{"type":"ScholarlyArticle","title":"MARCO: A Memory-Augmented Reinforcement Framework for Combinatorial Optimization","authors":[{"name":"Andoni I. Garmendia","slug":"andoni-i-garmendia","given":"Andoni","family":"I. Garmendia","affiliation":"University of the Basque Country (UPV/EHU) , Donostia-San Sebastian , Spain"},{"name":"Quentin Cappart","slug":"quentin-cappart","given":"Quentin","family":"Cappart","affiliation":"Polytechnique Montréal , Montreal , Canada"},{"name":"Josu Ceberio","slug":"josu-ceberio","given":"Josu","family":"Ceberio","affiliation":"University of the Basque Country (UPV/EHU) , Donostia-San Sebastian , Spain"},{"name":"Alexander Mendiburu","slug":"alexander-mendiburu","given":"Alexander","family":"Mendiburu","affiliation":"University of the Basque Country (UPV/EHU) , Donostia-San Sebastian , Spain"}],"abstract":"Neural Combinatorial Optimization (NCO) is an emerging domain where deep learning techniques are employed to address combinatorial optimization problems as a standalone solver. Despite their potential, existing NCO methods often suffer from inefficient search space exploration, frequently leading to local optima entrapment or redundant exploration of previously visited states. This paper introduces a versatile framework, referred to as Memory-Augmented Reinforcement for Combinatorial Optimization (MARCO), that can be used to enhance both constructive and improvement methods in NCO through an innovative memory module. MARCO stores data collected throughout the optimization trajectory and retrieves contextually relevant information at each state. This way, the search is guided by two competing criteria: making the best decision in terms of the quality of the solution and avoiding revisiting already explored solutions. This approach promotes a more efficient use of the available optimization budget. Moreover, thanks to the parallel nature of NCO models, several search threads can run simultaneously, all sharing the same memory module, enabling an efficient collaborative exploration. Empirical evaluations, carried out on the maximum cut, maximum independent set and travelling salesman problems, reveal that the memory module effectively increases the exploration, enabling the model to discover diverse, higher-quality solutions. MARCO achieves good performance in a low computational cost, establishing a promising new direction in the field of NCO.","doi":"10.24963/ijcai.2024/766","url":"https://ijcai.org/proceedings/2024/766","pdf":"https://ijcai.org/proceedings/2024/0766.pdf","markdown":"https://ijcai.org/proceedings/2024/766.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/766","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"Search","track":"Main Track","number":766,"pages":{"first":6931,"last":6939},"keywords":["Search: S: Combinatorial search and optimisation","Search: S: Search and machine learning"],"videos":[],"references":[{"position":1,"raw":"[Ahn et al., 2020] Sungsoo Ahn, Younggyo Seo, and Jinwoo Shin. Learning what to defer for maximum independent sets. In International Conference on Machine Learning, pages 134-144.","title":"Learning what to defer for maximum independent sets","authors":"Ahn","year":"2020","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"PMLR, 2020.","title":null,"authors":"Pmlr","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Applegate et al., 2006] David Applegate, Ribert Bixby, Vasek Chvatal, and William Cook. Concorde tsp solver, 2006. URL http://www. tsp. gatech. edu/concorde, 2006.","title":"Concorde tsp solver","authors":"David Applegate, Ribert Bixby, Vasek Chvatal, William Cook","year":"2006","venue":null,"doi":null,"url":"http://www.tsp.gatech.edu/concorde,2006","internal_url":null},{"position":4,"raw":"[Barrett et al., 2020] Thomas Barrett, William Clements, Jakob Foerster, and Alex Lvovsky. Exploratory combi- natorial optimization with reinforcement learning. In Pro- ceedings of the AAAI conference on artificial intelligence, volume 34, pages 3243-3250, 2020.","title":"Exploratory combinatorial optimization with reinforcement learning","authors":"Thomas Barrett, William Clements, Jakob Foerster, Alex Lvovsky","year":"2020","venue":"Proceedings of the AAAI conference on artificial intelligence","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Bello et al., 2016] Irwan Bello, Hieu Pham, Quoc V Le, Mohammad Norouzi, and Samy Bengio. Neural combi- natorial optimization with reinforcement learning. arXiv preprint arXiv:1611.09940, 2016.","title":"Neural combinatorial optimization with reinforcement learning","authors":"Irwan Bello, Hieu Pham, V Quoc, Mohammad Le, Samy Norouzi, Bengio","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Bengio et al., 2021] Yoshua Bengio, Andrea Lodi, and An- toine Prouvost. Machine learning for combinatorial op- timization: a methodological tour d'horizon. European Journal of Operational Research, 290(2):405-421, 2021.","title":"Machine learning for combinatorial optimization: a methodological tour d'horizon","authors":"Yoshua Bengio, Andrea Lodi","year":"2021","venue":"European Journal of Operational Research","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Blum, 2005] Christian Blum. Ant colony optimization: In- troduction and recent trends. Physics of Life reviews, 2(4):353-373, 2005.","title":"Christian Blum. Ant colony optimization: Introduction and recent trends","authors":"Blum","year":"2005","venue":"Physics of Life reviews","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Böther et al., 2021] Maximilian Böther, Otto Kißig, Martin Taraz, Sarel Cohen, Karen Seidel, and Tobias Friedrich. What's wrong with deep learning in tree search for com- binatorial optimization. In International Conference on Learning Representations, 2021.","title":"What's wrong with deep learning in tree search for combinatorial optimization","authors":"Maximilian Böther, Otto Kißig, Martin Taraz, Sarel Cohen, Karen Seidel, Tobias Friedrich","year":"2021","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Burer et al., 2002] Samuel Burer, Renato DC Monteiro, and Yin Zhang. Rank-two relaxation heuristics for max-cut and other binary quadratic programs. SIAM Journal on Optimization, 12(2):503-521, 2002.","title":"Rank-two relaxation heuristics for max-cut and other binary quadratic programs","authors":"Burer","year":"2002","venue":"SIAM Journal on Optimization","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Cappart et al., 2023] Quentin Cappart, Didier Chételat, Elias B Khalil, Andrea Lodi, Christopher Morris, and Petar Velickovic. Combinatorial optimization and reason- ing with graph neural networks. J. Mach. Learn. Res., 24:130-1, 2023.","title":"Combinatorial optimization and reasoning with graph neural networks","authors":"Quentin Cappart, Didier Chételat, Elias B Khalil, Andrea Lodi, Christopher Morris, Petar Velickovic","year":"2023","venue":"J. Mach. Learn. Res","doi":null,"url":null,"internal_url":"/proceedings/2021/595"},{"position":11,"raw":"[Chen and Tian, 2019] Xinyun Chen and Yuandong Tian. Learning to perform local rewriting for combinatorial op- timization. Advances in Neural Information Processing Systems, 32, 2019.","title":"Learning to perform local rewriting for combinatorial optimization","authors":"Chen, Tian ; ] Xinyun Chen, Yuandong Tian","year":"2019","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Choo et al., 2022] Jinho Choo, Yeong-Dae Kwon, Jihoon Kim, Jeongwoo Jae, André Hottung, Kevin Tierney, and Youngjune Gwon. Simulation-guided beam search for neural combinatorial optimization. Advances in Neural In- formation Processing Systems, 35:8760-8772, 2022.","title":"Simulation-guided beam search for neural combinatorial optimization","authors":"Jinho Choo, Yeong-Dae Kwon, Jihoon Kim, Jeongwoo Jae, André Hottung, Kevin Tierney, Youngjune Gwon","year":"2022","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Dorigo et al., 2006] Marco Dorigo, Mauro Birattari, and Thomas Stutzle. Ant colony optimization. IEEE compu- tational intelligence magazine, 1(4):28-39, 2006.","title":"Ant colony optimization","authors":"Marco Dorigo, Mauro Birattari, Thomas Stutzle","year":"2006","venue":"IEEE computational intelligence magazine","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Dunning et al., 2018] Iain Dunning, Swati Gupta, and John Silberholz. What works best when? a systematic evalua- tion of heuristics for max-cut and qubo. INFORMS Jour- nal on Computing, 30(3):608-624, 2018.","title":"What works best when? a systematic evaluation of heuristics for max-cut and qubo","authors":"Iain Dunning, Swati Gupta, John Silberholz","year":"2018","venue":"INFORMS Journal on Computing","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Dwivedi and Bresson, 2020] Vijay Prakash Dwivedi and Xavier Bresson. A generalization of transformer networks to graphs. arXiv preprint arXiv:2012.09699, 2020.","title":"A generalization of transformer networks to graphs","authors":"Vijay Prakash, Dwivedi, Xavier Bresson","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Erdős et al., 1960] Paul Erdős, Alfréd Rényi, et al. On the evolution of random graphs. Publ. math. inst. hung. acad. sci, 5(1):17-60, 1960.","title":"On the evolution of random graphs","authors":"Erdős","year":"1960","venue":"Publ. math. inst. hung. acad. sci","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Gagrani et al., 2022] Mukul Gagrani, Corrado Rainone, Yang Yang, Harris Teague, Wonseok Jeon, Roberto Bon- desan, Herke van Hoof, Christopher Lott, Weiliang Zeng, and Piero Zappi. Neural topological ordering for compu- tation graphs. Advances in Neural Information Processing Systems, 35:17327-17339, 2022.","title":"Neural topological ordering for computation graphs","authors":"Mukul Gagrani, Corrado Rainone, Yang Yang, Harris Teague, Wonseok Jeon, Roberto Bondesan, Christopher Herke Van Hoof, Weiliang Lott, Piero Zeng, Zappi","year":"2022","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Garmendia et al., 2023] Andoni I Garmendia, Josu Ceberio, and Alexander Mendiburu. Neural improvement heuris- tics for graph combinatorial optimization problems. IEEE Transactions on Neural Networks and Learning Systems, 2023.","title":"Neural improvement heuristics for graph combinatorial optimization problems","authors":"Josu Andoni I Garmendia, Alexander Ceberio, Mendiburu","year":"2023","venue":"IEEE Transactions on Neural Networks and Learning Systems","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Glover and Taillard, 1993] Fred Glover and Eric Taillard. A user's guide to tabu search. Annals of operations research, 41(1):1-28, 1993.","title":"A user's guide to tabu search","authors":"Taillard Glover, Fred Glover, Eric Taillard","year":"1993","venue":"Annals of operations research","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Grinsztajn et al., 2024] Nathan Grinsztajn, Daniel Furelos- Blanco, Shikha Surana, Clément Bonnet, and Tom Barrett. Winner takes it all: Training performant rl populations for combinatorial optimization. Advances in Neural Informa- tion Processing Systems, 36, 2024.","title":"Winner takes it all: Training performant rl populations for combinatorial optimization","authors":"Nathan Grinsztajn, Daniel Furelos-Blanco, Shikha Surana, Clément Bonnet, Tom Barrett","year":"2024","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"Gurobi Optimization, LLC. Gurobi Optimizer Reference Manual, 2023.","title":"Gurobi Optimization","authors":null,"year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Hottung et al., 2021] André Hottung, Yeong-Dae Kwon, and Kevin Tierney. Efficient active search for combina- torial optimization problems. In International Conference on Learning Representations, 2021.","title":"Efficient active search for combinatorial optimization problems","authors":"Hottung","year":"2021","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Kim et al., 2021] Minsu Kim, Jinkyoo Park, et al. Learn- ing collaborative policies to solve np-hard routing prob- lems. Advances in Neural Information Processing Sys- tems, 34:10418-10430, 2021.","title":"Learning collaborative policies to solve np-hard routing problems","authors":"Minsu Kim, Jinkyoo Park","year":"2021","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Kipf and Welling, 2016] Thomas N Kipf and Max Welling. Semi-supervised classification with graph convolutional networks. International Conference on Learning Repre- sentations, 2016.","title":"Semi-supervised classification with graph convolutional networks","authors":"N Thomas, Max Kipf, Welling","year":"2016","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Kool et al., 2018] Wouter Kool, Herke van Hoof, and Max Welling. Attention, learn to solve routing problems! In International Conference on Learning Representations, 2018.","title":"Attention, learn to solve routing problems!","authors":"Kool","year":"2018","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Kwon et al., 2020] Yeong-Dae Kwon, Jinho Choo, By- oungjip Kim, Iljoo Yoon, Youngjune Gwon, and Seungjai Min. Pomo: Policy optimization with multiple optima for reinforcement learning. Advances in Neural Information Processing Systems, 33:21188-21198, 2020.","title":"Pomo: Policy optimization with multiple optima for reinforcement learning","authors":"Yeong-Dae Kwon, Jinho Choo, Byoungjip Kim, Iljoo Yoon, Youngjune Gwon, Seungjai Min","year":"2020","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Lamm et al., 2016] Sebastian Lamm, Peter Sanders, Chris- tian Schulz, Darren Strash, and Renato F Werneck. Find- ing near-optimal independent sets at scale. In 2016 Pro- ceedings of the Eighteenth Workshop on Algorithm En- gineering and Experiments (ALENEX), pages 138-150.","title":"Finding near-optimal independent sets at scale","authors":"Sebastian Lamm, Peter Sanders, Christian Schulz, Darren Strash, Renato F Werneck","year":"2016","venue":"Proceedings of the Eighteenth Workshop on Algorithm Engineering and Experiments (ALENEX)","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Lawler et al., 1980] Eugene L. Lawler, Jan Karel Lenstra, and AHG Rinnooy Kan. Generating all maximal indepen- dent sets: Np-hardness and polynomial-time algorithms. SIAM Journal on Computing, 9(3):558-565, 1980.","title":"Generating all maximal independent sets: Np-hardness and polynomial-time algorithms","authors":"Eugene L Lawler, Jan Karel Lenstra, Ahg Rinnooy Kan","year":"1980","venue":"SIAM Journal on Computing","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Lawler et al., 1986] Eugene L Lawler, Jan Karel Lenstra, AHG Rinnooy Kan, and David Bernard Shmoys. The trav- eling salesman problem: a guided tour of combinatorial optimization. The Journal of the Operational Research Society, 37(5):535, 1986.","title":"The traveling salesman problem: a guided tour of combinatorial optimization","authors":"Eugene L Lawler, Jan Karel Lenstra, David Ahg Rinnooy Kan, Shmoys Bernard","year":"1986","venue":"The Journal of the Operational Research Society","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Lu et al., 2019] Hao Lu, Xingwen Zhang, and Shuang Yang. A learning-based iterative method for solving ve- hicle routing problems. In International conference on learning representations, 2019.","title":"A learning-based iterative method for solving vehicle routing problems","authors":"Hao Lu, Xingwen Zhang, Shuang Yang","year":"2019","venue":"International conference on learning representations","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Luo et al., 2024] Fu Luo, Xi Lin, Fei Liu, Qingfu Zhang, and Zhenkun Wang. Neural combinatorial optimization with heavy decoder: Toward large scale generalization. Advances in Neural Information Processing Systems, 36, 2024.","title":"Neural combinatorial optimization with heavy decoder: Toward large scale generalization","authors":"Xi Fu Luo, Fei Lin, Qingfu Liu, Zhenkun Zhang, Wang","year":"2024","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Ma et al., 2021] Yining Ma, Jingwen Li, Zhiguang Cao, Wen Song, Le Zhang, Zhenghua Chen, and Jing Tang. Learning to iteratively solve routing problems with dual- aspect collaborative transformer. Advances in Neural In- formation Processing Systems, 34:11096-11107, 2021.","title":"Learning to iteratively solve routing problems with dualaspect collaborative transformer","authors":"Yining Ma, Jingwen Li, Zhiguang Cao, Wen Song, Le Zhang, Zhenghua Chen, Jing Tang","year":"2021","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Ma et al., 2023] Yining Ma, Zhiguang Cao, and Yeow Meng Chee. Learning to search feasible and infeasible regions of routing problems with flexible neural k-opt. In Thirty-seventh Conference on Neural Information Processing Systems, 2023.","title":"Learning to search feasible and infeasible regions of routing problems with flexible neural k-opt","authors":"Yining Ma, Zhiguang Cao, Yeow Meng Chee","year":"2023","venue":"Thirty-seventh Conference on Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Mazyavkina et al., 2021] Nina Mazyavkina, Sergey Sviri- dov, Sergei Ivanov, and Evgeny Burnaev. Reinforcement learning for combinatorial optimization: A survey. Com- puters & Operations Research, 134:105400, 2021.","title":"Reinforcement learning for combinatorial optimization: A survey","authors":"Nina Mazyavkina, Sergey Sviridov, Sergei Ivanov, Evgeny Burnaev","year":"2021","venue":"Computers & Operations Research","doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Mirhoseini et al., 2021] Azalia Mirhoseini, Anna Goldie, Mustafa Yazgan, Joe Wenjie Jiang, Ebrahim Songhori, Shen Wang, Young-Joon Lee, Eric Johnson, Omkar Pathak, Azade Nazi, et al. A graph placement method- ology for fast chip design. Nature, 594(7862):207-212, 2021.","title":"A graph placement methodology for fast chip design","authors":"Azalia Mirhoseini, Anna Goldie, Mustafa Yazgan, Joe Wenjie Jiang, Ebrahim Songhori, Shen Wang, Young-Joon Lee, Eric Johnson, Omkar Pathak, Azade Nazi","year":"2021","venue":"Nature","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Papadimitriou, 1992] Christos H Papadimitriou. The com- plexity of the lin-kernighan heuristic for the travel- ing salesman problem. SIAM Journal on Computing, 21(3):450-465, 1992.","title":"The complexity of the lin-kernighan heuristic for the traveling salesman problem","authors":"Christos H Papadimitriou","year":"1992","venue":"SIAM Journal on Computing","doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Vaswani et al., 2017] Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. Attention is all you need. Advances in neural information processing systems, 30, 2017.","title":"Attention is all you need","authors":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, Illia Polosukhin","year":"2017","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":38,"raw":"[Vrček et al., 2022] Lovro Vrček, Xavier Bresson, Thomas Laurent, Martin Schmitz, and Mile Šikić. Learning to untangle genome assembly with graph convolutional net- works. arXiv preprint arXiv:2206.00668, 2022.","title":"Learning to untangle genome assembly with graph convolutional networks","authors":"Lovro Vrček, Xavier Bresson, Thomas Laurent, Martin Schmitz, Mile Šikić","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":39,"raw":"[Wang and Tang, 2021] Qi Wang and Chunlei Tang. Deep reinforcement learning for transportation network combi- natorial optimization: A survey. Knowledge-Based Sys- tems, 233:107526, 2021.","title":"Deep reinforcement learning for transportation network combinatorial optimization: A survey","authors":"Wang, Tang ; ] Qi Wang, Chunlei Tang","year":"2021","venue":"Knowledge-Based Systems","doi":null,"url":null,"internal_url":null},{"position":40,"raw":"[Williams, 1992] Ronald J Williams. Simple statistical gradient-following algorithms for connectionist reinforce- ment learning. Machine learning, 8:229-256, 1992.","title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning","authors":"Williams Ronald","year":"1992","venue":"Machine learning","doi":null,"url":null,"internal_url":null},{"position":41,"raw":"[Wu et al., 2021] Yaoxin Wu, Wen Song, Zhiguang Cao, Jie Zhang, and Andrew Lim. Learning improvement heuris- tics for solving routing problems. IEEE Transactions on Neural Networks and Learning Systems, 2021.","title":"Learning improvement heuristics for solving routing problems","authors":"Wu","year":"2021","venue":"IEEE Transactions on Neural Networks and Learning Systems","doi":null,"url":null,"internal_url":null},{"position":42,"raw":"[Xu and Li, 2000] Ke Xu and Wei Li. Exact phase transi- tions in random constraint satisfaction problems. Journal of Artificial Intelligence Research, 12:93-103, 2000.","title":"Exact phase transitions in random constraint satisfaction problems","authors":"Li ; ] Ke Xu, Wei Xu, Li","year":"2000","venue":"Journal of Artificial Intelligence Research","doi":null,"url":null,"internal_url":null},{"position":43,"raw":"[Ye et al., 2023] Haoran Ye, Jiarui Wang, Zhiguang Cao, Helan Liang, and Yong Li. Deepaco: Neural-enhanced ant systems for combinatorial optimization. arXiv preprint arXiv:2309.14032, 2023.","title":"Deepaco: Neural-enhanced ant systems for combinatorial optimization","authors":"Haoran Ye, Jiarui Wang, Zhiguang Cao, Helan Liang, Yong Li","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":44,"raw":"[Zhang et al., 2023] Dinghuai Zhang, Hanjun Dai, Nikolay Malkin, Aaron Courville, Yoshua Bengio, and Ling Pan. Let the flows tell: Solving graph combinatorial problems with gflownets. In Thirty-seventh Conference on Neural Information Processing Systems, 2023.","title":"Let the flows tell: Solving graph combinatorial problems with gflownets","authors":"Zhang","year":"2023","venue":"Thirty-seventh Conference on Neural Information Processing Systems","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}