed Approach
In response to the growing demand for user experience on innovative applications, computation offloading can migrate computation-intensive tasks from users to the network edge, which is closely coupled with resource allocation. For the rational motivations behind these issues, centralized decision-making may seriously compromise individuals’ rationality, and the complexity of this problem is gradually beyond the comfort zone of traditional methods. Therefore, realizing decentralized and intelligent resource management becomes an emerging technical issue in edge computing, which has not been much explored. This paper proposes a learning-based distributed resource coordination framework, L6C, which enables each decision-maker to pursue its benefit in a socializing and rational manner. We first formulate a two-timescale problem of computation offloading and resource allocation, then exploit game theory to discuss the rational properties of users and edges. Specifically, each user wants to minimize the execution cost of its task, and edges try to maximize the experience of task execution cooperatively. Further, we design two explicit information interaction mechanisms based on multi-agent deep reinforcement learning, where interactive contents can be generated dynamically along with resource decisions. Experimental results on a real-world dataset show that L6C achieves the superior performance of edges and users compared with various baselines.
- 21 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 9 (5) , 3136-3151
Learn to Coordinate for Computation Offloading and Resource Allocation in Edge Computing: A Rational-Based Distributed Approach
In response to the growing demand for user experience on innovative applications, computation offloading can migrate computation-intensive tasks from users to the network edge, which is closely coupled with resource allocation. For the rational motivations behind these issues, centralized decision-making may seriously compromise individuals’ rationality, and the complexity of this problem is gradually beyond the comfort zone of traditional methods. Therefore, realizing decentralized and intelligent resource management becomes an emerging technical issue in edge computing, which has not been much explored. This paper proposes a learning-based distributed resource coordination framework, L6C, which enables each decision-maker to pursue its benefit in a socializing and rational manner. We first formulate a two-timescale problem of computation offloading and resource allocation, then exploit game theory to discuss the rational properties of users and edges. Specifically, each user wants to minimize the execution cost of its task, and edges try to maximize the experience of task execution cooperatively. Further, we design two explicit information interaction mechanisms based on multi-agent deep reinforcement learning, where interactive contents can be generated dynamically along with resource decisions. Experimental results on a real-world dataset show that L6C achieves the superior performance of edges and users compared with various baselines.
- 1 October 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications
- Vol. 28 (5) , 200-208
Socialized Learning for Smart Cities: Cognitive Paradigm, Methodology, and Solution
Along with the unprecedented boom of 5G, the Internet of Things (IoT), and artificial intelligence, smart cities are making a great clamor. When billions of IoT devices are streaming in the smart city, realizing low-latency and high-bandwidth services has a significant impact on the benefits of smart cities. Thus, managing resources efficiently and intelligently to meet various service requirements has become a challenge for smart cities. With the rapid development of machine intelligence, it can be considered that many machines constitute a machine society just like that of human beings. Inspired by the efficient and collaborative operation mechanism of human society, we propose a socialized learning scheme to address various needs in smart cities (e.g., reasonable resource allocation). Specifically, we present the socialized learning scheme from three perspectives. First, we design a cognitive paradigm of socialized learning to enlighten the long-term vision of applying learning-based resource management to smart cities, with comprehensive discussions of three dimensions consisting of architecture, decision, and knowledge. Second, we also probe the socialized learning methodology including socialized training and socialized inference. It highlights social relationships and introduces a series of technologies to realize social relations within and across layers. Finally, we give a socialized learning solution for solving the practical resource allocation problem in smart cities, thereby jointly improving decision accuracy and reducing training costs. Illustrative simulations are provided to show the effectiveness of the proposed scheme.
- 1 October 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications
- Vol. 28 (5) , 200-208
Socialized Learning for Smart Cities: Cognitive Paradigm, Methodology, and Solution
Along with the unprecedented boom of 5G, the Internet of Things (IoT), and artificial intelligence, smart cities are making a great clamor. When billions of IoT devices are streaming in the smart city, realizing low-latency and high-bandwidth services has a significant impact on the benefits of smart cities. Thus, managing resources efficiently and intelligently to meet various service requirements has become a challenge for smart cities. With the rapid development of machine intelligence, it can be considered that many machines constitute a machine society just like that of human beings. Inspired by the efficient and collaborative operation mechanism of human society, we propose a socialized learning scheme to address various needs in smart cities (e.g., reasonable resource allocation). Specifically, we present the socialized learning scheme from three perspectives. First, we design a cognitive paradigm of socialized learning to enlighten the long-term vision of applying learning-based resource management to smart cities, with comprehensive discussions of three dimensions consisting of architecture, decision, and knowledge. Second, we also probe the socialized learning methodology including socialized training and socialized inference. It highlights social relationships and introduces a series of technologies to realize social relations within and across layers. Finally, we give a socialized learning solution for solving the practical resource allocation problem in smart cities, thereby jointly improving decision accuracy and reducing training costs. Illustrative simulations are provided to show the effectiveness of the proposed scheme.