{"type":"ScholarlyArticle","title":"Perception-Inspired Graph Convolution for Music Understanding Tasks","authors":[{"name":"Emmanouil Karystinaios","slug":"emmanouil-karystinaios","given":"Emmanouil","family":"Karystinaios","affiliation":"Institute of Computational Perception , Johannes Kepler University Linz , Austria"},{"name":"Francesco Foscarin","slug":"francesco-foscarin","given":"Francesco","family":"Foscarin","affiliation":"Institute of Computational Perception , Johannes Kepler University Linz , Austria; LIT AI Lab , Linz Institute of Technology , Austria"},{"name":"Gerhard Widmer","slug":"gerhard-widmer","given":"Gerhard","family":"Widmer","affiliation":"Institute of Computational Perception , Johannes Kepler University Linz , Austria; LIT AI Lab , Linz Institute of Technology , Austria"}],"abstract":"We propose a new graph convolutional block, called MusGConv, specifically designed for the efficient processing of musical score data and motivated by general perceptual principles. It focuses on two fundamental dimensions of music, pitch and rhythm, and considers both relative and absolute representations of these components. We evaluate our approach on four different musical understanding problems: monophonic voice separation, harmonic analysis, cadence detection, and composer identification which, in abstract terms, translate to different graph learning problems, namely, node classification, link prediction, and graph classification. Our experiments demonstrate that MusGConv improves the performance on three of the aforementioned tasks while being conceptually very simple and efficient. We interpret this as evidence that it is beneficial to include perception-informed processing of fundamental musical concepts when developing graph network applications on musical score data. All code and models are released on https://github.com/manoskary/musgconv.","doi":"10.24963/ijcai.2024/850","url":"https://ijcai.org/proceedings/2024/850","pdf":"https://ijcai.org/proceedings/2024/0850.pdf","markdown":"https://ijcai.org/proceedings/2024/850.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/850","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":"AI, Arts & Creativity","track":"AI, Arts & Creativity","number":850,"pages":{"first":7681,"last":7689},"keywords":["Methods and resources: Machine learning, deep learning, neural models, reinforcement learning","Methods and resources: Computational implementations inspired by fields such as psychology or cognitive science","Application domains: Music and sound"],"videos":[],"references":[{"position":1,"raw":"[Allegraud et al., 2019] Pierre Allegraud, Louis Bigo, Lau- rent Feisthauer, Mathieu Giraud, Richard Groult, Em- manuel Leguy, and Florence Levé. Learning sonata form structure on mozart's string quartets. Transactions of the International Society for Music Information Retrieval (TISMIR), 2(1):82-96, 2019.","title":"Learning sonata form structure on mozart's string quartets","authors":"Allegraud","year":"2019","venue":"Transactions of the International Society for Music Information Retrieval (TISMIR)","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Atzmon et al., 2018] Matan Atzmon, Haggai Maron, and Yaron Lipman. Point convolutional neural networks by extension operators. ACM Transactions on Graphics, 37(4), 2018.","title":"Point convolutional neural networks by extension operators","authors":"Matan Atzmon, Haggai Maron, Yaron Lipman","year":"2018","venue":"ACM Transactions on Graphics","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bresson and Laurent, 2017] Xavier Bresson and Thomas Laurent. Residual gated graph convnets. In Proceedings of the International Conference on Learning Representations, 2017.","title":"Xavier Bresson and Thomas Laurent. Residual gated graph convnets","authors":"Laurent Bresson","year":"2017","venue":"Proceedings of the International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Chawla et al., 2002] Nitesh V Chawla, Kevin W Bowyer, Lawrence O Hall, and W Philip Kegelmeyer. Smote: syn- thetic minority over-sampling technique. Journal of artifi- cial intelligence research, 16:321-357, 2002.","title":"Smote: synthetic minority over-sampling technique","authors":"Kevin W Nitesh V Chawla, Lawrence O Bowyer, Philip Hall, Kegelmeyer","year":"2002","venue":"Journal of artificial intelligence research","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Chen et al., 2018] Tsung-Ping Chen, Li Su, et al. Functional Harmony Recognition of Symbolic Music Data with Multi- task Recurrent Neural Networks. In Proceedings of the International Society for Music Information Retrieval Con- ference (ISMIR), 2018.","title":"Functional Harmony Recognition of Symbolic Music Data with Multitask Recurrent Neural Networks","authors":"Chen","year":"2018","venue":"Proceedings of the International Society for Music Information Retrieval Conference (ISMIR)","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Del Barrio et al., 2018] Eustasio Del Barrio, Juan A Cuesta- Albertos, and Carlos Matrán. An optimal transportation approach for assessing almost stochastic order. In The Math- ematics of the Uncertain, pages 33-44. Springer, 2018.","title":"Eustasio Del Barrio, Juan A Cuesta-Albertos, and Carlos Matrán. An optimal transportation approach for assessing almost stochastic order","authors":"Del Barrio","year":"2018","venue":"The Mathematics of the Uncertain","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Deutsch, 2013] Diana Deutsch. Psychology of music. Else- vier, 2013.","title":"Psychology of music","authors":"Diana Deutsch","year":"2013","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Di Giorgi et al., 2021] Bruno Di Giorgi, Matthias Mauch, and Mark Levy. Downbeat tracking with tempo-invariant convolutional neural networks. In Proceedings of the Inter- national Society for Music Information Retrieval Confer- ence (ISMIR), 2021.","title":"Downbeat tracking with tempo-invariant convolutional neural networks","authors":"Bruno Di, Giorgi, Matthias Mauch, Mark Levy","year":"2021","venue":"Proceedings of the International Society for Music Information Retrieval Conference (ISMIR)","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Duane and Pardo, 2009] Ben Duane and Bryan Pardo. Streaming from midi using constraint satisfaction optimiza- tion and sequence alignment. In Proceedings of the Inter- national Computer Music Conference (ICMC), 2009.","title":"Streaming from midi using constraint satisfaction optimization and sequence alignment","authors":"Duane, Pardo ; ] Ben, Duane, Bryan Pardo","year":"2009","venue":"Proceedings of the International Computer Music Conference (ICMC)","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Elowsson and Friberg, 2019] Anders Elowsson and Anders Friberg. Modeling Music Modality with a Key-Class In- variant Pitch Chroma CNN. In Proceedings of the Interna- tional Society for Music Information Retrieval Conference (ISMIR), 2019.","title":"Modeling Music Modality with a Key-Class Invariant Pitch Chroma CNN","authors":"Friberg Elowsson, Anders Elowsson, Anders Friberg","year":"2019","venue":"Proceedings of the International Society for Music Information Retrieval Conference (ISMIR)","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Foscarin et al., 2021] Francesco Foscarin, Nicolas Audebert, and Raphaël Fournier-S'Niehotta. Pkspell: Data-driven pitch spelling and key signature estimation. In Proceedings of the International Society for Music Information Retrieval Conference (ISMIR), 2021.","title":"Pkspell: Data-driven pitch spelling and key signature estimation","authors":"Francesco Foscarin, Nicolas Audebert, Raphaël Fournier, -S' Niehotta","year":"2021","venue":"Proceedings of the International Society for Music Information Retrieval Conference (ISMIR)","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Foscarin et al., 2022] Francesco Foscarin, Emmanouil Karystinaios, Silvan David Peter, Carlos Cancino-Chacón, Maarten Grachten, and Gerhard Widmer. The match file format: Encoding alignments between scores and performances. In Proceedings of the Music Encoding Conference (MEC), 2022.","title":"The match file format: Encoding alignments between scores and performances","authors":"Francesco Foscarin, Emmanouil Karystinaios, Silvan David Peter, Carlos Cancino-Chacón, Maarten Grachten, Gerhard Widmer","year":"2022","venue":"Proceedings of the Music Encoding Conference (MEC)","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Fradet et al., 2021] Nathan Fradet, Jean-Pierre Briot, Fabien Chhel, Amal El Fallah Seghrouchni, and Nicolas Gutowski. MidiTok: A python package for MIDI file tokenization. In Late-Breaking Demo Session of the International Society for Music Information Retrieval Conference (ISMIR), 2021.","title":"MidiTok: A python package for MIDI file tokenization","authors":"Nathan Fradet, Jean-Pierre Briot, Fabien Chhel, Amal El Fallah, Seghrouchni, Nicolas Gutowski","year":"2021","venue":"Late-Breaking Demo Session of the International Society for Music Information Retrieval Conference (ISMIR)","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Giraud et al., 2015] Mathieu Giraud, Richard Groult, Em- manuel Leguy, and Florence Levé. Computational Fugue Analysis. Computer Music Journal, 39(2):77-96, 2015.","title":"Emmanuel Leguy, and Florence Levé","authors":"Giraud Mathieu, Richard Groult","year":"2015","venue":"Computer Music Journal","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Hamilton et al., 2017] Will Hamilton, Zhitao Ying, and Jure Leskovec. Inductive representation learning on large graphs. Advances in Neural Information Processing Systems, 30, 2017.","title":"Inductive representation learning on large graphs","authors":"Hamilton","year":"2017","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Harte, 2010] Christopher Harte. Towards automatic extrac- tion of harmony information from music signals. PhD thesis, Queen Mary, University of London, 2010.","title":"Towards automatic extraction of harmony information from music signals","authors":"Christopher Harte","year":"2010","venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Hentschel et al., 2021] Johannes Hentschel, Markus Neuwirth, and Martin Rohrmeier. The annotated mozart sonatas: Score, harmony, and cadence. Transactions of the International Society for Music Information Retrieval (TISMIR), 4(1), May 2021.","title":"The annotated mozart sonatas: Score, harmony, and cadence","authors":"Hentschel","year":"2021","venue":"Transactions of the International Society for Music Information Retrieval (TISMIR)","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Hsiao and Su, 2021] Yo-Wei Hsiao and Li Su. Learning note- to-note affinity for voice segregation and melody line iden- tification of symbolic music data. In Proceedings of the International Society for Music Information Retrieval Con- ference (ISMIR), pages 285-292, 2021.","title":"Learning noteto-note affinity for voice segregation and melody line identification of symbolic music data","authors":"Su ; ] Yo-Wei Hsiao, Li Hsiao, Su","year":"2021","venue":"Proceedings of the International Society for Music Information Retrieval Conference (ISMIR)","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Hu et al., 2019] Weihua Hu, Bowen Liu, Joseph Gomes, Marinka Zitnik, Percy Liang, Vijay Pande, and Jure Leskovec. Strategies for pre-training graph neural networks. In International Conference on Learning Representations (ICLR), 2019.","title":"Strategies for pre-training graph neural networks","authors":"Weihua Hu, Bowen Liu, Joseph Gomes, Marinka Zitnik, Percy Liang, Vijay Pande, Jure Leskovec","year":"2019","venue":"International Conference on Learning Representations (ICLR)","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Jeong et al., 2019] Dasaem Jeong, Taegyun Kwon, Yoojin Kim, and Juhan Nam. Graph neural network for music score data and modeling expressive piano performance. In Proceedings of the International Conference on Machine Learning (ICML), pages 3060-3070. PMLR, 2019.","title":"Graph neural network for music score data and modeling expressive piano performance","authors":"Jeong","year":"2019","venue":"Proceedings of the International Conference on Machine Learning (ICML)","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Karystinaios and Widmer, 2022] Emmanouil Karystinaios and Gerhard Widmer. Cadence detection in symbolic clas- sical music using graph neural networks. In Proceedings of the International Society for Music Information Retrieval Conference (ISMIR), 2022.","title":"Cadence detection in symbolic classical music using graph neural networks","authors":"Widmer Karystinaios, Emmanouil Karystinaios, Gerhard Widmer","year":"2022","venue":"Proceedings of the International Society for Music Information Retrieval Conference (ISMIR)","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Karystinaios and Widmer, 2023] Emmanouil Karystinaios and Gerhard Widmer. Roman Numeral Analysis with Graph Neural Networks: Onset-wise Predictions from Note- wise Features. In Proceedings of the International Society for Music Information Retrieval Conference (ISMIR), 2023.","title":"Roman Numeral Analysis with Graph Neural Networks: Onset-wise Predictions from Notewise Features","authors":"Widmer Karystinaios, Emmanouil Karystinaios, Gerhard Widmer","year":"2023","venue":"Proceedings of the International Society for Music Information Retrieval Conference (ISMIR)","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Karystinaios et al., 2023] Emmanouil Karystinaios, Francesco Foscarin, and Gerhard Widmer. Musical Voice Separation as Link Prediction: Modeling a Musical Perception Task as a Multi-Trajectory Tracking Problem. In Proceedings of the Joint Conference on Atrificial Intelligence (IJCAI), 2023.","title":"Musical Voice Separation as Link Prediction: Modeling a Musical Perception Task as a Multi-Trajectory Tracking Problem","authors":"Emmanouil Karystinaios, Francesco Foscarin, Gerhard Widmer","year":"2023","venue":"Proceedings of the Joint Conference on Atrificial Intelligence (IJCAI)","doi":null,"url":null,"internal_url":"/proceedings/2023/430"},{"position":24,"raw":"[Kermarec et al., 2022] Mathieu Kermarec, Louis Bigo, and Mikaela Keller. Improving tokenization expressiveness with pitch intervals. In Late-Breaking Demo Session of the International Society for Music Information Retrieval Conference (ISMIR), 2022.","title":"Improving tokenization expressiveness with pitch intervals","authors":"Mathieu Kermarec, Louis Bigo, Mikaela Keller","year":"2022","venue":"Late-Breaking Demo Session of the International Society for Music Information Retrieval Conference (ISMIR)","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Klapuri and Davy, 2006] Anssi Klapuri and Manuel Davy. Signal Processing Methods for Music Transcription. Springer, 2006.","title":"Signal Processing Methods for Music Transcription","authors":"Anssi Klapuri, Manuel Davy","year":"2006","venue":null,"doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Lattner et al., 2018] Stefan Lattner, Maarten Grachten, and Gerhard Widmer. Learning Transposition-Invariant Interval Features from Symbolic Music and Audio. In Proceedings of the International Society for Music Information Retrieval Conference (ISMIR), 2018.","title":"Learning Transposition-Invariant Interval Features from Symbolic Music and Audio","authors":"Stefan Lattner, Maarten Grachten, Gerhard Widmer","year":"2018","venue":"Proceedings of the International Society for Music Information Retrieval Conference (ISMIR)","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Lattner et al., 2019] Stefan Lattner, Monika Dörfler, and An- dreas Arzt. Learning Complex Basis Functions for Invariant Representations of Audio. In Proceedings of the Interna- tional Society for Music Information Retrieval Conference (ISMIR), 2019.","title":"Learning Complex Basis Functions for Invariant Representations of Audio","authors":"Stefan Lattner, Monika Dörfler, Andreas Arzt","year":"2019","venue":"Proceedings of the International Society for Music Information Retrieval Conference (ISMIR)","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[López et al., 2021] Néstor Nápoles López, Mark Gotham, and Ichiro Fujinaga. AugmentedNet: A Roman Numeral Analysis Network with Synthetic Training Examples and Additional Tonal Tasks. In Proceedings of the Interna- tional Society for Music Information Retrieval Conference (ISMIR), 2021.","title":"AugmentedNet: A Roman Numeral Analysis Network with Synthetic Training Examples and Additional Tonal Tasks","authors":"López","year":"2021","venue":"Proceedings of the International Society for Music Information Retrieval Conference (ISMIR)","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[McLeod and Rohrmeier, 2021] Andrew Philip McLeod and Martin Alois Rohrmeier. A modular system for the har- monic analysis of musical scores using a large vocabulary. In Proceedings of the International Society for Music Infor- mation Retrieval Conference (ISMIR), 2021.","title":"A modular system for the harmonic analysis of musical scores using a large vocabulary","authors":"Andrew Philip, Mcleod, Martin Alois, Rohrmeier","year":"2021","venue":"Proceedings of the International Society for Music Information Retrieval Conference (ISMIR)","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Micchi et al., 2020] Gianluca Micchi, Mark Gotham, and Mathieu Giraud. Not all roads lead to Rome: Pitch repre- sentation and model architecture for automatic harmonic analysis. Transactions of the International Society for Mu- sic Information Retrieval (TISMIR), 3(1):42-54, 2020.","title":"Not all roads lead to Rome: Pitch representation and model architecture for automatic harmonic analysis","authors":"Gianluca Micchi, Mark Gotham, Mathieu Giraud","year":"2020","venue":"Transactions of the International Society for Music Information Retrieval (TISMIR)","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Nakamura et al., 2016] Eita Nakamura, Masatoshi Hamanaka, Keiji Hirata, and Kazuyoshi Yoshii. Tree- structured probabilistic model of monophonic written music based on the generative theory of tonal music. In Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 276-280. IEEE, 2016.","title":"Treestructured probabilistic model of monophonic written music based on the generative theory of tonal music","authors":"Eita Nakamura, Masatoshi Hamanaka, Keiji Hirata, Kazuyoshi Yoshii","year":"2016","venue":"Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP)","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Pearce, 2005] Marcus Pearce. The Construction and Evalu- ation of Statistical Models of Melodic Structure in Music Perception and Composition. PhD thesis, City University of London, UK, 2005.","title":"The Construction and Evaluation of Statistical Models of Melodic Structure in Music Perception and Composition","authors":"Marcus Pearce","year":"2005","venue":null,"doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Pearce, 2018] Marcus T. Pearce. Statistical learning and probabilistic prediction in music cognition: Mechanisms of stylistic enculturation. Annals of the New York Academy of Sciences, 1423(1):378-395, 2018.","title":"Statistical learning and probabilistic prediction in music cognition: Mechanisms of stylistic enculturation","authors":"Marcus T Pearce","year":"2018","venue":"Annals of the New York Academy of Sciences","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Satorras et al., 2021] Victor Garcia Satorras, Emiel Hooge- boom, and Max Welling. E(n) equivariant graph neural networks. In Proceedings of the International Conference on Machine Learning (ICML), 2021.","title":"equivariant graph neural networks","authors":"Victor Garcia Satorras, Emiel Hoogeboom, Max Welling E","year":"2021","venue":"Proceedings of the International Conference on Machine Learning (ICML)","doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Schlichtkrull et al., 2018] Michael Sejr Schlichtkrull, Thomas N. Kipf, Peter Bloem, Rianne van den Berg, Ivan Titov, and Max Welling. Modeling relational data with graph convolutional networks. In Proceedings of the Semantic Web International Conference, ESWC, volume 10843 of Lecture Notes in Computer Science, pages 593-607. Springer, 2018.","title":"Modeling relational data with graph convolutional networks","authors":"Schlichtkrull","year":"2018","venue":"Proceedings of the Semantic Web International Conference, ESWC","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Sears et al., 2017] David RW Sears, Andreas Arzt, Harald Frostel, Reinhard Sonnleitner, and Gerhard Widmer. Mod- eling harmony with skip-grams. In Proceedings of the International Society for Music Information Retrieval Con- ference (ISMIR), 2017.","title":"Modeling harmony with skip-grams","authors":"R W David, Andreas Sears, Harald Arzt, Reinhard Frostel, Gerhard Sonnleitner, Widmer","year":"2017","venue":"Proceedings of the International Society for Music Information Retrieval Conference (ISMIR)","doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Wang et al., 2019a] Yue Wang, Yongbin Sun, Ziwei Liu, Sanjay E. Sarma, Michael M. Bronstein, and Justin M. Solomon. Dynamic graph CNN for learning on point clouds. ACM Transactions on Graphics, 38(5):146:1-146:12, 2019.","title":"Dynamic graph CNN for learning on point clouds","authors":"Wang","year":"2019","venue":"ACM Transactions on Graphics","doi":null,"url":null,"internal_url":null},{"position":38,"raw":"[Wang et al., 2019b] Yue Wang, Yongbin Sun, Ziwei Liu, Sanjay E Sarma, Michael M Bronstein, and Justin M Solomon. Dynamic graph cnn for learning on point clouds. ACM Transactions on Graphics (tog), 38(5):1-12, 2019.","title":"Dynamic graph cnn for learning on point clouds","authors":"Wang","year":"2019","venue":"ACM Transactions on Graphics (tog)","doi":null,"url":null,"internal_url":null},{"position":39,"raw":"[Wu et al., 2021] Zonghan Wu, Shirui Pan, Fengwen Chen, Guodong Long, Chengqi Zhang, and Philip S. Yu. A comprehensive survey on graph neural networks. IEEE Transactions on Neural Networks and Learning Systems, 32(1):4-24, 2021.","title":"A comprehensive survey on graph neural networks","authors":"Wu","year":"2021","venue":"IEEE Transactions on Neural Networks and Learning Systems","doi":null,"url":null,"internal_url":null},{"position":40,"raw":"[Zhang et al., 2023] Huan Zhang, Emmanouil Karystinaios, Carlos Cancino-Chacón, Simon Dixon, and Gerhard Wid- mer. Symbolic music representations for classification tasks: A systematic evaluation. In Proceedings of the Inter- national Society for Music Information Retrieval Confer- ence (ISMIR), 2023.","title":"Symbolic music representations for classification tasks: A systematic evaluation","authors":"Huan Zhang, Emmanouil Karystinaios, Carlos Cancino-Chacón, Simon Dixon, Gerhard Widmer","year":"2023","venue":"Proceedings of the International Society for Music Information Retrieval Conference (ISMIR)","doi":null,"url":null,"internal_url":null},{"position":41,"raw":"[Zou et al., 2019] Difan Zou, Ziniu Hu, Yewen Wang, Song Jiang, Yizhou Sun, and Quanquan Gu. Layer-dependent importance sampling for training deep and large graph convolutional networks. Advances in neural information processing systems, 32, 2019.","title":"Layer-dependent importance sampling for training deep and large graph convolutional networks","authors":"Zou","year":"2019","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}