{"type":"ScholarlyArticle","title":"Learning to Accelerate Heuristic Searching for Large-Scale Maximum Weighted b-Matching Problems in Online Advertising","authors":[{"name":"Xiaotian Hao","slug":"xiaotian-hao","given":"Xiaotian","family":"Hao","affiliation":"College of Intelligence and Computing , Tianjin University"},{"name":"Junqi Jin","slug":"junqi-jin","given":"Junqi","family":"Jin","affiliation":"Alibaba Group , Beijing"},{"name":"Jianye Hao","slug":"jianye-hao","given":"Jianye","family":"Hao","affiliation":"College of Intelligence and Computing , Tianjin University; Noah's Ark Lab , Huawei; Tianjin Key Lab of Machine Learning"},{"name":"Jin Li","slug":"jin-li","given":"Jin","family":"Li","affiliation":"Alibaba Group , Beijing"},{"name":"Weixun Wang","slug":"weixun-wang","given":"Weixun","family":"Wang","affiliation":"College of Intelligence and Computing , Tianjin University"},{"name":"Yi Ma","slug":"yi-ma","given":"Yi","family":"Ma","affiliation":"College of Intelligence and Computing , Tianjin University"},{"name":"Zhenzhe Zheng","slug":"zhenzhe-zheng","given":"Zhenzhe","family":"Zheng","affiliation":"Shanghai Jiao Tong University"},{"name":"Han Li","slug":"han-li","given":"Han","family":"Li","affiliation":"Alibaba Group , Beijing"},{"name":"Jian Xu","slug":"jian-xu","given":"Jian","family":"Xu","affiliation":"Alibaba Group , Beijing"},{"name":"Kun Gai","slug":"kun-gai","given":"Kun","family":"Gai","affiliation":"Alibaba Group , Beijing"}],"abstract":"Bipartite b-matching is fundamental in algorithm design, and has been widely applied into diverse applications, such as economic markets, labor markets, etc. These practical problems usually exhibit two distinct features: large-scale and dynamic, which requires the matching algorithm to be repeatedly executed at regular intervals. However, existing exact and approximate algorithms usually fail in such settings due to either requiring intolerable running time or too much computation resource. \r\nTo address this issue, based on a key observation that the matching instances vary not too much, we propose NeuSearcher which leverage the knowledge learned from previously instances to solve new problem instances. Specifically, we design a multichannel graph neural network to predict the threshold of the matched edges, by which the search region could be significantly reduced. We further propose a parallel heuristic search algorithm to iteratively improve the solution quality until convergence. Experiments on both open and industrial datasets demonstrate that NeuSearcher can speed up 2 to 3 times while achieving exactly the same matching solution compared with the state-of-the-art approximation approaches.","doi":"10.24963/ijcai.2020/475","url":"https://ijcai.org/proceedings/2020/475","pdf":"https://ijcai.org/proceedings/2020/0475.pdf","markdown":"https://ijcai.org/proceedings/2020/475.md","bibtex":"https://ijcai.org/proceedings/2020/bibtex/475","volume":{"slug":"2020","title":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2020","url":"https://ijcai.org/proceedings/2020/","year":2020,"location":"Yokohama","dates":"January 2021 (postponed from 11-17 July 2020)","editors":"Christian Bessiere","isbn":"978-0-9992411-6-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2020"},"section":"Multidisciplinary Topics and Applications","track":"Main track","number":475,"pages":{"first":3437,"last":3443},"keywords":["Constraints and SAT: Constraint Optimization","Multidisciplinary Topics and Applications: Recommender Systems","Machine Learning Applications: Applications of Supervised Learning"],"videos":[{"label":"Video","url":"https://videos.ijcai20.org/25495/file_25495.m3u8","length_sec":305,"provider":"hls"}],"references":[{"position":1,"raw":"[Agrawal et al., 2018] Shipra Agrawal, Morteza Zadi- moghaddam, and Vahab Mirrokni. Proportional allo- cation: Simple, distributed, and diverse matching with high entropy. In International Conference on Machine Learning, pages 99-108, 2018.","title":"Proportional allocation: Simple, distributed, and diverse matching with high entropy","authors":"Shipra Agrawal, Morteza Zadimoghaddam, Vahab Mirrokni","year":"2018","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Avis, 1983] David Avis. A survey of heuristics for the weighted matching problem. Networks, 13(4):475-493, 1983.","title":"A survey of heuristics for the weighted matching problem","authors":"David Avis","year":"1983","venue":"Networks","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bayati et al., 2011] Mohsen Bayati, Christian Borgs, Jen- nifer Chayes, and Riccardo Zecchina. Belief propagation for weighted b-matchings on arbitrary graphs and its rela- tion to linear programs with integer solutions. SIAM Jour- nal on Discrete Mathematics, 25(2):989-1011, 2011.","title":"Belief propagation for weighted b-matchings on arbitrary graphs and its relation to linear programs with integer solutions","authors":"Mohsen Bayati, Christian Borgs, Jennifer Chayes, Riccardo Zecchina","year":"2011","venue":"SIAM Journal on Discrete Mathematics","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Chen and Tian, 2019] Xinyun Chen and Yuandong Tian. Learning to perform local rewriting for combinatorial op- timization. In Advances in Neural Information Processing Systems, pages 6278-6289, 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":5,"raw":"[De Francisci Morales et al., 2011] Gianmarco De Fran- cisci Morales, Aristides Gionis, and Mauro Sozio. Social content matching in mapreduce. Proceedings of the VLDB Endowment, 4(7):460-469, 2011.","title":"Social content matching in mapreduce","authors":"Francisci De, Morales","year":"2011","venue":"Proceedings of the VLDB Endowment","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Dhillon, 2001] Inderjit S Dhillon. Co-clustering documents and words using bipartite spectral graph partitioning. In Proceedings of the seventh ACM SIGKDD international conference on Knowledge discovery and data mining, pages 269-274. ACM, 2001.","title":"Co-clustering documents and words using bipartite spectral graph partitioning","authors":"Inderjit S Dhillon","year":"2001","venue":"Proceedings of the seventh ACM SIGKDD international conference on Knowledge discovery and data mining","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Ding et al., 2019] Jian-Ya Ding, Chao Zhang, Lei Shen, Shengyin Li, Bing Wang, Yinghui Xu, and Le Song. Opti- mal solution predictions for mixed integer programs. arXiv preprint arXiv:1906.09575, 2019.","title":"Optimal solution predictions for mixed integer programs","authors":"Jian-Ya Ding, Chao Zhang, Lei Shen, Shengyin Li, Bing Wang, Yinghui Xu, Le Song","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Edmonds, 1965] Jack Edmonds. Maximum matching and a polyhedron with 0, 1-vertices. Journal of research of the National Bureau of Standards B, 69(125-130):55-56, 1965.","title":"Maximum matching and a polyhedron with 0, 1-vertices","authors":"Jack Edmonds, Edmonds","year":"1965","venue":"Journal of research of the National Bureau of Standards B","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Grötschel and Holland, 1985] Martin Grötschel and Olaf Holland. Solving matching problems with linear program- ming. Mathematical Programming, 33(3):243-259, 1985.","title":"Solving matching problems with linear programming","authors":"Holland Grötschel, Martin Grötschel, Olaf Holland","year":"1985","venue":"Mathematical Programming","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Gurobi, 2014] Gurobi. Inc. gurobi optimizer reference man- ual, 2015. URL: http://www. gurobi. com, 2014.","title":"Gurobi. Inc. gurobi optimizer reference manual","authors":null,"year":"2014","venue":null,"doi":null,"url":"http://www.gurobi.com,2014","internal_url":null},{"position":11,"raw":"[Harper and Konstan, 2016] F Maxwell Harper and Joseph A Konstan. The movielens datasets: History and context. Acm transactions on interactive intelligent systems (tiis), 5(4):19, 2016.","title":"The movielens datasets: History and context","authors":"Maxwell Harper, Joseph A Konstan","year":"2016","venue":"Acm transactions on interactive intelligent systems","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[He and McAuley, 2016] Ruining He and Julian McAuley. Ups and downs: Modeling the visual evolution of fashion trends with one-class collaborative filtering. In proceed- ings of the 25th international conference on world wide web, pages 507-517. International World Wide Web Con- ferences Steering Committee, 2016.","title":"Ruining He and Julian McAuley. Ups and downs: Modeling the visual evolution of fashion trends with one-class collaborative filtering","authors":"Mcauley He","year":"2016","venue":"proceedings of the 25th international conference on world wide web","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[He et al., 2014] He He, Hal Daume III, and Jason M Eisner. Learning to search in branch and bound algorithms. In Advances in neural information processing systems, pages 3293-3301, 2014.","title":"Learning to search in branch and bound algorithms","authors":"He","year":"2014","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Hougardy, 2009] Stefan Hougardy. Linear time approxima- tion algorithms for degree constrained subgraph problems. In Research Trends in Combinatorial Optimization, pages 185-200. Springer, 2009.","title":"Linear time approximation algorithms for degree constrained subgraph problems","authors":"Stefan Hougardy","year":"2009","venue":"Research Trends in Combinatorial Optimization","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Khalil et al., 2017] Elias Khalil, Hanjun Dai, Yuyu Zhang, Bistra Dilkina, and Le Song. Learning combinatorial op- timization algorithms over graphs. In Advances in Neural Information Processing Systems, pages 6348-6358, 2017.","title":"Learning combinatorial optimization algorithms over graphs","authors":"Khalil","year":"2017","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Khan et al., 2016] Arif Khan, Alex Pothen, Md Mostofa Ali Patwary, Nadathur Rajagopalan Satish, Narayanan Sundaram, Fredrik Manne, Mahantesh Halappanavar, and Pradeep Dubey. Efficient approximation algorithms for weighted b-matching. SIAM Journal on Scientific Com- puting, 38(5):S593-S619, 2016.","title":"Efficient approximation algorithms for weighted b-matching","authors":"Arif Khan, Alex Pothen, Md Mostofa, Ali Patwary, Rajagopalan Nadathur, Narayanan Satish, Fredrik Sundaram, Mahantesh Manne, Pradeep Halappanavar, Dubey","year":"2016","venue":"SIAM Journal on Scientific Computing","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Li et al., 2018] Zhuwen Li, Qifeng Chen, and Vladlen Koltun. Combinatorial optimization with graph convolu- tional networks and guided tree search. In Advances in Neural Information Processing Systems, pages 539-548, 2018.","title":"Combinatorial optimization with graph convolutional networks and guided tree search","authors":"Li","year":"2018","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Müller-Hannemann and Schwartz, 2000] Matthias Müller- Hannemann and Alexander Schwartz. Implementing weighted b-matching algorithms: insights from a com- putational study. Journal of Experimental Algorithmics (JEA), 5:8, 2000.","title":"Implementing weighted b-matching algorithms: insights from a computational study","authors":"Müller-Hannemann, Matthias Schwartz, Alexander Müller-Hannemann, Schwartz","year":"2000","venue":"Journal of Experimental Algorithmics (JEA)","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Naim and Manne, 2018] Md Naim and Fredrik Manne. Scalable b-matching on gpus. In 2018 IEEE International Parallel and Distributed Processing Symposium Work- shops (IPDPSW), pages 637-646. IEEE, 2018.","title":"Scalable b-matching on gpus","authors":"Md Naim, Fredrik Manne","year":"2018","venue":"IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Padberg and Rao, 1982] Manfred W Padberg and M Ram Rao. Odd minimum cut-sets and b-matchings. Mathe- matics of Operations Research, 7(1):67-80, 1982.","title":"Odd minimum cut-sets and b-matchings","authors":"Rao Padberg, Manfred W Padberg, M Ram Rao","year":"1982","venue":"Mathematics of Operations Research","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Preis, 1999] Robert Preis. Linear time 1/2-approximation algorithm for maximum weighted matching in general graphs. In Annual Symposium on Theoretical Aspects of Computer Science, pages 259-269. Springer, 1999.","title":"Robert Preis. Linear time 1/2-approximation algorithm for maximum weighted matching in general graphs","authors":"Preis","year":"1999","venue":"Annual Symposium on Theoretical Aspects of Computer Science","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Vinyals et al., 2015] Oriol Vinyals, Meire Fortunato, and Navdeep Jaitly. Pointer networks. In Advances in Neural Information Processing Systems, pages 2692-2700, 2015.","title":"Pointer networks","authors":"Oriol Vinyals, Meire Fortunato, Navdeep Jaitly","year":"2015","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Wu et al., 2019] Zonghan Wu, Shirui Pan, Fengwen Chen, Guodong Long, Chengqi Zhang, and Philip S Yu. A comprehensive survey on graph neural networks. arXiv preprint arXiv:1901.00596, 2019.","title":"A comprehensive survey on graph neural networks","authors":"Wu","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Xu et al., 2018] Keyulu Xu, Weihua Hu, Jure Leskovec, and Stefanie Jegelka. How powerful are graph neural net- works? arXiv preprint arXiv:1810.00826, 2018.","title":"How powerful are graph neural networks","authors":"Xu","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Zanfir and Sminchisescu, 2018] Andrei Zanfir and Cristian Sminchisescu. Deep learning of graph matching. In Pro- ceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 2684-2693, 2018.","title":"Andrei Zanfir and Cristian Sminchisescu. Deep learning of graph matching","authors":"Sminchisescu Zanfir","year":"2018","venue":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}