LORM: Learning to Optimize for Resource Management in Wireless Networks With Few Training Samples
Open accessThe DOI matches its Crossref record; 39 of the 39 references it cites were found in a registry or an index.
Abstract
Effective resource management plays a pivotal role in wireless networks, which, unfortunately, typically results in challenging mixed-integer nonlinear programming (MINLP) problems. Machine learning-based methods have recently emerged as a disruptive way to obtain near-optimal performance for MINLPs with affordable computational complexity. There have been some attempts in applying such methods to resource management in wireless networks, but these attempts require huge amounts of training samples and lack the capability to handle constrained problems. Furthermore, they suffer from severe performance deterioration when the network parameters change, which commonly happens and is referred to as thetask mismatchproblem. In this paper, to reduce the sample complexity and address the feasibility issue, we propose a framework of Learning to Optimize for Resource Management (LORM). In contrast to the end-to-end learning approach adopted in previous studies, LORM learns the optimal pruning policy in the branch-and-bound algorithm for MINLPs via a sample-efficient method, namely,imitation learning. To further address the task mismatch problem, we develop a transfer learning method via self-imitation in LORM, namedLORM-TL, which can quickly adapt a pre-trained machine learning model to the new task with only a few additionalunlabeledtraining samples. Numerical simulations demonstrate that LORM outperforms specialized state-of-the-art algorithms and achieves near-optimal performance, w…
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“This learning based brand-and-bound method can significantly save the time for pruning the nodes in the search tree, achieve near-optimal performance with few training samples, as well as guarantee feasibility of constraints without performance degradation.”
From Edge artificial intelligence for 6g: vision, enabling technologies, and applications (2022) · cites this paper as [22]
In the citing paper
“To solve the large-scale mixed combinatorial optimization problem efficiently, imitation learning was adopted in [22] to learn an aggressive pruning policy in the globally optimal-achieving branch-and-bound algorithm.”
From Edge artificial intelligence for 6g: vision, enabling technologies, and applications (2022) · cites this paper as [22]
In the citing paper
“However, due to the distribution shift for system parameters in episodically dynamic environment, the trained model may suffer from performance deterioration when the dataset follows a different distribution in the inference stage [22].”
From Edge artificial intelligence for 6g: vision, enabling technologies, and applications (2022) · cites this paper as [22]
Citations
Cites
Pan, S. J., & Yang, Q. (2010) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2009.191 · Cited by 23,387 · cited 1×
“An essential assumption of most machine learning algorithms is that the training and future testing data are in the same feature space with the same distribution, i.e., the same task [33].”
BackgroundMastering the game of Go with deep neural networks and tree search
Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., van den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., et al. (2016) · Nature · doi:10.1038/nature16961 · Cited by 15,612 · cited 1×
“Modeling the tree search process as a sequential decision problem is a common method in machine learning [30].”
Method(2002) · Electronics - A First Course · doi:10.4324/9780080574714-46 · Cited by 3,877
Multiuser OFDM with adaptive subcarrier, bit, and power allocation
Wong, C. Y., Cheng, R. S., Lataief, K. B., & Murch, R. D. (1999) · IEEE Journal on Selected Areas in Communications · doi:10.1109/49.793310 · Cited by 2,657 · cited 4×
“Typical examples include subcarrier management in OFDMA [4], user association [5], network power minimization in Cloud-RANs [6], and joint task offloading scheduling and transmit power management [7].”
BackgroundInfluentialSelf-citationShi, Q., Razaviyayn, M., Luo, Z.-Q., & He, C. (2011) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2011.2147784 · Cited by 2,129 · cited 4×
“For instance, different algorithms have been developed for power control (e.g., water filling [17]), transmit beamforming design (e.g., WMMSE [18] and conic optimization-based algorithms [19]), user association (e.g., the primal dual optimization-based algorithm [5]), and dynamic offloading (e.g., the Lyapunov optimizat…”
MethodInfluentialVinyals, O., Fortunato, M., & Jaitly, N. (2015) · neural information processing systems · Cited by 2,043
A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning
Ross, S., Gordon, G. J., & Bagnell, J. A. (2018) · Carnegie Mellon University · doi:10.1184/r1/6550949 · Cited by 1,941
Dynamic computation offloading for mobile-edge computing with energy harvesting devices
Mao, Y., Zhang, J., & Letaief, K. B. (2016) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2016.2611964 · Cited by 1,705 · cited 2×
“Typical examples include subcarrier management in OFDMA [4], user association [5], network power minimization in Cloud-RANs [6], and joint task offloading scheduling and transmit power management [7].”
BackgroundSelf-citationAn Introduction to Deep Reinforcement Learning
Vincent, F.-L., Peter, H., Riashat, I., Marc, G. B., & Joelle, P. (2018) · Foundations and Trends® in Machine Learning · doi:10.1561/2200000071 · Cited by 1,286 · cited 1×
“…found, N opt ← the node containing optimal visited nodes and features into D Save solutions of solved convex problems into T 3: if c ∗ c ∗ old then 4: N opt ← the nodes from root to N opt 5: else 6: if node ( D j ) ∈ N opt then 10: end if 14: end for 15: return c ∗ , N opt , D , T policy [34].”
BackgroundUser Association for Load Balancing in Heterogeneous Cellular Networks
Ye, Q., Rong, B., Chen, Y., Al-Shalash, M., Caramanis, C., & Andrews, J. G. (2013) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2013.040413.120676 · Cited by 1,228 · cited 3×
“, the primal dual optimization-based algorithm [5]), and dynamic offloading (e.”
Background
Research works printed but not linked: 3
- proakis, 2001, Digital Communications, 4
- goodfellow, 2016, Deep Learning
- song, 2017, Learning to search via self-imitation with application to risk-aware planning, Proc Adv Neural Inf Process Syst Workshop
Cited by
Edge artificial intelligence for 6g: vision, enabling technologies, and applications
Letaief, K. B., Shi, Y., Lu, J., & Lu, J. (2022) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2021.3126076 · Cited by 829
“However, due to the distribution shift for system parameters in episodically dynamic environment, the trained model may suffer from performance deterioration when the dataset follows a different distribution in the inference stage [22].”
BackgroundMethodInfluentialSelf-citationNear-Field Communications: A Tutorial Review
Liu, Y., Wang, Z., Xu, J., Ouyang, C., Mu, X., & Schober, R. (2023) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2023.3305583 · Cited by 575
“Furthermore, some low-complexity algorithms, such alternating direction method of multipliers (ADMM) [72] and machine-learning-based methods [73], can be employed to obtain a high-quality sub-optimal solution.”
MethodShen, Y., Shi, Y., Zhang, J., & Letaief, K. B. (2021) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2020.3036965 · Cited by 367
“Most of existing works on “learning to optimize” approaches to solve problems in wireless networks adopted MLPs as the neural network architecture [7], [9], [11].”
BackgroundMethodInfluentialSelf-citationZhou, X., Liang, W., Shimizu, S., Ma, J., & Jin, Q. (2021) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2020.3047675 · Cited by 347
“[19] presented a machine learning-based framework for resource management in wireless communications.”
BackgroundDeep-Learning-Based Wireless Resource Allocation With Application to Vehicular Networks
Liang, L., Ye, H., Yu, G., & Li, G. Y. (2020) · Proceedings of the IEEE · doi:10.1109/jproc.2019.2957798 · Cited by 282
“Alternatively, deep learning can be embedded as a component to accelerate some steps of a well-behaved optimization algorithm, such as the pruning stage of the branch-and-bound in [39], [40].”
BackgroundMethodInfluentialGraph Neural Networks for Wireless Communications: From Theory to Practice
Shen, Y., Zhang, J., Song, S. H., & Letaief, K. B. (2023) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2022.3219840 · Cited by 230
“Such advantage is a major motivation underlying the recent interests in “learning to optimize” approaches [2], [3], [8].”
BackgroundResultSelf-citationImitation Learning Enabled Task Scheduling for Online Vehicular Edge Computing
Wang, X., Ning, Z., Guo, S., & Wang, L. (2022) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2020.3012509 · Cited by 219
Machine Learning for Large-Scale Optimization in 6G Wireless Networks
Shi, Y., Lian, L., Shi, Y., Wang, Z., Zhou, Y., Fu, L., Bai, L., Zhang, J., & Zhang, W. (2023) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2023.3300664 · Cited by 205
“For example, for solving mixed combinatorial optimization problems, the complexity of branchand-bound (BB) algorithm grows exponentially with the scale of problem [15].”
BackgroundMethodInfluentialSelf-citationHybrid Beamforming for 5G and Beyond Millimeter-Wave Systems: A Holistic View
Zhang, J., Yu, X., & Letaief, K. B. (2020) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2019.2959595 · Cited by 188
Self-citationGraph Embedding-Based Wireless Link Scheduling With Few Training Samples
Lee, M., Yu, G., & Li, G. Y. (2021) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2020.3040983 · Cited by 180
“Meanwhile, another paradigm is to exploit the specific algorithm structures based on ML to simplify resource allocation, for example for cloud radio access networks (Cloud-RANs) [20] and D2D communications [21].”
BackgroundEfficient Automated Disease Diagnosis Using Machine Learning Models
Kumar, N., Narayan Das, N., Gupta, D., Gupta, K., & Bindra, J. (2021) · Journal of Healthcare Engineering · doi:10.1155/2021/9983652 · Cited by 164
“In wireless networking, resource management is another problem where ML was applied to obtain optimal performance [14].”
MethodA GNN-Based Supervised Learning Framework for Resource Allocation in Wireless IoT Networks
Chen, T., Zhang, X., You, M., Zheng, G., & Lambotharan, S. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3091551 · Cited by 175
“Shen et al. [11] proposed a framework named learning to optimize for resource management (LORM) to accelerate the optimal pruning policy in the B&B algorithm for the mixed-integer nonlinear programming problems, and verified it via a network power minimization problem in cloud radio access networks.”
BackgroundMethodTrustworthy Federated Learning via Blockchain
Yang, Z., Shi, Y., Zhou, Y., Wang, Z., & Yang, K. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3201117 · Cited by 122
“This long-term resource allocation problem cannot be equivalently transformed to multiple one-shot problems with respect to the channel of each round, due to the correlation in the long-term average power constraint [32].”
BackgroundSelf-citationNoman, H. M. F., Hanafi, E., Noordin, K. A., Dimyati, K., Hindia, M. N., Abdrabou, A., & Qamar, F. (2023) · IEEE Access · doi:10.1109/access.2023.3302250 · Cited by 153
“Furthermore, a classification of recent works is provided based on ML types such as SML [87], [88], [89], uSML [90], DL [91], RL [92], DRL [93], [94], [95], [96], [97], and FL [98], [99] to address resource allocation problems as depicted in Fig.”
MethodA Graph Neural Network Approach for Scalable Wireless Power Control
Shen, Y., Shi, Y., Zhang, J., & Letaief, K. B. (2019) · 2019 IEEE Globecom Workshops (GC Wkshps) · doi:10.1109/gcwkshps45667.2019.9024538 · Cited by 87
Self-citationApplications of Machine Learning in Networking: A Survey of Current Issues and Future Challenges
Ridwan, M. A., Radzi, N. A. M., Abdullah, F., & Jalil, Y. E. (2021) · IEEE Access · doi:10.1109/access.2021.3069210 · Cited by 88
“The works in [124], [125] have proven the effectiveness of using ANN algorithms to learn from the environment, perform classification for resource network management, and accurately allocate network resources to high-priority applications.”
BackgroundLearning to Branch: Accelerating Resource Allocation in Wireless Networks
Lee, M., Yu, G., & Li, G. Y. (2019) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2019.2953724 · Cited by 80
“In [21], the transfer learning method has been used to solve this problem.”
BackgroundMethodInfluentialWang, X., Ning, Z., Guo, S., Wen, M., & Poor, H. V. (2021) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2021.3053136 · Cited by 73
Decentralized Inference With Graph Neural Networks in Wireless Communication Systems
Lee, M., Yu, G., & Dai, H. (2021) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2021.3125793 · Cited by 66
“For example, the authors in [7], [8] havemade use of the imitation learning technique to replace the pruning strategy in the branch-and-bound algorithm, a widely-used algorithm for mixed-integer wireless resource allocation problems with exponential complexity in the worst case.”
BackgroundAdapting to Dynamic LEO-B5G Systems: Meta-Critic Learning Based Efficient Resource Scheduling
Yuan, Y., Lei, L., Vu, T. X., Chang, Z., Chatzinotas, S., & Sun, S. (2022) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2022.3178171 · Cited by 63
Gu, Y., She, C., Quan, Z., Qiu, C., & Xu, X. (2023) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2023.3253126 · Cited by 63
“Inspired by the recent advances in data-driven models, deep learning-based methods were proposed to solve the power allocation problems in wireless networks to combat the computation complexity [9], [10], [11], [12], [13].”
MethodLearning for Graph Matching and Related Combinatorial Optimization Problems
Yan, J., Yang, S., & Hancock, E. R. (2020) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2020/694 · Cited by 74
“For resource management, imitation learning is adopted in [Shen et al. , 2019] to learn the pruning policy in the optimal branch-and-bound al-gorithm.”
Accelerating Generalized Benders Decomposition for Wireless Resource Allocation
Lee, M., Ma, N., Yu, G., & Dai, H. (2020) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2020.3031920 · Cited by 55
“However, the accelerated B&B algorithm in [16], [17] suffers from loss of optimality.”
BackgroundMethodA Joint Energy and Latency Framework for Transfer Learning Over 5G Industrial Edge Networks
Yang, B. F., Fagbohungbe, O. I., Cao, X., Yuen, C., Qian, L., Niyato, D. T., & Zhang, Y. (2021) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2021.3075444 · Cited by 57
Wang, Y., Li, Y., Shi, Q., & Wu, Y. (2023) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2023.3325735 · Cited by 62
User Association for Millimeter-Wave Networks: A Machine Learning Approach
Liu, R., Lee, M., Yu, G., & Li, G. Y. (2020) · IEEE Transactions on Communications · doi:10.1109/tcomm.2020.2983036 · Cited by 54
“When encountering the more complicated mixed-integer nonlinear programming (MINLP) problems, one efficient approach is to utilize imitation learning to accelerate the most time-consuming branch process of the branch-and-bound algorithm [40], [41].”
MethodSun, H., Pu, W., Fu, X., Chang, T., & Hong, M. (2022) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2022.3143372 · Cited by 59
“Similar ideas have been applied in wireless settings recently [17, 52, 53] to deal with scenarios that network parameters changes.”
BackgroundMethodInfluentialSun, L., Wang, Y., Swindlehurst, A. L., & Tang, X. (2020) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2020.3036954 · Cited by 49
Algorithm Unrolling for Massive Access via Deep Neural Networks With Theoretical Guarantee
Shi, Y., Choi, H., Shi, Y., & Zhou, Y. (2021) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2021.3100500 · Cited by 48
“For instance, the authors in [22]–[26] proposed the idea of “learning to optimize”, where neural networks were developed to replace the traditional optimization algorithms to solve the non-convex constrained optimization problems [22]–[24] and mixed-integer nonlinear programming (MINLP) problems [25], [26] for resourc…”
BackgroundSelf-citationQureshi, H. N., Masood, U., Manalastas, M., Zaidi, S. M. A., Farooq, H., Forgeat, J., Bouton, M., Bothe, S., Karlsson, P., Rizwan, A., et al. (2023) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2023.3271419 · Cited by 55
“Authors in [139] use self-imitation via transfer learning to achieve few-shot learning for the resource management (network power minimization) problem in Cloud Radio Access Networks (C-RAN).”
BackgroundLee, W., Lee, K., Choi, H.-H., & Leung, V. C. M. (2021) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2021.3065029 · Cited by 41
“Moreover, advanced machine learning mechanisms, using a distributed framework [27] and imitation learning [28], were suggested for resource management.”
BackgroundGBLinks: GNN-Based Beam Selection and Link Activation for Ultra-Dense D2D mmWave Networks
He, S., Xiong, S., Zhang, W., Yang, Y., Ren, J., & Huang, Y. (2022) · IEEE Transactions on Communications · doi:10.1109/tcomm.2022.3158646 · Cited by 46
Li, J., Zhou, C., Liu, J., Sheng, M., Zhao, N., & Su, Y. (2023) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2023.3282909 · Cited by 38
“Moreover, the UAV communication network is fundamentally dynamic since both its users numbers and locations change over time [11].”
BackgroundGraph Neural Networks Approach for Joint Wireless Power Control and Spectrum Allocation
Marwani, M., & Kaddoum, G. (2024) · IEEE Transactions on Machine Learning in Communications and Networking · doi:10.1109/tmlcn.2024.3408723 · Cited by 46
Branch and Bound in Mixed Integer Linear Programming Problems: A Survey of Techniques and TrendsPreprint
Huang, L., Chen, X., Huo, W., Wang, J., Zhang, F., Bai, B. B., & Shi, L. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.06257 · Cited by 78
“Inspired by works [79,107] and so on, we could expand the output to indicate the probability of whether to conduct a primal heuristics (or other problems which has binary classes) with problem features (A, b, c) or the extracted feature by GCNN [77–79, 105] as shown in Fig.”
BackgroundMethodQualitative Survey on Artificial Intelligence Integrated Blockchain Approach for 6G and Beyond
Pathak, V., Pandya, R. J., Bhatia, V., & López, O. L. A. (2023) · IEEE Access · doi:10.1109/access.2023.3319083 · Cited by 39
Edge Intelligence for Mission Cognitive Wireless Emergency Networks
Wang, L., Zhang, J., Chuan, J., Ma, R., & Fei, A. (2020) · IEEE Wireless Communications · doi:10.1109/mwc.001.1900418 · Cited by 32
“For example, a recent study [12] applied imitation learning to learn the pruning policy in the branch-and-bound algorithm.”
BackgroundSelf-citation$Q$ - TRANSFER: A Novel Framework for Efficient Deep Transfer Learning in Networking
Phan, T. V., Sultana, S., Nguyen, T. G., & Bauschert, T. (2020) · International Conference on Artificial Intelligence in Information and Communication (ICAIIC) · doi:10.1109/icaiic48513.2020.9065240 · Cited by 39
Distributed Auto-Learning GNN for Multi-Cell Cluster-Free NOMA Communications
Xu, X., Liu, Y., Chen, Q., Mu, X., & Ding, Z. (2023) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2023.3242703 · Cited by 33
“While specific solutions such as Learning to Optimize for Resource Management (LORM) [16] have been proposed to handle mixed-integer nonlinear programming (MINLP) in wireless systems, they are typically centralized scheduling methods.”
BackgroundOptimized IoT Service Chain Implementation in Edge Cloud Platform: A Deep Learning Framework
Pham, C., Nguyen, D. T., Tran, N. H. K., Nguyen, K. K., & Cheriet, M. (2021) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2021.3049824 · Cited by 31
“There are some studies in this topic [26], [36], [37] that tried to improve the performance of BnB, but they designed for their specific problems.”
BackgroundShrestha, S., Fu, X., & Hong, M. (2023) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2023.3244096 · Cited by 33
“Such methods have also been adopted in wireless communications in [31], [41] where resource allocation tasks are framed as mixed integer and nonlinear programs (MINPs).”
MethodXu, L., Qin, M., Yang, Q., & Kwak, K. S. (2021) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2021.3135885 · Cited by 40
Efficient Global Algorithms for Transmit Beamforming Design in ISAC Systems
Wu, J., Wang, Z., Liu, Y., & Liu, F. (2024) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2024.3457817 · Cited by 30
“Building upon this foundation, the work [35] introduced a pruning policy based on a multi-layer perceptron (MLP) specifically tailored for wireless networks.”
MethodFaster Activity and Data Detection in Massive Random Access: A Multiarmed Bandit Approach
Dong, J., Zhang, J., Shi, Y., & Wang, J. H. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3142185 · Cited by 28
Self-citationLee, K., Lee, J.-R., & Choi, H.-H. (2020) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2020.2972596 · Cited by 25
“For this reason, the training process of NN is not included to calculate the computational complexity [7]–[11].”
BackgroundBalcan, M.-F., DeBlasio, D., Dick, T., Kingsford, C., Sandholm, T., & Vitercik, E. (2021) · ACM Symposium on Theory of Computing (STOC) · doi:10.1145/3406325.3451036 · Cited by 88
Rago, A., Piro, G., Boggia, G., & Dini, P. (2021) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2021.3099472 · Cited by 25
“Available approaches intend to maximize the overall resource capacity [20], to minimize energy consumption [19] and delay [18], [21], [22], as well as to fulfill the expected upper bound for the overall delay [18], [22].”
BackgroundQ-Learning ADR Agent for LoRaWAN Optimization
Carvalho, R. F., AL-Tam, F., & Correia, N. (2021) · IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT) · doi:10.1109/iaict52856.2021.9532518 · Cited by 24
An Unsupervised Deep Unrolling Framework for Constrained Optimization Problems in Wireless Networks
He, S., Xiong, S., An, Z., Zhang, W., Huang, Y., & Zhang, Y. (2022) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2022.3166964 · Cited by 29
“proposed a learning framework for resource management to learn the optimal pruning policy in the branch-and-bound algorithm for mixed-integer nonlinear programming via imitation learning to reduce the computational complexity [16].”
BackgroundLinear Regression Without Correspondences via Concave Minimization
Peng, L., & Tsakiris, M. C. (2020) · IEEE Signal Processing Letters · doi:10.1109/lsp.2020.3019693 · Cited by 22
“9% permutations can be excluded, which is possible with a tight lower bound [27] or with a learning-based pruning strategy [30].”
BackgroundCache-Enabled Multicast Content Pushing With Structured Deep Learning
Chen, Q., Wang, W., Chen, W., Yu, F. R., & Zhang, Z. (2021) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2021.3078493 · Cited by 25
“Inspired by the recent explosion of successful deep learning based applications, some researches have begun to explore deep learning for optimizing the communication performance [14], [15].”
BackgroundAI Empowered Resource Management for Future Wireless Networks
Shen, Y., Zhang, J., Song, S. H., & Letaief, K. B. (2021) · 2021 IEEE International Mediterranean Conference on Communications and Networking (MeditCom) · doi:10.1109/meditcom49071.2021.9647580 · Cited by 22
Self-citationLearning to Beamform in Joint Multicast and Unicast Transmission With Imperfect CSI
Zhang, Z., Tao, M., & Liu, Y. (2023) · IEEE Transactions on Communications · doi:10.1109/tcomm.2023.3251995 · Cited by 24
“In addition, the node pruning policy in the branch-and-bound based algorithm was learned by a FCNN for solving the mixed integer linear programming problems [24], [25], the mixed integer non-linear programming problems [26] and the complex modulus constrained problems [27].”
MethodInfluentialPrivacy-Preserving Decentralized Inference With Graph Neural Networks in Wireless Networks
Lee, M., Yu, G., & Dai, H. (2023) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2023.3279442 · Cited by 27
“…attracting increasing interest, and shown to outperform traditional model-based design paradigms in many wireless applications, such as resource allocation [2], [3], [4], [5], [6], [7], [8], [9], [10], [11], [12], [13], networking [14], [15], and physical layer design [16], [17], [18], [19], [20].”
BackgroundLearning to Continuously Optimize Wireless Resource in Episodically Dynamic Environment
Sun, H., Pu, W., Zhu, M., Fu, X., Chang, T.-H., & Hong, M. (2021) · ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp39728.2021.9413503 · Cited by 21
“Transfer learning (TL) [15] – update the model using the current data batch (a total of 5, 000 samples); 2.”
BackgroundMethodInfluentialA Study on Deep Learning for Latency Constraint Applications in Beyond 5G Wireless Systems
Sritharan, S., Weligampola, H., & Gacanin, H. (2020) · IEEE Access · doi:10.1109/access.2020.3040133 · Cited by 23
“In [19], the authors propose a framework for ‘‘Learning to Optimize for Resource Man-agement’’ which provides near-optimal performance using fewer data samples.”
BackgroundSparse Array Design for Optimum Beamforming Using Deep Learning
Hamza, S. A., & Amin, M. (2024) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2023.3285201 · Cited by 19
“The DNN design based on standard supervised learning, on the other hand, has been shown to realize computationally efficient implementation of iterative complex signal processing algorithms [38], [39].”
MethodChien, T. V., Le, H. A., Tùng, T. H., Ngo, H. Q., & Chatzinotas, S. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3423008 · Cited by 23
“Furthermore, these ML-based methods generalize poorly with the significantly dropped performance when the system settings in the test data set differ from the training [29].”
Sparse Optimization for Green Edge AI Inference
Yang, X., Hua, S., Shi, Y., Wang, H., Zhang, J., & Letaief, K. B. (2020) · Journal of Communications and Information Networks · doi:10.23919/jcin.2020.9055106 · Cited by 19
Self-citationA Scalable Test Problem Generator for Sequential Transfer Optimization
Xue, X., Yang, C., Feng, L., Zhang, K., Song, L., & Tan, K. C. (2025) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2025.3547565 · Cited by 28
“…broadly categorized into two groups: 1) learning-based methods that predict the target optimum through a learned mapping derived from source tasks [9], [10], [11] and 2) knowledge transfer-based methods that enhance target search performance by transferring knowledge from the source tasks [12],…”
Deep momentum uncertainty hashing
Fu, C., Wang, G., Wu, X., Zhang, Q., & He, R. (2021) · Pattern Recognition · doi:10.1016/j.patcog.2021.108264 · Cited by 19
How Neural Architectures Affect Deep Learning for Communication Networks?
Shen, Y., Zhang, J., & Letaief, K. B. (2022) · International Conference on Communications · doi:10.1109/icc45855.2022.9839205 · Cited by 19
“Higher sample efficiency implies better generalization: Recently, there is a growing interest in sample-efficient neural architectures for solving communication problems [4], [12], [26].”
Self-citationMuy, S., Lee, K., & Lee, J.-R. (2021) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2021.3055205 · Cited by 19
Learning-Based Resource Allocation in Heterogeneous Ultradense Network
Zhang, X., Zhang, Z. J., & Yang, L. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3173210 · Cited by 18
Improving Learning Efficiency for Wireless Resource Allocation with Symmetric Prior
Sun, C., Wu, J., & Yang, C. (2022) · IEEE Wireless Communications · doi:10.1109/mwc.003.21003437 · Cited by 24
“By customizing DNNs for specific tasks, model-based deep learning may need very few samples [10] or with low computational complexity for training [11].”
Two-Dimensional Task Offloading for Mobile Networks: An Imitation Learning Framework
Yan, Z., Cheng, P., Chen, Z., Vucetic, B. S., & Li, Y. (2021) · IEEE/ACM Transactions on Networking · doi:10.1109/tnet.2021.3093452 · Cited by 18
Learn to Communicate With Neural Calibration: Scalability and Generalization
Ma, Y., Shen, Y., Yu, X., Zhang, J., Song, S., & Letaief, K. B. (2022) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2022.3181219 · Cited by 21
“For example, it was shown in [25] that the execution time of the proposed resource management scheme is 2.”
Self-citationXiao, Z., Zhi, J., & Keskin, B. B. (2022) · Computers & Operations Research · doi:10.1016/j.cor.2022.105897 · Cited by 17
How Much Data Is Sufficient to Learn High-Performing Algorithms?
Balcan, M.-F., DeBlasio, D., Dick, T., Kingsford, C., Sandholm, T., & Vitercik, E. (2024) · Journal of the ACM · doi:10.1145/3676278 · Cited by 26
Lazy Lagrangians for Optimistic Learning With Budget Constraints
Anderson, D., Iosifidis, G., & Leith, D. J. (2023) · IEEE/ACM Transactions on Networking · doi:10.1109/tnet.2022.3222404 · Cited by 14
“From a network management perspective, the availability of predictions is common in wireless networks and (mobile) computing systems and several works use deep learning or other function approximators [27] to predict f τ , g τ for τ ≥ t and select a better x t [28], [29].”
BackgroundHuang, M., Huang, L., Zhong, Y., Yang, H., Chen, X., Huo, W., Wang, J., Zhang, F., Bai, B. B., & Shi, L. (2023) · Journal of the Operations Research Society of China · doi:10.1007/s40305-023-00493-1 · Cited by 14
Meta-Gating Framework for Fast and Continuous Resource Optimization in Dynamic Wireless Environments
Hou, Q., Lee, M., Yu, G., & Cai, Y. (2023) · IEEE Transactions on Communications · doi:10.1109/tcomm.2023.3292257 · Cited by 17
Zhang, Z., & Tao, M. (2021) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2021.3123620 · Cited by 14
Learning Sparse Array Capon Beamformer Design Using Deep Learning Approach
Hamza, S. A., & Amin, M. G. (2020) · IEEE Radar Conference (RadarConf) · doi:10.1109/radarconf2043947.2020.9266359 · Cited by 13
“Recently, ’learn to optimize’ approaches has been proposed to improve and automate the implementation of DNNs learning approach and has also been shown to realize computationally efficient implementation of iterative signal processing algorithms [23]– [27].”
BackgroundAccelerating Resource Allocation for D2D Communications Using Imitation Learning
Lee, M., Yu, G., & Li, G. Y. (2019) · IEEE Vehicular Technology Conference · doi:10.1109/vtcfall.2019.8891075 · Cited by 15
“1) Feature Design: In [7], problem-independent features have been proposed, while problem-dependent ones have been exploited in [8] to improve the performance of the imitation learning method.”
BackgroundMethodContinual Learning-Based Fast Beamforming Adaptation in Downlink MISO Systems
Zhou, H., Xia, W., Zhao, H., Zhang, J., Ni, Y., & Zhu, H. (2022) · IEEE Wireless Communications Letters · doi:10.1109/lwc.2022.3216330 · Cited by 15
“We compare the proposed CL-BNN scheme with another four training schemes, which are introduced as follows: 1) Transfer learning (Labelled as TL) [11] 3(a) and 3(b), we compare the proposed scheme with four different training schemes.”
BackgroundMethodSelf-citationZhou, H., Xia, W., Zheng, G., & Zhu, H. (2025) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2025.3585146 · Cited by 16
Scalable Video Caching for Information Centric Wireless Networks
Zhang, Z., Dai, J., Zeng, M., Liu, D., & Mao, S. (2020) · IEEE Access · doi:10.1109/access.2020.2989532 · Cited by 12
“Existing solutions such as branch-and-bound algorithms may suffer from forbidding computational complexity or unsatisfactory optimality [28].”
BackgroundIntelligent Beamforming for UAV-Assisted IIoT Based on Hypergraph Inspired Explainable Deep Learning
Zhao, H., Liu, K., Liu, M., Garg, S., & Alrashoud, M. R. (2023) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2023.3325128 · Cited by 11
“Thus, the popularity of DL based optimization have gradually exceeds the one of traditional algorithms to solve NP hard problems for wireless resource allocations [13], [14], [15], [16], [17].”
BackgroundResource Allocation for D2D Cellular Networks With QoS Constraints: A DC Programming- Based Approach
Chang, H.-H., Liu, L., Bai, J., Pidwerbetsky, A., Berlinsky, A., Huang, J., Ashdown, J., Turck, K., & Yi, Y. (2021) · IEEE Access · doi:10.1109/access.2021.3132260 · Cited by 10
“Similar to [49], [50], we compare with the global optimal solution using the branchand-bound (BB) method to show the performance gaps of different methods with the optimal solution [31].”
Calibrated Learning for Online Distributed Power Allocation in Small-Cell Networks
Zhang, X., Nakhai, M. R., Zheng, G., Lambotharan, S., & Ottersten, B. (2019) · IEEE Transactions on Communications · doi:10.1109/tcomm.2019.2938514 · Cited by 10
“resource allocation have been developed in wireless communications [21]–[26].”
BackgroundContinual Learning-Based MIMO Channel Estimation: A Benchmarking Study
Akrout, M., Feriani, A., Bellili, F., Mezghani, A., & Hossain, E. (2023) · International Conference on Communications · doi:10.1109/icc45041.2023.10278623 · Cited by 13
“However, these learning-based methods are usually trained and evaluated on fixed datasets and/or stationary propagation environments [3].”
AI-Enabled Intelligent Resource Management in 6G
Ponnusamy, V., & Vasuki, A. (2022) · Blockchain technologies · doi:10.1007/978-981-19-2868-0_4 · Cited by 8
Lv, S., Li, X., Liu, J., & Shi, M. (2024) · IEEE Transactions on Green Communications and Networking · doi:10.1109/tgcn.2024.3359208 · Cited by 7
“Recently, the deep learning (DL) methods have been applied in the field of communication to deal with intractable problems [20], [21], [22], [23].”
BackgroundCross Layer Power Allocation by Graph Neural Networks in Heterogeneous D2D Video Communications
Tseng, S., Wen, S.-T., Fang, C., & Norouzi, M. (2025) · IEEE Access · doi:10.1109/access.2025.3548854 · Cited by 13
QoS controlled capacity offload optimization in heterogeneous networks
Thiagarajah, S. P., Alias, M. Y., & Tan, W.-N. (2020) · Bulletin of Electrical Engineering and Informatics · doi:10.11591/eei.v9i6.2706 · Cited by 7
“Branch and bound (BB) is a popular algorithm used in the radio resource allocation of HetNet [11-15].”
MethodMuhammad, O., Jiang, H., Umer, M. M., Muhammad, B., & Naeem, M. A. (2023) · Intelligent Automation & Soft Computing · doi:10.32604/iasc.2023.041232 · Cited by 6
Transfer Learning Empowered Resource Allocation for Vehicular Edge Computing
Zhang, Y., Zhang, K., & Wu, F. (2022) · IEEE International Conference on Communication Technology (ICCT) · doi:10.1109/icct56141.2022.10072466 · Cited by 6
“In [7], the authors apply transfer learning to resource management in wireless networks, where a pretrained machine learning model is quickly adapted to the new task with only a few additional unlabeled training samples.”
BackgroundMission Structure Learning-Based Resource Allocation in Space Information Networks
He, H., Zhou, D., Sheng, M., & Li, J. (2021) · International Conference on Communications · doi:10.1109/icc42927.2021.9500738 · Cited by 6
“To cope with the difficulties caused by the changes of missions, transfer learning (TL) has been successfully applied in [10], we also use it to accelerate solving process which is denoted as SRAAH-TL.”
MethodBhairanatti, S., & Kumar, S. M. (2023) · International Journal of Electrical and Electronics Engineering · doi:10.14445/23488379/ijeee-v10i1p103 · Cited by 4
Migration-Aware Optimized Resource Allocation in B5G Edge Networks
Prastowo, T., Shah, A., Palopoli, L., Passerone, R., & Piro, G. (2022) · IEEE Consumer Communications and Networking Conference · doi:10.1109/ccnc49033.2022.9700644 · Cited by 4
Zhang, W., Bo, L., Zhang, S., & Wang, Y. (2022) · Computational Intelligence and Neuroscience · doi:10.1155/2022/5148879 · Cited by 4
RetractedNguyen, A.-N., Nguyen, G.-H., Nguyen, K., Son, N. T., Bui, N.-A., Le, P.-C., Hoang, M.-D., Trinh, T.-D., Hoang, T.-A., & So–In, C. (2026) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2026.3656312 · Cited by 3
“This characteristic makes traditional gradient-based methods and deterministic global solvers unsuitable for finding the global optimum of the formulated SEE [54], [87], [88], [89].”
Learning-Based Branching Acceleration for Unit Commitment with Few Training Samples
Zhang, C., Qin, Z., & Sun, Y. (2025) · Applied Sciences · doi:10.3390/app15063366 · Cited by 3
Novel Bee Colony Optimization with Update Quantities for OFDMA Resource Allocation
Sun, M. Y., Huang, Y., Wang, S., & Xu, Y. (2021) · Wireless Communications and Mobile Computing · doi:10.1155/2021/8891020 · Cited by 3
Liu, Z., Li, Y., Wu, Y., & Gong, Y. (2025) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2025.3560116 · Cited by 7
“…evaluate the effectiveness of the proposed low-rank covariance approach (LRCA), we compare it to the following benchmarks: • Transfer Learning (TL) [19]: This benchmark exclusively updates the DNN with data from the current phase, demonstrating how catastrophic forgetting can affect DNN’s…”
InfluentialGraph Neural Networks Based Channel Estimation for mmWave Massive MIMO Systems
Ye, M., Liang, X., Pan, C., Xu, Y., Jiang, M., & Li, C. (2025) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2025.3589434 · Cited by 4
Tseng, S., Wu, J., & Fang, C. (2024) · IEEE Access · doi:10.1109/access.2024.3423840 · Cited by 3
Graph Neural Network Performance Analysis in the Cell-Free Massive MIMO Wireless Systems
Rahman, M. H., Sejan, M. A. S., Aziz, M. A., Tabassum, R., & Song, H. (2024) · International Joint Conference on Computer Science and Software Engineering · doi:10.1109/jcsse61278.2024.10613688 · Cited by 2
“For example, when the user count or signal-to-noise ratio (SNR) in the test dataset differs slightly from that in the training dataset, the efficiency deterioration of MLP-augmented branch-and-bound for the access point selection problem might exceed 50% [7].”
BackgroundGreen communication for OverGNN enabled heterogeneous ultra‐dense networks
Zeng, J., Lin, S., Ai, Y., Wan, G., Luo, W., & Chen, Q. (2025) · IET Communications · doi:10.1049/cmu2.70005 · Cited by 2
Metadata
- Authors
- Shen, Y., Shi, Y., Zhang, J., & Letaief, K. B.
- Affiliations
- Hong Kong University of Science and Technology (HK)
- ShanghaiTech University (CN)
- Hong Kong Polytechnic University (HK)
- Venue
- IEEE Transactions on Wireless Communications
- Published
- 2020-01
- Volume
- 19
- Issue
- 1
- Pages
- 665-679
- ISSN
- 1536-1276 (ISSN-L)
- 1558-2248
- OpenAlex
- W2981871664
- Cited by
- 134
- References
- 37
- Citations by year
- 2026: 11 · 2025: 10 · 2024: 12 · 2023: 24 · 2022: 19 · 2021: 33 · 2020: 19
- FWCI
- 6.92
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Transactions on Wireless Communications (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Rare & Special e-Zone (The Hong Kong University of Science and Technology) (submittedVersion)
- arXiv (Cornell University)
- Funders
- General Research Funding from the Research Grants Council of Hong Kong (16210719)
- National Natural Science Foundation of China (61601290)
- Topics
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Wireless Network Optimization
- Physical Sciences › Computer Science › Computer Networks and Communications › Software-Defined Networks and 5G
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced MIMO Systems Optimization
- Keywords
- mixed-integer nonlinear programming, learning to optimize, imitation learning, transfer learning, self-imitation, sample efficiency, unlabeled samples, feasibility
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.