| 组合优化+强化学习必读论文列表 | 您所在的位置：网站首页 › graph editor cs academy › 组合优化+强化学习必读论文列表 |
|
刚刚上海交大Thinklab实验室放出了他们收集的组合优化的论文列表。短短两个小时已经有了60个GitHub Star。 GitHub地址：（请大家多多点赞，谢谢！） 组合优化是什么？在应用数学和理论计算机科学的领域中，组合优化是在一个有限的对象集中找出最优对象的一类课题。在很多组合优化的问题中，穷举搜索／枚举法是不可行的。组合优化的问题的特征是可行解的集是离散或者可以简化到离散的，并且目标是找到最优解。常见的例子有旅行商问题和最小生成树。二维的例子，比如服装厂做衣服，衣服分成很多块，这些块需要从布料上切下来。怎么切，剩下的废布料最少？三维的例子，如集装优化。组合优化和生产生活中遇到的很多决策问题都息息相关。 强化学习是什么？强化学习（英语：Reinforcement learning，简称RL）是机器学习中的一个领域，强调如何基于环境而行动，以取得最大化的预期利益。强化学习是除了监督学习和非监督学习之外的第三种基本的机器学习方法。与监督学习不同的是，强化学习不需要带标签的输入输出对，同时也无需对非最优解的精确地纠正。其关注点在于寻找探索（对未知领域的）和利用（对已有知识的）的平衡，强化学习中的“探索-利用”的交换，在多臂老虎机问题和有限MDP中研究得最多。 下面是论文列表。 Survey PapersA Survey of Reinforcement Learning and Agent-Based Approaches to Combinatorial Optimization. INFORMS Journal on Computing, 1999. journalSmith, Kate A.Model-Based Search for Combinatorial Optimization: A Critical Survey. Annals of Operations Research, 2004. journalZlochin, Mark and Birattari, Mauro and Meuleau, Nicolas and Dorigo, Marco.Machine Learning Approaches to Learning Heuristics for Combinatorial Optimization Problems. Procedia Manufacturing, 2018. journalMirshekarian, Sadegh and Sormaz, Dusan.Boosting combinatorial problem modeling with machine learning. IJCAI, 2018. paperLombardi, Michele and Milano, Michela.A Review of combinatorial optimization with graph neural networks. BigDIA, 2019. paperHuang, Tingfei and Ma, Yang and Zhou, Yuzhen and Huang, Honglan Huang and Chen, Dongmei and Gong, Zidan and Liu, Yao.Machine Learning for Combinatorial Optimization: a Methodological Tour d'horizon. EJOR, 2020. journalBengio, Yoshua and Lodi, Andrea and Prouvost, Antoine.Reinforcement Learning for Combinatorial Optimization: A Survey. Arxiv, 2020. paperMazyavkina, Nina and Sviridov, Sergey and Ivanov, Sergei and Burnaev, Evgeny.✨Learning Graph Matching and Related Combinatorial Optimization Problems. IJCAI, 2020. paperYan, Junchi and Yang, Shuang, and Hancock, Edwin R.Learning Combinatorial Optimization on Graphs: A Survey with Applications to Networking. IEEE ACCESS, 2020. journalVesselinova, Natalia and Steinert, Rebecca and Perez-Ramirez, Daniel F. and Boman, Magnus.From Shallow to Deep Interactions Between Knowledge Representation, Reasoning and Machine Learning. Arxiv, 2020. paperBouraoui, Zied and Cornuéjols, Antoine and Denœux, Thierry and Destercke, Sébastien and Dubois, Didier and Guillaume, Romain and Marques-Silva, João and Mengin, Jérôme and Prade, Henri and Schockaert, Steven and Serrurier, Mathieu and Vrain, Christel.A Survey on Reinforcement Learning for Combinatorial Optimization. Arxiv, 2020. paperYang, Yunhao and Whinston, Andrew.Research Reviews of Combinatorial Optimization Methods Based on Deep Reinforcement Learning. (in chinese) 自动化学报, 2020. journalLi, Kai-Wen and Zhang, Tao and Wang, Rui and Qin, Wei-Jian and He, Hui-Hui and Huang, Hong.Graph Learning for Combinatorial Optimization: A Survey of State-of-the-Art. Data Science and Engineering, 2021. journalPeng, Yue, Choi, Byron, and Xu, Jianliang.Combinatorial Optimization and Reasoning with Graph Neural Networks Arxiv, 2021. paperCappart, Quentin and Chetelat, Didier and Khalil, Elias and Lodi, Andrea and Morris, Christopher and Velickovic, PetarMachine Learning for Electronic Design Automation (EDA) : A Survey TODAES, 2021. journalHuang, Guyue and Hu, Jingbo and He, Yifan and Liu, Jialong and Ma, Mingyuan and Shen, Zhaoyang and Wu, Juejian and Xu, Yuanfan and Zhang, Hengrui and Zhong, Kai and othersProblemsGraph MatchingRevised Note on Learning Algorithms for Quadratic Assignment with Graph Neural Networks Arxiv, 2017. paper, codeNowak, Alex and Villar, Soledad and Bandeira, S. Afonso and Bruna, JoanDeep Learning of Graph Matching. CVPR, 2018. paperZanfir, Andrei and Sminchisescu, Cristian✨Learning Combinatorial Embedding Networks for Deep Graph Matching. ICCV, 2019. paper, codeWang, Runzhong and Yan, Junchi and Yang, XiaokangDeep Graphical Feature Learning for the Feature Matching Problem. ICCV, 2019. paperZhang, Zhen and Lee, Wee SunGLMNet: Graph Learning-Matching Networks for Feature Matching. Arxiv, 2019. paperJiang, Bo and Sun, Pengfei and Tang, Jin and Luo, Bin✨Learning deep graph matching with channel-independent embedding and Hungarian attention. ICLR, 2020. paperYu, Tianshu and Wang, Runzhong and Yan, Junchi and Li, BaoxinDeep Graph Matching Consensus. ICLR, 2020. paperFey, Matthias and Lenssen, Jan E. and Morris, Christopher and Masci, Jonathan and Kriege, Nils M.✨Graduated Assignment for Joint Multi-Graph Matching and Clustering with Application to Unsupervised Graph Matching Network Learning. NeurIPS, 2020. paperWang, Runzhong and Yan, Junchi and Yang, Xiaokang✨Combinatorial Learning of Robust Deep Graph Matching: An Embedding Based Approach. TPAMI, 2020. paperWang, Runzhong and Yan, Junchi and Yang, XiaokangDeep Graph Matching via Blackbox Differentiation of Combinatorial Solvers. ECCV, 2020. paper, codeRolinek, Michal and Swoboda, Paul and Zietlow, Dominik and Paulus, Anselm and Musil, Vit and Martius, Georg✨Deep Reinforcement Learning of Graph Matching. Arxiv, 2020. paperLiu, Chang and Wang, Runzhong and Jiang, Zetian and Yan, Junchi✨Neural Graph Matching Network: Learning Lawler's Quadratic Assignment Problem with Extension to Hypergraph and Multiple-graph Matching. TPAMI, 2021. paperWang, Runzhong and Yan, Junchi and Yang, Xiaokang✨Deep Latent Graph Matching ICML, 2021. paperYu, Tianshu and Wang, Runzhong and Yan, Junchi and Li, Baoxin.Quadratic Assignment ProblemRevised Note on Learning Algorithms for Quadratic Assignment with Graph Neural Networks Arxiv, 2017. paper, codeNowak, Alex and Villar, Soledad and Bandeira, S. Afonso and Bruna, Joan✨Deep Reinforcement Learning of Graph Matching. Arxiv, 2020. paperLiu, Chang and Wang, Runzhong and Jiang, Zetian and Yan, Junchi✨Neural Graph Matching Network: Learning Lawler's Quadratic Assignment Problem with Extension to Hypergraph and Multiple-graph Matching. TPAMI, 2021. paperWang, Runzhong and Yan, Junchi and Yang, XiaokangTravelling Salesman ProblemLearning Combinatorial Optimization Algorithms over Graphs. NeurIPS, 2017. paperDai, Hanjun and Khalil, Elias B and Zhang, Yuyu and Dilkina, Bistra and Song, LePOMO: Policy Optimization with Multiple Optima for Reinforcement Learning. NeurIPS, 2018. paperKwon, Yeong-Dae and Choo, Jinho and Kim, Byoungjip and Yoon, Iljoo and Min, Seungjai and Gwon, Youngjune.Learning Heuristics for the TSP by Policy Gradient CPAIOR, 2018. paper, codeMichel DeudonPierre CournutAlexandre LacosteAttention, Learn to Solve Routing Problems! ICLR, 2019. paperKool, Wouter and Van Hoof, Herke and Welling, Max.Learning to Solve NP-Complete Problems: A Graph Neural Network for Decision TSP. AAAI, 2019. paperPrates, Marcelo and Avelar, Pedro HC and Lemos, Henrique and Lamb, Luis C and Vardi, Moshe Y.An Efficient Graph Convolutional Network Technique for the Travelling Salesman Problem Arxiv, 2019. paper, codeChaitanya K. Joshi, Thomas Laurent, Xavier BressonGeneralize a Small Pre-trained Model to Arbitrarily Large TSP Instances. Arxiv, 2020. paperFu, Zhang-Hua and Qiu, Kai-Bin and Zha, Hongyuan.Differentiation of Blackbox Combinatorial Solvers ICLR, 2020. paper, codeMarin Vlastelica, Anselm Paulus, Vít Musil, Georg Martius, Michal RolínekThe Transformer Network for the Traveling Salesman Problem IPAM, 2021. paperXavier Bresson，Thomas LaurentLearning Improvement Heuristics for Solving Routing Problems TNNLS, 2021. journalWu, Yaoxin and Song, Wen and Cao, Zhiguang and Zhang, Jie and Lim, AndrewReversible Action Design for Combinatorial Optimization with Reinforcement Learning Arxiv, 2021. paperYao, Fan and Cai, Renqin and Wang, HongningMaximal CutLearning Combinatorial Optimization Algorithms over Graphs. NeurIPS, 2017. paperDai, Hanjun and Khalil, Elias B and Zhang, Yuyu and Dilkina, Bistra and Song, LeExploratory Combinatorial Optimization with Reinforcement Learning. AAAI, 2020. paperLBarrett, Thomas and Clements, William and Foerster, Jakob and Lvovsky, Alex.Erdos Goes Neural: an Unsupervised Learning Framework for Combinatorial Optimization on Graphs. NeurIPS, 2020. paperKaralias, Nikolaos and Loukas, AndreasReversible Action Design for Combinatorial Optimization with Reinforcement Learning Arxiv, 2021. paperYao, Fan and Cai, Renqin and Wang, HongningVehicle Routing ProblemLearning to Perform Local Rewriting for Combinatorial Optimization. NeurIPS, 2019. paper, codeChen, Xinyun and Tian, Yuandong.Deep Reinforcement Learning for the Electric Vehicle Routing Problem with Time Windows. Arxiv, 2020. paperLin, Bo and Ghaddar, Bissan and Nathwani, Jatin.A Learning-based Iterative Method for Solving Vehicle Routing Problems ICLR, 2020. paperLu, Hao and Zhang, Xingwen and Yang, ShuangLearning Improvement Heuristics for Solving Routing Problems TNNLS, 2021. journalWu, Yaoxin and Song, Wen and Cao, Zhiguang and Zhang, Jie and Lim, AndrewAnalytics and Machine Learning in Vehicle Routing Research Arxiv, 2021. paperBai, Ruibin and Chen, Xinan and Chen, Zhi-Long and Cui, Tianxiang and Gong, Shuhui and He, Wentao and Jiang, Xiaoping and Jin, Huan and Jin, Jiahuan and Kendall, Graham and othersRP-DQN: An application of Q-Learning to Vehicle Routing Problems Arxiv, 2021. paperBdeir, Ahmad and Boeder, Simon and Dernedde, Tim and Tkachuk, Kirill and Falkner, Jonas K and Schmidt-Thieme, LarsComputing Resource AllocationResource Management with Deep Reinforcement Learning. HotNets, 2016. paperMao, Hongzi and Alizadeh, Mohammad and Menache, Ishai and Kandula, Srikanth.Learning to Perform Local Rewriting for Combinatorial Optimization. NeurIPS, 2019. paper, codeChen, Xinyun and Tian, Yuandong.Learning Scheduling Algorithms for Data Processing Clusters SIGCOMM, 2019. paper, codeMao, Hongzi and Schwarzkopf, Malte and Venkatakrishnan, Bojja Shaileshh and Meng, Zili and Alizadeh, Mohammad.Smart Resource Allocation for Mobile Edge Computing: A Deep Reinforcement Learning Approach IEEE Transactions on Emerging Topics in Computing, 2019. PaperJiadai; Lei Zhao; Jiajia Liu; Nei KatoA Two-stage Framework and Reinforcement Learning-based Optimization Algorithms for Complex Scheduling Problems Arxiv, 2021. paperHe, Yongming and Wu, Guohua and Chen, Yingwu and Pedrycz, WitoldJob Shop SchedulingLearning to Dispatch for Job Shop Scheduling via Deep Reinforcement Learning. NeurIPS, 2020. paper, codeZhang, Cong and Song, Wen and Cao, Zhiguang and Zhang, Jie and Tan, Puay Siew and Xu, Chi.Bin Packing ProblemSmall Boxes Big Data: A Deep Learning Approach to Optimize Variable Sized Bin Packing BigDataService, 2017. paperMao, Feng and Blanco, Edgar and Fu, Mingang and Jain, Rohit and Gupta, Anurag and Mancel, Sebastien and Yuan, Rong and Guo, Stephen and Kumar, Sai and Tian, YayangSolving a New 3D Bin Packing Problem with Deep Reinforcement Learning Method Arxiv, 2017. paperHu, Haoyuan and Zhang, Xiaodong and Yan, Xiaowei and Wang, Longfei and Xu, YinghuiRanked Reward: Enabling Self-Play Reinforcement Learning for Combinatorial Optimization Alexandre Arxiv, 2018. paperLaterre, Alexandre and Fu, Yunguan and Jabri, Mohamed Khalil and Cohen, Alain-Sam and Kas, David and Hajjar, Karl and Dahl, Torbjorn S and Kerkeni, Amine and Beguir, KarimA Multi-task Selected Learning Approach for Solving 3D Bin Packing Problem. AAMAS, 2019. paperDuan, Lu and Hu, Haoyuan and Qian, Yu and Gong, Yu and Zhang, Xiaodong and Xu, Yinghui and Wei, Jiangwen.A Data-Driven Approach for Multi-level Packing Problems in Manufacturing Industry KDD, 2019. paperChen, Lei and Tong, Xialiang and Yuan, Mingxuan and Zeng, Jia and Chen, LeiSolving Packing Problems by Conditional Query Learning OpenReview, 2019. paperLi, Dongda and Ren, Changwei and Gu, Zhaoquan and Wang, Yuexuan and Lau, FrancisRePack: Dense Object Packing Using Deep CNN with Reinforcement Learning CACS, 2019. paperChu, Yu-Cheng and Lin, Horng-HorngA Generalized Reinforcement Learning Algorithm for Online 3D Bin-Packing. AAAI Workshop, 2020. paperVerma, Richa and Singhal, Aniruddha and Khadilkar, Harshad and Basumatary, Ansuma and Nayak, Siddharth and Singh, Harsh Vardhan and Kumar, Swagat and Sinha, Rajesh.Robot Packing with Known Items and Nondeterministic Arrival Order. TASAE, 2020. paperWang, Fan and Hauser, Kris.TAP-Net: Transport-and-Pack using Reinforcement Learning. TOG, 2020. paper, codeHu, Ruizhen and Xu, Juzhan and Chen, Bin and Gong, Minglun and Zhang, Hao and Huang, Hui.Simultaneous Planning for Item Picking and Placing by Deep Reinforcement Learning IROS, 2020. paperTanaka, Tatsuya and Kaneko, Toshimitsu and Sekine, Masahiro and Tangkaratt, Voot and Sugiyama, MasashiMonte Carlo Tree Search on Perfect Rectangle Packing Problem Instances GECCO, 2020. paperPejic, Igor and van den Berg, DaanPackIt: A Virtual Environment for Geometric Planning ICML, 2020. paperGoyal, Ankit and Deng, JiaOnline 3D Bin Packing with Constrained Deep Reinforcement Learning. AAAI, 2021. paperZhao, Hang and She, Qijin and Zhu, Chenyang and Yang, Yin and Xu, Kai.Graph Edit DistanceSimGNN - A Neural Network Approach to Fast Graph Similarity Computation WSDM, 2019. paper, codeBai, Yunsheng and Ding, Hao and Bian, Song and Chen, Ting and Sun, Yizhou and Wang, WeiGraph Matching Networks for Learning the Similarity of Graph Structured Objects ICML, 2019. paperLi, Yujia and Gu, Chenjie and Dullien, Thomas and Vinyals, Oriol and Kohli, Pushmeet✨Combinatorial Learning of Graph Edit Distance via Dynamic Embedding. CVPR, 2021. paperWang, Runzhong and Zhang, Tianqi and Yu, Tianshu and Yan, Junchi and Yang, Xiaokang.Graph ColoringDeep Learning-based Hybrid Graph-Coloring Algorithm for Register Allocation. Arxiv, 2019. paperDas, Dibyendu and Ahmad, Shahid Asghar and Venkataramanan, Kumar.Maximal Common SubgraphFast Detection of Maximum Common Subgraph via Deep Q-Learning. Arxiv, 2020. paperBai, Yunsheng and Xu, Derek and Wang, Alex and Gu, Ken and Wu, Xueqing and Marinovic, Agustin and Ro, Christopher and Sun, Yizhou and Wang, Wei.Influence MaximizationLearning Heuristics over Large Graphs via Deep Reinforcement Learning. NeurIPS, 2020. paperMittal, Akash and Dhawan, Anuj and Manchanda, Sahil and Medya, Sourav and Ranu, Sayan and Singh, Ambuj.Maximal Independent SetCombinatorial Optimization with Graph Convolutional Networks and Guided Tree Search. NeurIPS, 2018. paperLi, Zhuwen and Chen, Qifeng and Koltun, Vladlen.Distributed Scheduling Using Graph Neural Networks ICASSP, 2021. paperZhao, Zhongyuan and Verma, Gunjan and Rao, Chirag and Swami, Ananthram and Segarra, SantiagoMixed Integer ProgrammingImproving Learning to Branch via Reinforcement Learning. NeurIPS Workshop, 2020. paperSun, Haoran and Chen, Wenbo and Li, Hui and Song, Le.CombOptNet: Fit the Right NP-Hard Problem by Learning Integer Programming Constraints Arxiv, 2021. paperPaulus, Anselm and Rolinek, Michal and Musil, Vit and Amos, Brandon and Martius, GeorgSmart Feasibility Pump: Reinforcement Learning for (Mixed) Integer Programming Arxiv, 2021. paperQi, Meng and Wang, Mengxin and Shen, Zuo-JunCausal DiscoveryCausal Discovery with Reinforcement Learning. ICLR, 2020. paperZhu, Shengyu and Ng, Ignavier and Chen, Zhitang.Game Theoretic SemanticsFirst-Order Problem Solving through Neural MCTS based Reinforcement Learning. Arxiv, 2021. paperXu, Ruiyang and Kadam, Prashank and Lieberherr, Karl.Boolean SatisfiabilityGraph neural networks and boolean satisfiability. Arxiv, 2017. paperBünz, Benedikt, and Matthew Lamm.Learning a SAT solver from single-bit supervision. Arxiv, 2018. paper, codeSelsam, Daniel, Matthew Lamm, Benedikt Bünz, Percy Liang, Leonardo de Moura, and David L. Dill.Machine learning-based restart policy for CDCL SAT solvers. SAT, 2018. paperLiang, Jia Hui, Chanseok Oh, Minu Mathew, Ciza Thomas, Chunxiao Li, and Vijay Ganesh.Learning to solve circuit-SAT: An unsupervised differentiable approach ICLR, 2019. paper, codeAmizadeh, Saeed, Sergiy Matusevych, and Markus Weimer.Learning Local Search Heuristics for Boolean Satisfiability. NeurIPS, 2019. paper, codeYolcu, Emre and Poczos, BarnabasImproving SAT solver heuristics with graph networks and reinforcement learning. Arxiv, 2019. paperKurin, Vitaly, Saad Godil, Shimon Whiteson, and Bryan Catanzaro.Graph neural reasoning may fail in certifying boolean unsatisfiability Arxiv, 2019. paperChen, Ziliang, and Zhanfu Yang.Guiding high-performance SAT solvers with unsat-core predictions SAT, 2019. paperSelsam, Daniel, and Nikolaj Bjørner.G2SAT: Learning to Generate SAT Formulas NeurIPS, 2019. paper, codeYou, Jiaxuan, Haoze Wu, Clark Barrett, Raghuram Ramanujan, and Jure Leskovec.Learning Heuristics for Quantified Boolean Formulas through Reinforcement Learning Arxiv, 2019. paper, codeLederman, Gil, Markus N. Rabe, Edward A. Lee, and Sanjit A. Seshia.Enhancing SAT solvers with glue variable predictions. Arxiv, 2020. paperHan, Jesse Michael.Can Q-Learning with Graph Networks Learn a Generalizable Branching Heuristic for a SAT Solver? NeurIPS, 2020. paperWhiteson, Shimon.Online Bayesian Moment Matching based SAT Solver Heuristics. ICML, 2020. paper, codeDuan, Haonan, Saeed Nejati, George Trimponias, Pascal Poupart, and Vijay Ganesh.Learning Clause Deletion Heuristics with Reinforcement Learning. AITP, 2020. paperVaezipoor, Pashootan, Gil Lederman, Yuhuai Wu, Roger Grosse, and Fahiem Bacchus.Classification of SAT problem instances by machine learning methods. CEUR, 2020. paperDanisovszky, Márk, Zijian Győző Yang, and Gábor Kusper.Predicting Propositional Satisfiability via End-to-End Learning. AAAI, 2020. paperCameron, Chris, Rex Chen, Jason Hartford, and Kevin Leyton-Brown.Neural heuristics for SAT solving. Arxiv, 2020. paperJaszczur, Sebastian, Michał Łuszczyk, and Henryk Michalewski.NLocalSAT: Boosting Local Search with Solution Prediction Arxiv, 2020. paper, codeZhang, Wenjie, Zeyu Sun, Qihao Zhu, Ge Li, Shaowei Cai, Yingfei Xiong, and Lu Zhang.Differentiable OptimizationDifferentiable Learning of Submodular Models NeurIPS, 2017. paper, codeJosip Djolonga, Andreas KrauseMelding the Data-Decisions Pipeline: Decision-Focused Learning for Combinatorial Optimization AAAI, 2019. paperBryan Wilder, Bistra Dilkina, Milind TambeMIPaaL: Mixed Integer Program as a Layer AAAI, 2020. paper, codeAaron Ferber, Bryan Wilder, Bistra Dilkina, Milind TambeSmart Predict-and-Optimize for Hard Combinatorial Optimization Problems AAAI, 2020. paper, codeJaynta Mandi, Emir Demirovi, Peter. J Stuckey, Tias GunsDifferentiation of blackbox combinatorial solvers ICLR, 2020. paper, codeMarin Vlastelica Pogani, Anselm Paulus, Vit Musil, Georg Martius, Michal RolinekInterior Point Solving for LP-based prediction+optimization NeurIPS, 2020. paper, codeJayanta Mandi, Tias GunsCar DispatchDispatch of autonomous vehicles for taxi services: A deep reinforcement learning approach Transportation Research, 2020. paperChao Mao, Yulin Liu, Zuo-Jun (Max) Shen |
| CopyRight 2018-2019 实验室设备网 版权所有 |