{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T13:02:14Z","timestamp":1785502934510,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":49,"publisher":"ACM","license":[{"start":{"date-parts":[[2027,4,20]],"date-time":"2027-04-20T00:00:00Z","timestamp":1808179200000},"content-version":"vor","delay-in-days":365,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Science Foundation","award":["2550105"],"award-info":[{"award-number":["2550105"]}]},{"name":"National Science Foundation","award":["2550106"],"award-info":[{"award-number":["2550106"]}]},{"name":"National Science Foundation","award":["2242812"],"award-info":[{"award-number":["2242812"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770854.3780231","type":"proceedings-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T12:07:40Z","timestamp":1785499660000},"page":"2010-2019","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Heterogeneous Multi-Agent Reinforcement Learning with Attention for Cooperative and Scalable Feature Transformation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4942-9775","authenticated-orcid":false,"given":"Tao","family":"Zhe","sequence":"first","affiliation":[{"name":"University of Kansas, Lawrence, Kansas, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4759-1672","authenticated-orcid":false,"given":"Huazhen","family":"Fang","sequence":"additional","affiliation":[{"name":"Michigan State University, East Lansing, Michigan, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6053-5977","authenticated-orcid":false,"given":"Kunpeng","family":"Liu","sequence":"additional","affiliation":[{"name":"Clemson University, Clemson, South Carolina, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5462-2567","authenticated-orcid":false,"given":"Qian","family":"Lou","sequence":"additional","affiliation":[{"name":"University of Central Florida, Orlando, Florida, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6845-0361","authenticated-orcid":false,"given":"Tamzidul","family":"Hoque","sequence":"additional","affiliation":[{"name":"University of Kansas, Lawrence, Kansas, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3948-0059","authenticated-orcid":false,"given":"Dongjie","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Kansas, Lawrence, Kansas, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,20]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611978032.100"},{"key":"e_1_3_2_2_2_1","volume-title":"Representation learning: A review and new perspectives","author":"Bengio Yoshua","year":"2013","unstructured":"Yoshua Bengio, Aaron Courville, and Pascal Vincent. 2013. Representation learning: A review and new perspectives. IEEE transactions on pattern analysis and machine intelligence, Vol. 35, 8 (2013), 1798-1828."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.5555\/944919.944937"},{"key":"e_1_3_2_2_4_1","volume-title":"Random forests. Machine learning","author":"Breiman Leo","year":"2001","unstructured":"Leo Breiman. 2001. Random forests. Machine learning, Vol. 45, 1 (2001), 5-32."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2019.00017"},{"key":"e_1_3_2_2_7_1","volume-title":"Support-vector networks. Machine learning","author":"Cortes Corinna","year":"1995","unstructured":"Corinna Cortes and Vladimir Vapnik. 1995. Support-vector networks. Machine learning, Vol. 20, 3 (1995), 273-297."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1967.1053964"},{"key":"e_1_3_2_2_9_1","volume-title":"Nando De Freitas, and Shimon Whiteson.","author":"Foerster Jakob","year":"2016","unstructured":"Jakob Foerster, Ioannis Alexandros Assael, Nando De Freitas, and Shimon Whiteson. 2016. Learning to communicate with deep multi-agent reinforcement learning. Advances in neural information processing systems, Vol. 29 (2016)."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3679102"},{"key":"e_1_3_2_2_12_1","volume-title":"GPT-FT: An Efficient Automated Feature Transformation Using GPT for Sequence Reconstruction and Performance Enhancement. arXiv preprint arXiv:2508.20824","author":"Gao Yang","year":"2025","unstructured":"Yang Gao, Dongjie Wang, Scott Piersall, Ye Zhang, and Liqiang Wang. 2025. GPT-FT: An Efficient Automated Feature Transformation Using GPT for Sequence Reconstruction and Performance Enhancement. arXiv preprint arXiv:2508.20824 (2025)."},{"key":"e_1_3_2_2_13_1","unstructured":"Huifeng Guo Ruiming Tang Yunming Ye Zhenguo Li and Xiuqiang He. 2017. DeepFM: a factorization-machine based neural network for CTR prediction. arXiv preprint arXiv:1703.04247 (2017)."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1080\/00401706.1970.10488634"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-43823-4_10"},{"key":"e_1_3_2_2_16_1","unstructured":"Jeremy Howard. 2022. Kaggle Dataset Download [EB\/OL]. https:\/\/www.kaggle.com\/datasets."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3680105"},{"key":"e_1_3_2_2_18_1","volume-title":"Collaborative Multi-Agent Reinforcement Learning for Automated Feature Transformation with Graph-Driven Path Optimization. arXiv preprint arXiv:2504.17355","author":"Huang Xiaohan","year":"2025","unstructured":"Xiaohan Huang, Dongjie Wang, Zhiyuan Ning, Ziyue Qiao, Qingqing Long, Haowei Zhu, Yi Du, Min Wu, Yuanchun Zhou, and Meng Xiao. 2025. Collaborative Multi-Agent Reinforcement Learning for Automated Feature Transformation with Graph-Driven Path Optimization. arXiv preprint arXiv:2504.17355 (2025)."},{"key":"e_1_3_2_2_19_1","volume-title":"Enhancing Tabular Data Optimization with a Flexible Graph-based Reinforced Exploration Strategy. arXiv preprint arXiv:2406.07404","author":"Huang Xiaohan","year":"2024","unstructured":"Xiaohan Huang, Dongjie Wang, Zhiyuan Ning, Ziyue Qiao, Qingqing Long, Haowei Zhu, Min Wu, Yuanchun Zhou, and Meng Xiao. 2024. Enhancing Tabular Data Optimization with a Flexible Graph-based Reinforced Exploration Strategy. arXiv preprint arXiv:2406.07404 (2024)."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/DSAA.2015.7344858"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11678"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDMW.2016.0190"},{"key":"e_1_3_2_2_23_1","volume-title":"Trust region policy optimisation in multi-agent reinforcement learning. arXiv preprint arXiv:2109.11251","author":"Kuba Jakub Grudzien","year":"2021","unstructured":"Jakub Grudzien Kuba, Ruiqing Chen, Muning Wen, Ying Wen, Fanglei Sun, Jun Wang, and Yaodong Yang. 2021. Trust region policy optimisation in multi-agent reinforcement learning. arXiv preprint arXiv:2109.11251 (2021)."},{"key":"e_1_3_2_2_24_1","unstructured":"Chih-Jen Lin. 2022. LibSVM Dataset Download [EB\/OL]. https:\/\/www.csie.ntu.edu.tw\/ cjlin\/libsvmtools\/datasets\/."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3711896.3736891"},{"key":"e_1_3_2_2_26_1","volume-title":"OpenAI Pieter Abbeel, and Igor Mordatch","author":"Lowe Ryan","year":"2017","unstructured":"Ryan Lowe, Yi I Wu, Aviv Tamar, Jean Harb, OpenAI Pieter Abbeel, and Igor Mordatch. 2017. Multi-agent actor-critic for mixed cooperative-competitive environments. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_2_27_1","volume-title":"Contrasting centralized and decentralized critics in multi-agent reinforcement learning. arXiv preprint arXiv:2102.04402","author":"Lyu Xueguang","year":"2021","unstructured":"Xueguang Lyu, Yuchen Xiao, Brett Daley, and Christopher Amato. 2021. Contrasting centralized and decentralized critics in multi-agent reinforcement learning. arXiv preprint arXiv:2102.04402 (2021)."},{"key":"e_1_3_2_2_28_1","volume-title":"Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602","author":"Mnih Volodymyr","year":"2013","unstructured":"Volodymyr Mnih. 2013. Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)."},{"key":"e_1_3_2_2_29_1","unstructured":"Public. 2022. OpenML Dataset Download [EB\/OL]. https:\/\/www.openml.org."},{"key":"e_1_3_2_2_30_1","volume-title":"Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347","author":"Schulman John","year":"2017","unstructured":"John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)."},{"key":"e_1_3_2_2_31_1","volume-title":"Reinforcement learning: An introduction. A Bradford Book","author":"Sutton Richard S","year":"2018","unstructured":"Richard S Sutton. 2018. Reinforcement learning: An introduction. A Bradford Book (2018)."},{"key":"e_1_3_2_2_32_1","volume-title":"Policy gradient methods for reinforcement learning with function approximation. Advances in neural information processing systems","author":"Sutton Richard S","year":"1999","unstructured":"Richard S Sutton, David McAllester, Satinder Singh, and Yishay Mansour. 1999. Policy gradient methods for reinforcement learning with function approximation. Advances in neural information processing systems, Vol. 12 (1999)."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12293-015-0173-y"},{"key":"e_1_3_2_2_34_1","unstructured":"UCI Machine Learning Repository. 2022 [EB\/OL]. UCI Dataset Download. https:\/\/archive.ics.uci.edu\/."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"e_1_3_2_2_36_1","volume-title":"Attention is all you need. Advances in neural information processing systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539278"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1887"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1201"},{"key":"e_1_3_2_2_40_1","volume-title":"Reinforcement learning. Adaptation, learning, and optimization","author":"Wiering Marco A","year":"2012","unstructured":"Marco A Wiering and Martijn Van Otterlo. 2012. Reinforcement learning. Adaptation, learning, and optimization, Vol. 12, 3 (2012), 729."},{"key":"e_1_3_2_2_41_1","volume-title":"Traceable group-wise self-optimizing feature transformation learning: A dual optimization perspective. ACM Transactions on Knowledge Discovery from Data","author":"Xiao Meng","year":"2024","unstructured":"Meng Xiao, Dongjie Wang, Min Wu, Kunpeng Liu, Hui Xiong, Yuanchun Zhou, and Yanjie Fu. 2024. Traceable group-wise self-optimizing feature transformation learning: A dual optimization perspective. ACM Transactions on Knowledge Discovery from Data, Vol. 18, 4 (2024), 1-22."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611977653.ch87"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM58522.2023.00078"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3672015"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM58522.2023.00084"},{"key":"e_1_3_2_2_46_1","volume-title":"Sixun Dong, Dongjie Wang, Denghui Zhang, and Yanjie Fu.","author":"Ying Wangyang","year":"2025","unstructured":"Wangyang Ying, Cong Wei, Nanxu Gong, Xinyuan Wang, Haoyue Bai, Arun Vignesh Malarkkan, Sixun Dong, Dongjie Wang, Denghui Zhang, and Yanjie Fu. 2025. A survey on data-centric ai: Tabular learning from reinforcement learning and generative ai perspective. arXiv preprint arXiv:2502.08828 (2025)."},{"key":"e_1_3_2_2_47_1","volume-title":"The surprising effectiveness of ppo in cooperative multi-agent games. Advances in neural information processing systems","author":"Yu Chao","year":"2022","unstructured":"Chao Yu, Akash Velu, Eugene Vinitsky, Jiaxuan Gao, Yu Wang, Alexandre Bayen, and Yi Wu. 2022. The surprising effectiveness of ppo in cooperative multi-agent games. Advances in neural information processing systems, Vol. 35 (2022), 24611-24624."},{"key":"e_1_3_2_2_48_1","volume-title":"Forty-first International Conference on Machine Learning.","author":"Zhang Bin","year":"2024","unstructured":"Bin Zhang, Hangyu Mao, Lijuan Li, Zhiwei Xu, Dapeng Li, Rui Zhao, and Guoliang Fan. 2024. Sequential asynchronous action coordination in multi-agent systems: A stackelberg decision transformer approach. In Forty-first International Conference on Machine Learning."},{"key":"e_1_3_2_2_49_1","volume-title":"International Conference on Automated Machine Learning. PMLR, 17-1.","author":"Zhu Guanghui","year":"2022","unstructured":"Guanghui Zhu, Zhuoer Xu, Chunfeng Yuan, and Yihua Huang. 2022. DIFER: differentiable automated feature engineering. In International Conference on Automated Machine Learning. PMLR, 17-1."}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3770854.3780231","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3770854.3780231","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T12:14:51Z","timestamp":1785500091000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770854.3780231"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,20]]},"references-count":49,"alternative-id":["10.1145\/3770854.3780231","10.1145\/3770854"],"URL":"https:\/\/doi.org\/10.1145\/3770854.3780231","relation":{},"subject":[],"published":{"date-parts":[[2026,4,20]]},"assertion":[{"value":"2026-04-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}