{"type":"ScholarlyArticle","title":"Table2Graph: Transforming Tabular Data to Unified Weighted Graph","authors":[{"name":"Kaixiong Zhou","slug":"kaixiong-zhou","given":"Kaixiong","family":"Zhou","affiliation":"Department of Computer Science , Rice University"},{"name":"Zirui Liu","slug":"zirui-liu","given":"Zirui","family":"Liu","affiliation":"Department of Computer Science , Rice University"},{"name":"Rui Chen","slug":"rui-chen","given":"Rui","family":"Chen","affiliation":"Samsung Research America"},{"name":"Li Li","slug":"li-li","given":"Li","family":"Li","affiliation":"Samsung Research America"},{"name":"Soo-Hyun Choi","slug":"soo-hyun-choi","given":"Soo-Hyun","family":"Choi","affiliation":"Samsung Electronics"},{"name":"Xia Hu","slug":"xia-hu","given":"Xia","family":"Hu","affiliation":"Department of Computer Science , Rice University"}],"abstract":"Learning useful interactions between input features is  crucial for tabular data modeling. Recent efforts start to explicitly model the feature interactions with  graph, where each feature is treated as an individual node. However, the existing graph construction methods either heuristically formulate a fixed feature-interaction graph based on specific domain knowledge, or simply apply attention function to compute the pairwise feature similarities for each sample. While the fixed graph may be sub-optimal to downstream tasks, the sample-wise graph construction is time-consuming during model training and inference. To tackle these issues, we propose a framework named Table2Graph to transform the feature interaction modeling to learning a unified graph. Represented as a probability adjacency matrix, the unified graph learns to model the key feature interactions shared by the diverse samples in the tabular data. To well optimize the unified graph, we employ the reinforcement learning policy to capture the key feature interactions stably. A sparsity constraint is also proposed to regularize the learned graph from being overly-sparse/smooth. The experimental results in a variety of real-world applications demonstrate the effectiveness and efficiency of our Table2Graph, in terms of the prediction accuracy and feature interaction detection.","doi":"10.24963/ijcai.2022/336","url":"https://ijcai.org/proceedings/2022/336","pdf":"https://ijcai.org/proceedings/2022/0336.pdf","markdown":"https://ijcai.org/proceedings/2022/336.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/336","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":"Data Mining","track":"Main Track","number":336,"pages":{"first":2420,"last":2426},"keywords":["Machine Learning: Sequence and Graph Learning","Data Mining: Mining Graphs","Data Mining: Information Retrieval","Data Mining: Recommender Systems"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38986819","length_sec":76,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38984962","length_sec":316,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Cai et al., 2017] Han Cai, Kan Ren, Weinan Zhang, Klean- this Malialis, Jun Wang, Yong Yu, and Defeng Guo. Real- time bidding by reinforcement learning in display advertis- ing. In Proceedings of the Tenth ACM International Con- ference on WSDM, pages 661-670, 2017.","title":"Realtime bidding by reinforcement learning in display advertising","authors":"Han Cai, Kan Ren, Weinan Zhang, Kleanthis Malialis, Jun Wang, Yong Yu, Defeng Guo","year":"2017","venue":"Proceedings of the Tenth ACM International Conference on WSDM","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Chen et al., 2022] Tianlong Chen, Kaixiong Zhou, Keyu Duan, Wenqing Zheng, Peihao Wang, Xia Hu, and Zhangyang Wang. Bag of tricks for training deeper graph neural networks: A comprehensive benchmark study. IEEE TPAMI, 2022.","title":"Bag of tricks for training deeper graph neural networks: A comprehensive benchmark study","authors":"Tianlong Chen, Kaixiong Zhou, Keyu Duan, Wenqing Zheng, Peihao Wang, Xia Hu, Zhangyang Wang","year":"2022","venue":"IEEE TPAMI","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Dal Pozzolo et al., 2015] Andrea Dal Pozzolo, Olivier Cae- len, Reid A Johnson, and Gianluca Bontempi. Calibrating probability with undersampling for unbalanced classifica- tion. In 2015 IEEE Symposium Series on Computational Intelligence, pages 159-166, 2015.","title":"Calibrating probability with undersampling for unbalanced classification","authors":"Andrea Dal Pozzolo, Olivier Caelen, Reid A Johnson, Gianluca Bontempi","year":"2015","venue":"IEEE Symposium Series on Computational Intelligence","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Elsken et al., 2019] Thomas Elsken, Jan Hendrik Metzen, Frank Hutter, et al. Neural architecture search: A survey. J. Mach. Learn. Res., 20(55):1-21, 2019.","title":"Neural architecture search: A survey","authors":"Thomas Elsken, Jan Hendrik Metzen, Frank Hutter","year":"2019","venue":"J. Mach. Learn. Res","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Friedman et al., 2008] Jerome H Friedman, Bogdan E Popescu, et al. Predictive learning via rule ensembles. An- nals of Applied Statistics, 2(3):916-954, 2008.","title":"Predictive learning via rule ensembles","authors":"Bogdan E Jerome H Friedman, Popescu","year":"2008","venue":"Annals of Applied Statistics","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Guo et al., 2017] Huifeng Guo, Ruiming Tang, Yunming Ye, Zhenguo Li, and Xiuqiang He. Deepfm: a factorization-machine based neural network for ctr predic- tion. IJCAI, 2017.","title":"Deepfm: a factorization-machine based neural network for ctr prediction","authors":"Guo","year":"2017","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2017/239"},{"position":7,"raw":"[Hamilton et al., 2017] Will Hamilton, Zhitao Ying, and Jure Leskovec. Inductive representation learning on large graphs. In NeuIPS, pages 1024-1034, 2017.","title":"Inductive representation learning on large graphs","authors":"Hamilton","year":"2017","venue":"NeuIPS","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[He et al., 2017] Xiangnan He, Lizi Liao, Hanwang Zhang, Liqiang Nie, Xia Hu, and Tat-Seng Chua. Neural collab- orative filtering. In Proceedings of the 26th Web Confer- ence, pages 173-182, 2017.","title":"Neural collaborative filtering","authors":"He","year":"2017","venue":"Proceedings of the 26th Web Conference","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[He et al., 2018] Xiangnan He, Zhankui He, Jingkuan Song, Zhenguang Liu, Yu-Gang Jiang, and Tat-Seng Chua. Nais: Neural attentive item similarity model for recommenda- tion. IEEE TKDE, 30(12), 2018.","title":"Nais: Neural attentive item similarity model for recommendation","authors":"He","year":"2018","venue":"IEEE TKDE","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Jaafra et al., 2019] Yesmina Jaafra, Jean Luc Laurent, Aline Deruyver, and Mohamed Saber Naceur. Reinforcement learning for neural architecture search: A review. Image and Vision Computing, 89:57-66, 2019.","title":"Reinforcement learning for neural architecture search: A review","authors":"Jaafra","year":"2019","venue":"Image and Vision Computing","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Kabbur et al., 2013] Santosh Kabbur, Xia Ning, and George Karypis. Fism: factored item similarity models for top-n recommender systems. In Proceedings of the 19th ACM SIGKDD, pages 659-667, 2013.","title":"Fism: factored item similarity models for top-n recommender systems","authors":"Santosh Kabbur, Xia Ning, George Karypis","year":"2013","venue":"Proceedings of the 19th ACM SIGKDD","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Ke et al., 2018] Guolin Ke, Jia Zhang, Zhenhui Xu, Jiang Bian, and Tie-Yan Liu. Tabnn: A uni- versal neural network solution for tabular data. https://openreview.net/forum?id=r1eJssCqY7, 2018.","title":"Tabnn: A universal neural network solution for tabular data","authors":"Guolin Ke, Jia Zhang, Zhenhui Xu, Jiang Bian, Tie-Yan Liu","year":"2018","venue":null,"doi":null,"url":"https://openreview.net/forum?id=r1eJssCqY7","internal_url":null},{"position":13,"raw":"[Kipf and Welling, 2016] Thomas N Kipf and Max Welling. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907, 2016.","title":"Semi-supervised classification with graph convolutional networks","authors":"N Thomas, Max Kipf, Welling","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Li et al., 2019] Zekun Li, Zeyu Cui, Shu Wu, Xiaoyu Zhang, and Liang Wang. Fi-gnn: Modeling feature in- teractions via graph neural networks for ctr prediction. In Proceedings of the 28th CIKM, pages 539-548, 2019.","title":"Fi-gnn: Modeling feature interactions via graph neural networks for ctr prediction","authors":"Li","year":"2019","venue":"Proceedings of the 28th CIKM","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Lian et al., 2018] Jianxun Lian, Xiaohuan Zhou, Fuzheng Zhang, Zhongxia Chen, Xing Xie, and Guangzhong Sun. xdeepfm: Combining explicit and implicit feature interac- tions for recommender systems. In Proceedings of the 24th ACM SIGKDD, pages 1754-1763, 2018.","title":"xdeepfm: Combining explicit and implicit feature interactions for recommender systems","authors":"Lian","year":"2018","venue":"Proceedings of the 24th ACM SIGKDD","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Liu et al., 2020] Zirui Liu, Qingquan Song, Kaixiong Zhou, Ting-Hsiang Wang, Ying Shan, and Xia Hu. Detecting interactions from neural networks via topological analysis. NeurIPS, 33, 2020.","title":"Detecting interactions from neural networks via topological analysis","authors":"Liu","year":"2020","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"Parra et al., ] Denis Parra, Alexandros Karatzoglou, Xavier Amatriain, and Idil Yavuz. Implicit feedback recommen- dation via implicit-to-explicit ordinal logistic regression mapping. Proceedings of the CARS-2011.","title":"Implicit feedback recommendation via implicit-to-explicit ordinal logistic regression mapping","authors":"Parra","year":null,"venue":"Proceedings of the CARS-2011","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Rendle, 2010] Steffen Rendle. Factorization machines. In 2010 IEEE ICDM, pages 995-1000. IEEE, 2010.","title":"Factorization machines","authors":"Steffen Rendle","year":"2010","venue":"IEEE ICDM","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Seo et al., 2017] Sungyong Seo, Jing Huang, Hao Yang, and Yan Liu. Interpretable convolutional neural networks with dual local and global attention for review rating pre- diction. In Proceedings of the eleventh ACM conference on recommender systems, 2017.","title":"Interpretable convolutional neural networks with dual local and global attention for review rating prediction","authors":"Seo","year":"2017","venue":"Proceedings of the eleventh ACM conference on recommender systems","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Shan et al., 2016] Ying Shan, T Ryan Hoens, Jian Jiao, Hai- jing Wang, Dong Yu, and JC Mao. Deep crossing: Web- scale modeling without manually crafted combinatorial features. In Proceedings of the 22nd ACM SIGKDD, pages 255-262, 2016.","title":"Deep crossing: Webscale modeling without manually crafted combinatorial features","authors":"Ying Shan, Ryan Hoens, Jian Jiao, Haijing Wang, Dong Yu, J C Mao","year":"2016","venue":"Proceedings of the 22nd ACM SIGKDD","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Shaw et al., 2018] Peter Shaw, Jakob Uszkoreit, and Ashish Vaswani. Self-attention with relative position representa- tions. arXiv preprint arXiv:1803.02155, 2018.","title":"Self-attention with relative position representations","authors":"Peter Shaw, Jakob Uszkoreit, Ashish Vaswani","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Song et al., 2019] Weiping Song, Chence Shi, Zhiping Xiao, Zhijian Duan, Yewen Xu, Ming Zhang, and Jian Tang. Autoint: Automatic feature interaction learning via self-attentive neural networks. In Proceedings of the 28th ACM CIKM, pages 1161-1170, 2019.","title":"Autoint: Automatic feature interaction learning via self-attentive neural networks","authors":"Weiping Song, Chence Shi, Zhiping Xiao, Zhijian Duan, Yewen Xu, Ming Zhang, Jian Tang","year":"2019","venue":"Proceedings of the 28th ACM CIKM","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Sorokina et al., 2008] Daria Sorokina, Rich Caruana, Mirek Riedewald, and Daniel Fink. Detecting statistical interac- tions with additive groves of trees. In Proceedings of the 25th ICML, pages 1000-1007, 2008.","title":"Detecting statistical interactions with additive groves of trees","authors":"Daria Sorokina, Rich Caruana, Mirek Riedewald, Daniel Fink","year":"2008","venue":"Proceedings of the 25th ICML","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Su and Khoshgoftaar, 2009] Xiaoyuan Su and Taghi M Khoshgoftaar. A survey of collaborative filtering tech- niques. Advances in artificial intelligence, 2009, 2009.","title":"A survey of collaborative filtering techniques","authors":"Xiaoyuan Su, M Taghi, Khoshgoftaar","year":"2009","venue":"Advances in artificial intelligence","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Sutton et al., 1999] Richard S Sutton, David A McAllester, Satinder P Singh, Yishay Mansour, et al. Policy gradient methods for reinforcement learning with function approx- imation. In NIPS. Citeseer, 1999.","title":"Policy gradient methods for reinforcement learning with function approximation","authors":"David A Richard S Sutton, Mcallester, P Satinder, Yishay Singh, Mansour","year":"1999","venue":"NIPS. Citeseer","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Wang et al., 2020] Shoujin Wang, Liang Hu, Yan Wang, Xi- angnan He, Quan Z Sheng, Mehmet Orgun, Longbing Cao, Nan Wang, Francesco Ricci, and Philip S Yu. Graph learning approaches to recommender systems: A review. arXiv, 2020.","title":"Graph learning approaches to recommender systems: A review","authors":"Shoujin Wang, Liang Hu, Yan Wang, Xiangnan He, Z Quan, Mehmet Sheng, Longbing Orgun, Nan Cao, Francesco Wang, Philip S Ricci, Yu","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Wang et al., 2021] Ruoxi Wang, Rakesh Shivanna, Derek Cheng, Sagar Jain, Dong Lin, Lichan Hong, and Ed Chi. Dcn v2: Improved deep & cross network and practical lessons for web-scale learning to rank systems. In Pro- ceedings of the Web Conference, pages 1785-1797, 2021.","title":"Dcn v2: Improved deep & cross network and practical lessons for web-scale learning to rank systems","authors":"Wang","year":"2021","venue":"Proceedings of the Web Conference","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Xiao et al., 2017] Jun Xiao, Hao Ye, Xiangnan He, Han- wang Zhang, Fei Wu, and Tat-Seng Chua. Atten- tional factorization machines: Learning the weight of fea- ture interactions via attention networks. arXiv preprint arXiv:1708.04617, 2017.","title":"Attentional factorization machines: Learning the weight of feature interactions via attention networks","authors":"Jun Xiao, Xiangnan Hao Ye, Hanwang He, Fei Zhang, Tat-Seng Wu, Chua","year":"2017","venue":null,"doi":null,"url":null,"internal_url":"/proceedings/2017/435"},{"position":29,"raw":"[Zhou et al., 2019] Kaixiong Zhou, Qingquan Song, Xiao Huang, and Xia Hu. Auto-gnn: Neural architecture search of graph neural networks. arXiv:1909.03184, 2019.","title":"Auto-gnn: Neural architecture search of graph neural networks","authors":"Kaixiong Zhou, Qingquan Song, Xiao Huang, Xia Hu","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Zhou et al., 2020] Kaixiong Zhou, Xiao Huang, Yuening Li, Daochen Zha, Rui Chen, and Xia Hu. Towards deeper graph neural networks with differentiable group normal- ization. NeurIPS, 33:4917-4928, 2020.","title":"Towards deeper graph neural networks with differentiable group normalization","authors":"Kaixiong Zhou, Xiao Huang, Yuening Li, Daochen Zha, Rui Chen, Xia Hu","year":"2020","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Zhou et al., 2021a] Kaixiong Zhou, Xiao Huang, Daochen Zha, Rui Chen, Li Li, Soo-Hyun Choi, and Xia Hu. Dirich- let energy constrained learning for deep graph neural net- works. NeurIPS, 34, 2021.","title":"Dirichlet energy constrained learning for deep graph neural networks","authors":"Zhou","year":"2021","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Zhou et al., 2021b] Kaixiong Zhou, Qingquan Song, Xiao Huang, Daochen Zha, Na Zou, and Xia Hu. Multi-channel graph neural networks. In Proceedings of the Twenty-Ninth International Conference on International Joint Confer- ences on Artificial Intelligence, pages 1352-1358, 2021.","title":"Multi-channel graph neural networks","authors":"Zhou","year":"2021","venue":"Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2020/188"},{"position":33,"raw":"[Zoph and Le, 2016] Barret Zoph and Quoc V Le. Neural architecture search with reinforcement learning. arXiv preprint arXiv:1611.01578, 2016.","title":"Neural architecture search with reinforcement learning","authors":"Le Zoph","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}