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
Items 101–136 of 136
Learning to Branch-and-Bound for Header-Free Communications
Shi, Y., & Shi, Y. (2019) · IEEE Globecom Workshops (GC Wkshps) · doi:10.1109/gcwkshps45667.2019.9024448 · Cited by 2
“The learning-based framework to accelerate the branch-and-bound algorithm for mixed-integer linear programming (MILP) and mixed-integer nonlinear programming (MINLP) were proposed in [9] and [10], respectively.”
BackgroundMethodInfluentialSelf-citationHaberleşme Sistemlerinde Derin Öğrenme
Yıldırım, M. (2020) · European Journal of Science and Technology · doi:10.31590/ejosat.679929 · Cited by 3
A Learning Based Branch-and-Bound Algorithm for Single-Group Multicast Beamforming
Zhang, Z., & Tao, M. (2021) · Globecom · doi:10.1109/globecom46510.2021.9686002 · Cited by 2
“Unlike the BB algorithms for solving MILPs [11] and MINLPs [12] where the branching variables are integers, the branching of AC-BB is based on continuous argument sets.”
BackgroundMethodInfluentialReducing Sample Complexity of Deep Learning with Symmetric Prior of Wireless TasksPreprint
Sun, C., Wu, J., & Yang, C. (2020) · arXiv (Cornell University) · Cited by 2
Machine Learning-Enabled Radio Resource Management for Next-Generation Wireless Networks
Elsayed, M. (2021) · uO Research (University of Ottawa) · doi:10.20381/ruor-26696 · Cited by 3
Resource Management Through Energy Harvesting and Mobility Prediction: A Learning Approach
Alqasir, A., & Aldubaikhy, K. (2024) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-024-09407-6 · Cited by 1
Model-Driven Meta-Learning-Aided Fast Beam Prediction in Millimeter-Wave Communications
Lu, W., Jiang, X., Cao, Y., Ohtsuki, T. O., & Bai, E. (2025) · Electronics · doi:10.3390/electronics14132734 · Cited by 1
Load-Balancing During Resource Allocation in Multi-Cell MIMO-NOMA
Samuel, A., Zhu, R., Li, Y., & Zhou, B. (2026) · IEEE Transactions on Communications · doi:10.1109/tcomm.2026.3657399 · Cited by 1
“According to [[29], Theorem 1], the complexity of searching for the feasible solution of non-optimal nodes is O ( N 2 U 2 + n ).”
Quantum neural network empowered spectral efficiency analysis in IRS-assisted communication systems
Rahman, M. H., Aziz, M. A., Tabassum, R., Sejan, M. A. S., Baek, M.-S., & Song, H. (2025) · Alexandria Engineering Journal · doi:10.1016/j.aej.2025.08.032 · Cited by 1
Yihe, D. I. A. O., Ding, R., Zeng, Z., Zhou, F., & Wu, Q. (2026) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2026.3709883 · Cited by 2
“However, the resource allocation problems are generally formulated as mixed integer nonlinear programming (MINLP) problems due to the continuous and discrete variables [14].”
Transmission Power Control for Interference Reduction in Cellular D2D Networks
Sadehvand, M., Moghim, N., Ghahfarokhi, B. S., & Shetty, S. S. (2023) · International Symposium on Networks, Computers and Communications (ISNCC) · doi:10.1109/isncc58260.2023.10323715 · Cited by 1
“In [8], a learning-to-optimize framework is proposed for resource management in wireless networks with dynamic channel conditions.”
BackgroundAdvancing 6G Networks: The Implications of Edge AI Integration
Hannah Jessie Rani, R., Mishra, A., & Ratchagar, N. P. (2023) · International Conference on Advances in Computation, Communication and Information Technology (ICAICCIT) · doi:10.1109/icaiccit60255.2023.10466006 · Cited by 1
“[21] A Federated Learning (FL) technique was created to learn the tail distribution of queue lengths in order to reduce queuing delay in vehicular networks.”
MethodA Graph Convolutional Network Approach for AP Selection in User-Centric Cell-Free Massive MIMO
Zhao, Y., Zhang, F., Zhang, P., & Zhou, Z. (2024) · International Conference on Neural Networks, Information and Communication Engineering (NNICE) · doi:10.1109/nnice61279.2024.10498770 · Cited by 2
“A prominent short-coming of above DL approaches is that they requires a huge amounts of training samples [10].”
BackgroundA deep learning‐based HARQ chase combining for FBMC‐OQAM systems
Bedoui, A., & Et‐tolba, M. (2021) · International Journal of Communication Systems · doi:10.1002/dac.4957 · Cited by 1
“15 They proposed a framework of learning to optimize resource management (LORM) based on a transfer learning method via self-imitation in LORM, which achieved near-optimal performance with low computational complexity.”
MethodPerformance of a Neural Network Receiver under Mismatch of Channel Training Samples
de Souza, P. H. C., Mendes, L. L., & Souza, R. D. (2022) · IEEE Future Networks World Forum (FNWF) · doi:10.1109/fnwf55208.2022.00099 · Cited by 2
Data Representation for Deep Learning with Priori Knowledge of Symmetric Wireless Tasks.Preprint
Sun, C., Wu, J., & Yang, C. (2020) · arXiv (Cornell University) · Cited by 1
Sparse Array Beamformer Design for Active and Passive SensingPreprint
Hamza, S. A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.06816 · Cited by 1
Xue, X., Yang, C., Feng, L., Zhang, K., Song, L., & Tan, K. C. (2022) · doi:10.36227/techrxiv.21694754.v1 · Cited by 1
Distributed Learning in Non-Convex World: Theory, Algorithms, and Applications
Sun, H. (2021) · University of Minnesota Digital Conservancy (University of Minnesota)
2020 Index IEEE Transactions on Wireless Communications Vol. 19
(2020) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2020.3044507 · Cited by 1
Xue, X., Yang, C., Feng, L., Zhang, K., Song, L., & Tan, K. C. (2022) · doi:10.36227/techrxiv.21694754
Load Balanced User Association Scheme in Planned Non-bias Small Cell Deployment
Thiagarajah, S. P., Alias, M. Y., & Tan, W.-N. (2023) · IJAIT (International Journal of Applied Information Technology) · doi:10.25124/ijait.v6i01.4835
Density-based anti-clustering for scheduling D2D communications
Elsheikh, A., Ibrahim, A. S., & Ismail, M. H. (2024) · Wireless Networks · doi:10.1007/s11276-023-03635-8
“…transformation [4], heuristics, which can use any form of minimization or maximization of utility under certain assumptions [5], and adaptive learning optimization, which uses deep learning for the pruning step instead of calculating all possibilities for a certain branching operation [6, 7].”
OverGNN Assisted Power Allocation for Heterogeneous Ultra-Dense Networks
Lin, S., Lee, M., Chen, Q., Wen, D., Du, W., & He, Z. (2023) · International Conference on Wireless Communications and Signal Processing (WCSP) · doi:10.1109/wcsp58612.2023.10405334
“Currently, deep neural network (DNN) has been widely investigated in resource allocation due to its ability to learn the mapping from wireless networks to sub-optimal resource allocation policies [2], [3].”
BackgroundMethodEfficient Automated Model for Predicting and Detecting the Heart Disease Through Machine Learning
Parisha, P. (2024) · Journal of Electrical Systems · doi:10.52783/jes.2025
“Another issue in wireless networking where machine learning was used to achieve optimal performance was resource management [14].”
BackgroundLearning to optimize via graph neural networks
Yong, Z., Zou, Y., Wu, Y., Shi, Y., & Zhang, J. (2025) · Elsevier eBooks · doi:10.1016/b978-0-44-322073-9.00020-1
Self-citation6G and AI: Viewpoints, Processes, and Technologies
Shoyusupov, S. A., Lanitha, B., Goyal, S., Goyal, V., Husain, S. O., & Sharma, P. (2024) · International Conference on Communication, Computing and Energy Efficient Technologies (I3CEET) · doi:10.1109/i3ceet61722.2024.10993761
Cao, Z., Qiu, T., Zhou, X., Huang, M., & Wang, X. (2026) · IEEE Transactions on Networking · doi:10.1109/ton.2026.3682855
“While DAgger expands the dataset by introducing nodes deviating from expert trajectories as negative samples, it inevitably results in expert trajectories being overshadowed by the increasing volume of negative samples [26].”
InfluentialMassive MIMO with Artificial Intelligence for Interference Management
Bhaskar, K., Jahnavi, C., Alekhya, G., Dhanush, K., Chaithanya, A., & Akash, M. (2026) · International Journal of Emerging Research in Science Engineering and Management · doi:10.58482/ijersem.v2i3.41
Deep Learning-Based Sparse Array Design with Pre-Steering for Adaptive Beamforming
Straub, I., & Hamza, S. A. (2026) · IEEE Radar Conference (RadarConf) · doi:10.1109/radarconf2663773.2026.11674961
Lyapunov-Guided Learning for AoI Minimization in Wireless-Powered NOMA Sensor Networks
Huang, L., Qiu, X., Chi, K., & Wu, Y. (2026) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2026.3709543
Bayat, M. H., Khalily-Dermany, M., & Karimi, A. (2026) · The Journal of Supercomputing · doi:10.1007/s11227-026-08742-9
“Shen et al. introduced LORM [17], a learning-based optimization model for resource management in wireless networks with limited training samples.”
AI-Empowered Fog or Edge Resource Management
Banchhode, S., Phadatare, A., & Varade, P. (2026) · Smart innovation, systems and technologies · doi:10.1007/978-3-032-15996-0_20
SysUM: NDT-Assisted System-Level Scenario-Adaptive Universal Model for AI-6G Networks
He, D., Jiao, T., Tao, T., Xu, Y., Xiao, Z., Huang, Y., Sun, S. D., Dai, M., Sun, J., Guan, Y., et al. (2026) · IEEE Wireless Communications Letters · doi:10.1109/lwc.2026.3733994
“Learning-to-optimize approaches improve real-time processing capability but require supervision from conventional optimization results, which inherently constrains achievable performance [3].”
Chen, N., Xiao, A., Wu, S., Jia, H., Ji, Z., & Kuang, L. (2026) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2026.3734463
“Shen et al. [84] proposed LORM, which learns the pruning policy of branch-and-bound for mixed-integer nonlinear programming and reduces the search space while retaining near-optimality and feasibility.”
QoS-Aware LEO Satellite Access Scheduling With Residual-Doppler Risk Calibration
Ma, J., Zhao, T., Li, Y., Wu, J., Guo, Z., & Zhou, J. (2026) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2026.3741700
“Learned resource allocation can model stochastic policies or assist constrained optimization [29], [30], [31].”
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.