For English reader,please refer to English Version.

随着深度学习的发展，使用深度学习解决相关通信领域问题的研究也越来越多。作为一名通信专业的研究生，如果实验室没有相关方向的代码积累，入门并深入一个新的方向会十分艰难。同时，大部分通信领域的论文不会提供开源代码，reproducible research比较困难。
基于深度学习的通信论文这几年飞速增加，明显能感觉这些论文的作者更具开源精神。本项目专注于整理在通信中应用深度学习，并公开了相关源代码的论文。
个人关注的领域和精力有限，这个列表不会那么完整。如果你知道一些相关的开源论文，但不在此列表中，非常欢迎添加，为community贡献一份力量。欢迎交流^_^
温馨提示:watch相较于star更容易得到更新通知 。
TODO

• 按不同小方向分类
• 论文添加下载链接
• 增加更多相关论文代码
• 传统通信论文代码列表
• “通信+DL”论文列表（引用较高，可以没有代码）

论文/Paper

Paper	Code
Exploiting Bi-Directional Channel Reciprocity in Deep Learning for Low Rate Massive MIMO CSI Feedback	Bi-Directional-Channel-Reciprocity
Performance Evaluation of Channel Decoding With Deep Neural Networks	deep-neural-network-decoder
Learning the MMSE Channel Estimator	learning-mmse-est
Deep Deterministic Policy Gradient (DDPG)-Based Energy Harvesting Wireless Communications	Energy-Harvesting-DDPG
Model-Aware Deep Architectures for One-Bit Compressive Variational Autoencoding	deep1bitVAE Not Yet
CSI-based Positioning in Massive MIMO systems using Convolutional Neural Networks	MaMIMO_CSI_with_CNN_positioning Not Yet
Deep Learning for mmWave Beam and Blockage Prediction Using Sub-6GHz Channels	Sub6-Preds-mmWave
Deep Learning for Channel Coding via Neural Mutual Information Estimation	Wireless_encoding_with_MI_estimation
Deep Learning for the Gaussian Wiretap Channel	NN_GWTC
Multi-resolution CSI Feedback with deep learning in Massive MIMO System	CRNet Recommend! very detailed README
Deep-Reinforcement Learning Multiple Access for Heterogeneous Wireless Networks	DLMA
Mobility-Aware Centralized Reinforcement Learning for Dynamic Resource Allocation in HetNets	UARA
Deep Learning for Direct Hybrid Precoding in Millimeter Wave Massive MIMO Systems	DL-hybrid-precoder
Deep Learning-Based Detector for OFDM-IM	DeepIM
Meta-Learning to Communicate: Fast End-to-End Training for Fading Channels	meta-autoencoder
Learning to Communicate in a Noisy Environment	echo
Low-rank mmWave MIMO channel estimation in one-bit receivers	Low-rank-MIMO-channel-estimation-from-one-bit-measurements
Deep Learning for Massive MIMO with 1-Bit ADCs: When More Antennas Need Fewer Pilots	1-Bit-ADCs
ns-3 meets OpenAI Gym: The Playground for Machine Learning in Networking Research	ns3-gym
Turbo Autoencoder: Deep learning based channel code for point-to-point communication channels	yihanjiang/turboae
Communication Algorithms via Deep Learning	yihanjiang/commviadl
Towards Optimal Power Control via Ensembling Deep Neural Networks	PCNet-ePCNet
Low-Precision Neural Network Decoding of Polar Codes	low-precision-nnd
A Graph Neural Network Approach for Scalable Wireless Power Control	Globecom2019
CNN-based Precoder and Combiner Design in mmWave MIMO Systems	Deep_HybridBeamforming
Sequential Convolutional Recurrent Neural Networks for Fast Automatic Modulation Classification	coming soon
An Open-Source Framework for Adaptive Traffic Signal Control	docwza/sumolights
A CNN-Based End-to-End Learning Framework Towards Intelligent Communication Systems	Deepcom
Reinforcement Learning for Channel Coding: Learned Bit-Flipping Decoding	RLdecoding
Adaptive Neural Signal Detection for Massive MIMO	mehrdadkhani/MMNet
Deep Reinforcement Learning for Dynamic Multichannel Access in Wireless Networks	DynamicMultiChannelRL
Q-Learning Algorithm for VoLTE Closed-Loop Power Control in Indoor Small Cells	Q-Learning-Power-Control
Spectrum sharing in vehicular networks based on multi-agent reinforcement learning	MARLspectrumSharingV2X
Deep Learning Models for Wireless Signal Classification With Distributed Low-Cost Spectrum Sensors	modulation_classif
Learning Physical-Layer Communication with Quantized Feedback	quantizedfeedback
Decentralized Scheduling for Cooperative Localization with Deep Reinforcement Learning	DeepRLVehicularLocalization
Deep Reinforcement Learning for Dynamic Multichannel Access in Wireless Networks	DynamicMultiChannelRL
MIST: A Novel Training Strategy for Low-latencyScalable Neural Net Decoders	MIST_CNN_Decoder
Deep UL2DL: Channel Knowledge Transfer from Uplink to Downlink	UL2DL
Deep Learning for TDD and FDD Massive MIMO: Mapping Channels in Space and Frequency	DL-Massive-MIMO
Machine Learning meets Stochastic Geometry: Determinantal Subset Selection for Wireless Networks	DPPL
Learning Based Power Control for mmWave Massive MIMO against Jamming	Learning-Based-Power-Control-for-mmWave-Massive-MIMO-against-Jamming
Sparsely Connected Neural Network for Massive MIMO Detection	MIMO_Detection
Power Allocation in Multi-Cell Networks Using Deep Reinforcement Learningg	qfnet
Deep Learning in Downlink Coordinated Multipoint in New Radio Heterogeneous Networks	DL-CoMP-Machine-Learning
Deep Reinforcement Learning for Resource Allocation in V2V Communications	https://github.com/haoyye/ResourceAllocationReinforcementLearning
RF-based Direction Finding of UAVs Using DNN	https://github.com/LahiruJayasinghe/DeepDOA
Deepcode: Feedback Codes via Deep Learning	https://github.com/hyejikim1/Deepcode https://github.com/yihanjiang/feedback_code
Physical Adversarial Attacks Against End-to-End Autoencoder Communication Systems	https://github.com/meysamsadeghi/Security-and-Robustness-of-Deep-Learning-in-Wireless-Communication-Systems
AIF: An Artificial Intelligence Framework for Smart Wireless Network Management	caogang/WlanDqn
Deep-Learning-Power-Allocation-in-Massive-MIMO	lucasanguinetti / Deep-Learning-Power-Allocation-in-Massive-MIMO
DeepMIMO: A Generic Deep Learning Dataset for Millimeter Wave and Massive MIMO Applications	The DeepMIMO Dataset
Fast Deep Learning for Automatic Modulation Classification	dl4amc/source
Deep Learning-Based Channel Estimation	Mehran-Soltani/ChannelNet
Transmit Power Control Using Deep Neural Network for Underlay Device-to-Device Communication	seotaijiya/TPC_D2D
Deep learning-based channel estimation for beamspace mmWave massive MIMO systems	hehengtao/LDAMP_based-Channel-estimation
Spatial deep learning for wireless scheduling	willtop/Spatial_DeepLearning_Wireless_Scheduling
Decentralized Computation Offloading for Multi-User Mobile Edge Computing: A Deep Reinforcement Learning Approach	swordest/mec_drl
A deep-reinforcement learning approach for software-defined networking routing optimization	knowledgedefinednetworking / a-deep-rl-approach-for-sdn-routing-optimization
Q-Learning Algorithm for VoLTE Closed-Loop Power Control in Indoor Small Cells	farismismar / Q-Learning-Power-Control
Deep Learning for Optimal Energy-Efficient Power Control in Wireless Interference Networks	bmatthiesen / deep-EE-opt
Actor-Critic-Based Resource Allocation for Multi-modal Optical Networks	BoyuanYan / Actor-Critic-Based-Resource-Allocation-for-Multimodal-Optical-Networks
Deep MIMO Detection	neevsamuel/DeepMIMODetection
Learning to Detect	neevsamuel/LearningToDetect
An iterative BP-CNN architecture for channel decoding	liangfei-info/Iterative-BP-CNN
On Deep Learning-Based Channel Decoding	gruberto/DL-ChannelDecoding Decoder-using-deep-learning
DELMU: A Deep Learning Approach to Maximising the Utility of Virtualised Millimetre-Wave Backhauls	ruihuili / DELMU
Deep Q-Learning for Self-Organizing Networks Fault Management and Radio Performance Improvement	farismismar / Deep-Q-Learning-SON-Perf-Improvement
An Introduction to Deep Learning for the Physical Layer	yashcao / RTN-DL-for-physical-layer musicbeer / Deep-Learning-for-the-Physical-Layer helloMRDJ / autoencoder-for-the-Physical-Layer
Convolutional Radio Modulation Recognition Networks	chrisruk/cnn qieaaa / Singal-CNN
Deep-Waveform: A Learned OFDM Receiver Based on Deep Complex Convolutional Networks	zhongyuanzhao / dl_ofdm
Joint Transceiver Optimization for WirelessCommunication PHY with Convolutional NeuralNetwork	hlz1992/RadioCNN
Deep Learning for Massive MIMO CSI Feedback	sydney222 / Python_CsiNet
Beamforming Design for Large-Scale Antenna Arrays Using Deep Learning	TianLin0509/BF-design-with-DL
5G MIMO Data for Machine Learning: Application to Beam-Selection using Deep Learning	lasseufpa/5gm-data
Deep multi-user reinforcement learning for dynamic spectrum access in multichannel wireless networks	shkrwnd/Deep-Reinforcement-Learning-for-Dynamic-Spectrum-Access
DeepNap: Data-Driven Base Station Sleeping Operations through Deep Reinforcement Learning	zaxliu/deepnap
Automatic Modulation Classification: A Deep Learning Enabled Approach	mengxiaomao/CNN_AMC
Deep Architectures for Modulation Recognition	qieaaa / Deep-Architectures-for-Modulation-Recognition
Energy Efficiency in Reinforcement Learning for Wireless Sensor Networks	mkoz71 / Energy-Efficiency-in-Reinforcement-Learning
Learning to optimize: Training deep neural networks for wireless resource management	Haoran-S / DNN_WMMSE
Implications of Decentralized Q-learning Resource Allocation in Wireless Networks	wn-upf / decentralized_qlearning_resource_allocation_in_wns
Power of Deep Learning for Channel Estimation and Signal Detection in OFDM Systems	haoyye/OFDM_DNN

"通信+DL"论文（无代码)/Paper List Without Code

说明：论文主要来源于arxiv中Signal Processing和Information Theory

• Robust Data Detection for MIMO Systems with One-Bit ADCs: A Reinforcement Learning Approach
• Distributed Power Control for Large Energy Harvesting Networks: A Multi-Agent Deep Reinforcement Learning Approach
• Machine Learning for Wireless Communication Channel Modeling: An Overview
• Sum Spectral Efficiency Maximization in Massive MIMO Systems: Benefits from Deep Learning

数据集/Database

• MASSIVE MIMO CSI MEASUREMENTS
• SM-CsiNet+ and PM-CsiNet+:来自论文Convolutional Neural Network based Multiple-Rate Compressive Sensing for Massive MIMO CSI Feedback: Design, Simulation, and Analysis
• An open online real modulated dataset:来自论文Deep Learning for Signal Demodulation in Physical Layer Wireless Communications: Prototype Platform, Open Dataset, and Analytics。

To the best of our knowledge,this is the first open dataset of real modulated signals for wireless communication systems.

• RF DATASETS FOR MACHINE LEARNING
• open datase:来自论文Signal Demodulation With Machine Learning Methods for Physical Layer Visible Light Communications: Prototype Platform, Open Dataset, and Algorithms

The dataset is collected in real physical environment, and the channel suffers from many factors such as limited LED bandwidth, multi-reflection,spurious or continuous jamming, etc.

学者个人主页/Researcher Homepage

• Ahmed Alkhateeb:Research Interests
  • Millimeter Wave and Massive MIMO Communication
  • Vehicular and Drone Communication Systems
  • Applications of Machine Learning in Wireless Communication
  • Building Mobile Communication Systems that Work in Reality!
• Emil Björnson: He performs research on multi-antenna communications, Massive MIMO, radio resource allocation, energy-efficient communications, and network design.
• Leo-Chu:His research interests are in the theoretical and algorithmic studies in random matrix theory, nonconvex optimization, deep learning, as well as their applications in wireless communications, bioengineering, and smart grid.

有用的网页和材料/Useful Websites and Materials

• 机器学习和通信结合论文列表/Research Library
• Best Readings in Machine Learning in Communications

贡献者/Contributors：

• WxZhu:
  • Github
  • Email:wenxingzhu@shu.edu.cn
• LinTian
• HongtaiChen
• yihanjiang

版本更新/Version Update：

1. 第一版完成/First Version：2019-02-21