{"type":"ScholarlyArticle","title":"Robust Subset Selection by Greedy and Evolutionary Pareto Optimization","authors":[{"name":"Chao Bian","slug":"chao-bian","given":"Chao","family":"Bian","affiliation":"State Key Laboratory for Novel Software Technology , Nanjing University , Nanjing 210023 , China"},{"name":"Yawen Zhou","slug":"yawen-zhou","given":"Yawen","family":"Zhou","affiliation":"State Key Laboratory for Novel Software Technology , Nanjing University , Nanjing 210023 , China"},{"name":"Chao Qian","slug":"chao-qian","given":"Chao","family":"Qian","affiliation":"State Key Laboratory for Novel Software Technology , Nanjing University , Nanjing 210023 , China"}],"abstract":"Subset selection, which aims to select a subset from a ground set to maximize some objective function, arises in various applications such as influence maximization and sensor placement. In real-world scenarios, however, one often needs to find a subset which is robust against (i.e., is good over) a number of possible objective functions due to uncertainty, resulting in the problem of robust subset selection. This paper considers robust subset selection with monotone objective functions, relaxing the submodular property required by previous studies. We first show that the greedy algorithm can obtain an approximation ratio with respect to the correlation and submodularity ratios of the objective functions; and then propose EPORSS, an evolutionary Pareto optimization algorithm that can utilize more time to find better subsets. We prove that EPORSS can also be theoretically grounded, achieving a similar approximation guarantee to the greedy algorithm. In addition, we derive the lower bound of the correlation ratio for the application of robust influence maximization, and further conduct experiments to validate the performance of the greedy algorithm and EPORSS.","doi":"10.24963/ijcai.2022/655","url":"https://ijcai.org/proceedings/2022/655","pdf":"https://ijcai.org/proceedings/2022/0655.pdf","markdown":"https://ijcai.org/proceedings/2022/655.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/655","volume":{"slug":"2022","title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2022","url":"https://ijcai.org/proceedings/2022/","year":2022,"location":"Vienna","dates":"23-29 July 2022","editors":"Luc De Raedt","isbn":"978-1-956792-00-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2022"},"section":"Search","track":"Main Track","number":655,"pages":{"first":4726,"last":4732},"keywords":["Search: Evolutionary Computation","Search: Combinatorial Search and Optimisation","Machine Learning: Evolutionary Learning","Search: Heuristic Search"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38986857","length_sec":82,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38985000","length_sec":334,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Anari et al., 2019] N. Anari, N. Haghtalab, J. Naor, S. Pokutta, M. Singh, and A. Torrico. Structured robust submodular max- imization: Offline and online algorithms. In AISTATS, pages 3128-3137, Naha, Japan, 2019.","title":"Structured robust submodular maximization: Offline and online algorithms","authors":"N Anari, N Haghtalab, J Naor, S Pokutta, M Singh, A Torrico","year":"2019","venue":"AISTATS","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bian et al., 2017] A. A. Bian, J. M. Buhmann, A. Krause, and S. Tschiatschek. Guarantees for greedy maximization of non- submodular functions with applications. In ICML, pages 498- 507, Sydney, Australia, 2017.","title":"Guarantees for greedy maximization of nonsubmodular functions with applications","authors":"A A Bian, J M Buhmann, A Krause, S Tschiatschek","year":"2017","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chen et al., 2009] W. Chen, Y. Wang, and S. Yang. Efficient influ- ence maximization in social networks. In KDD, pages 199-208, Paris, France, 2009.","title":"Efficient influence maximization in social networks","authors":"W Chen, Y Wang, S Yang","year":"2009","venue":"KDD","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Chen et al., 2016] W. Chen, T. Lin, Z. Tan, M. Zhao, and X. Zhou. Robust influence maximization. In KDD, pages 795-804, San Francisco, CA, 2016.","title":"Robust influence maximization","authors":"W Chen, T Lin, Z Tan, M Zhao, X Zhou","year":"2016","venue":"KDD","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Das and Kempe, 2011] A. Das and D. Kempe. Submodular meets spectral: Greedy algorithms for subset selection, sparse approx- imation and dictionary selection. In ICML, pages 1057-1064, Bellevue, WA, 2011.","title":"Submodular meets spectral: Greedy algorithms for subset selection, sparse approximation and dictionary selection","authors":"A Das, D Kempe","year":"2011","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Elenberg et al., 2018] E. R. Elenberg, R. Khanna, A. G. Dimakis, and S. Negahban. Restricted strong convexity implies weak sub- modularity. The Annals of Statistics, 46(6B):3539-3568, 2018.","title":"Restricted strong convexity implies weak submodularity","authors":"E R Elenberg, R Khanna, A G Dimakis, S Negahban","year":"2018","venue":"The Annals of Statistics","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Feng et al., 2019] C. Feng, C. Qian, and K. Tang. Unsupervised feature selection by Pareto optimization. In AAAI, pages 3534- 3541, Honolulu, HI, 2019.","title":"Unsupervised feature selection by Pareto optimization","authors":"C Feng, C Qian, K Tang","year":"2019","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Friedrich and Neumann, 2015] T. Friedrich and F. Neumann. Maximizing submodular functions under matroid constraints by evolutionary algorithms. Evolutionary Computation, 23(4):543- 558, 2015.","title":"Maximizing submodular functions under matroid constraints by evolutionary algorithms","authors":"T Friedrich, F Neumann","year":"2015","venue":"Evolutionary Computation","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Friedrich et al., 2019] T. Friedrich, A. Göbel, F. Neumann, F. Quinzan, and R. Rothenberger. Greedy maximization of func- tions with bounded curvature under partition matroid constraints. In AAAI, pages 2272-2279, Honolulu, HI, 2019.","title":"Greedy maximization of functions with bounded curvature under partition matroid constraints","authors":"T Friedrich, A Göbel, F Neumann, F Quinzan, R Rothenberger","year":"2019","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Goyal et al., 2011] A. Goyal, W. Lu, and L. Lakshmanan. Sim- path: An efficient algorithm for influence maximization under the linear threshold model. In ICDM, pages 211-220, Vancou- ver, Canada, 2011.","title":"Simpath: An efficient algorithm for influence maximization under the linear threshold model","authors":"A Goyal, W Lu, L Lakshmanan","year":"2011","venue":"ICDM","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Harshaw et al., 2019] C. Harshaw, M. Feldman, J. Ward, and A. Karbasi. Submodular maximization beyond non-negativity: Guarantees, fast algorithms, and applications. In ICML, pages 2634-2643, Long Beach, CA, 2019.","title":"Submodular maximization beyond non-negativity: Guarantees, fast algorithms, and applications","authors":"C Harshaw, M Feldman, J Ward, A Karbasi","year":"2019","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Hassidim and Singer, 2017] A. Hassidim and Y. Singer. Robust guarantees of stochastic greedy algorithms. In ICML, pages 1424-1432, Sydney, Australia, 2017.","title":"Robust guarantees of stochastic greedy algorithms","authors":"A Hassidim, Y Singer","year":"2017","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[He and Kempe, 2016] X. He and D. Kempe. Robust influence maximization. In KDD, pages 885-894, San Francisco, CA, 2016.","title":"Robust influence maximization","authors":"Kempe He, X He, D Kempe","year":"2016","venue":"KDD","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Hou and Clark, 2021] Q. Hou and A. Clark. Robust maximiza- tion of correlated submodular functions under cardinality and matroid constraints. IEEE Transactions on Automatic Control, 66(12):6148-6155, 2021.","title":"Robust maximization of correlated submodular functions under cardinality and matroid constraints","authors":"Q Hou, A Clark","year":"2021","venue":"IEEE Transactions on Automatic Control","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Iyer, 2019] R. Iyer. A unified framework of robust submodular optimization. arXiv:1906.06393, 2019.","title":"A unified framework of robust submodular optimization","authors":"R Iyer","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Kalimeris et al., 2019] D. Kalimeris, G. Kaplun, and Y. Singer. Robust influence maximization for hyperparametric models. In ICML, pages 3192-3200, Long Beach, CA, 2019.","title":"Robust influence maximization for hyperparametric models","authors":"D Kalimeris, G Kaplun, Y Singer","year":"2019","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Kempe et al., 2003] D. Kempe, J. Kleinberg, and É. Tardos. Maxi- mizing the spread of influence through a social network. In KDD, pages 137-146, Washington, DC, 2003.","title":"Maximizing the spread of influence through a social network","authors":"D Kempe, J Kleinberg, É Tardos","year":"2003","venue":"KDD","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Krause et al., 2008a] A. Krause, M. H. Brendan, G. Carlos, and A. Gupta. Robust submodular observation selection. Journal of Machine Learning Research, 9:2761-2801, 2008.","title":"Robust submodular observation selection","authors":"Krause","year":"2008","venue":"Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Krause et al., 2008b] A. Krause, A. Singh, and C. Guestrin. Near- optimal sensor placements in Gaussian processes: Theory, ef- ficient algorithms and empirical studies. Journal of Machine Learning Research, 9:235-284, 2008.","title":"Nearoptimal sensor placements in Gaussian processes: Theory, efficient algorithms and empirical studies","authors":"Krause","year":"2008","venue":"Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Lin and Bilmes, 2011] H. Lin and J. Bilmes. A class of submodu- lar functions for document summarization. In ACL, pages 510- 520, Portland, OR, 2011.","title":"A class of submodular functions for document summarization","authors":"H Lin, J Bilmes","year":"2011","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Minoux, 1978] M. Minoux. Accelerated greedy algorithms for maximizing submodular set functions. Optimization Techniques, pages 234-243, 1978.","title":"Accelerated greedy algorithms for maximizing submodular set functions","authors":"M Minoux","year":"1978","venue":"Optimization Techniques","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Mirzasoleiman et al., 2015] B. Mirzasoleiman, A. Badanidiyuru, A. Karbasi, J. Vondrák, , and A. Krause. Lazier than lazy greedy. In AAAI, pages 1812-1818, Austin, TX, 2015.","title":"Lazier than lazy greedy","authors":"B Mirzasoleiman, A Badanidiyuru, A Karbasi, J Vondrák, A Krause","year":"2015","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Nemhauser and Wolsey, 1978] G. L. Nemhauser and L. A. Wolsey. Best algorithms for approximating the maximum of a submodu- lar set function. Mathematics of Operations Research, 3(3):177- 188, 1978.","title":"Best algorithms for approximating the maximum of a submodular set function","authors":"G L Nemhauser, L A Wolsey","year":"1978","venue":"Mathematics of Operations Research","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Nemhauser et al., 1978] G. L. Nemhauser, L. A. Wolsey, and M. L. Fisher. An analysis of approximations for maximizing submod- ular set functions -I. Mathematical Programming, 14(1):265- 294, 1978.","title":"An analysis of approximations for maximizing submodular set functions -I","authors":"G L Nemhauser, L A Wolsey, M L Fisher","year":"1978","venue":"Mathematical Programming","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Qian et al., 2015] C. Qian, Y. Yu, and Z.-H. Zhou. Subset selection by Pareto optimization. In NIPS, pages 1765-1773, Montreal, Canada, 2015.","title":"Subset selection by Pareto optimization","authors":"C Qian, Y Yu, Z.-H Zhou","year":"2015","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Qian et al., 2016] C. Qian, J.-C. Shi, Y. Yu, K. Tang, and Z.-H. Zhou. Parallel Pareto optimization for subset selection. In IJCAI, pages 1939-1945, New York, NY, 2016.","title":"Parallel Pareto optimization for subset selection","authors":"C Qian, J.-C Shi, Y Yu, K Tang, Z.-H Zhou","year":"2016","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2016/277"},{"position":27,"raw":"[Qian et al., 2018] C. Qian, Y. Yu, and K. Tang. Approximation guarantees of stochastic greedy algorithms for subset selection. In IJCAI, pages 1478-1484, Stockholm, Sweden, 2018.","title":"Approximation guarantees of stochastic greedy algorithms for subset selection","authors":"C Qian, Y Yu, K Tang","year":"2018","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2018/205"},{"position":28,"raw":"[Qian et al., 2019] C. Qian, Y. Yu, K. Tang, X. Yao, and Z.-H. Zhou. Maximizing submodular or monotone approximately sub- modular functions by multi-objective evolutionary algorithms. Artificial Intelligence, 275:279-294, 2019.","title":"Maximizing submodular or monotone approximately submodular functions by multi-objective evolutionary algorithms","authors":"C Qian, Y Yu, K Tang, X Yao, Z.-H Zhou","year":"2019","venue":"Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Thompson, 2022] R. Thompson. Robust subset selection. Compu- tational Statistics and Data Analysis, 169(107415):1-19, 2022.","title":"Robust subset selection","authors":"R Thompson","year":"2022","venue":"Computational Statistics and Data Analysis","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Udwani, 2018] R. Udwani. Multi-objective maximization of monotone submodular functions with cardinality constraint. In NIPS, pages 9513-9524, Montréal, Canada, 2018.","title":"Multi-objective maximization of monotone submodular functions with cardinality constraint","authors":"R Udwani","year":"2018","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Zhu et al., 2015] F. Zhu, B. Fan, X. Zhu, Y. Wang, S. Xiang, and C. Pan. 10,000+ times accelerated robust subset selection (ARSS). In AAAI, pages 3217-3223, Austin, TX, 2015.","title":"10,000+ times accelerated robust subset selection (ARSS)","authors":"F Zhu, B Fan, X Zhu, Y Wang, S Xiang, C Pan","year":"2015","venue":"AAAI","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}