{"type":"ScholarlyArticle","title":"Remote Sensing for Water Quality: A Multi-Task, Metadata-Driven Hypernetwork Approach","authors":[{"name":"Olivier Graffeuille","slug":"olivier-graffeuille","given":"Olivier","family":"Graffeuille","affiliation":"School of Computer Science , The University of Auckland"},{"name":"Yun Sing Koh","slug":"yun-sing-koh","given":"Yun Sing","family":"Koh","affiliation":"School of Computer Science , The University of Auckland"},{"name":"Jörg Wicker","slug":"jorg-wicker","given":"Jörg","family":"Wicker","affiliation":"School of Computer Science , The University of Auckland"},{"name":"Moritz Lehmann","slug":"moritz-lehmann","given":"Moritz","family":"Lehmann","affiliation":"Xerra Earth Observation Institute , The University of Waikato"}],"abstract":"Inland water quality monitoring is vital for clean water access and aquatic ecosystem management. Remote sensing machine learning models enable large-scale observations, but are difficult to train due to data scarcity and variability across many lakes. Multi-task learning approaches enable learning of lake differences by learning multiple lake functions simultaneously. However, they suffer from a trade-off between parameter efficiency and the ability to model task differences flexibly, and struggle to model many diverse lakes with few samples per task. We propose Multi-Task Hypernetworks, a novel multi-task learning architecture which circumvents this trade-off using a shared hypernetwork to generate different network weights for each task from small task-specific embeddings. Our approach stands out from existing works by providing the added capacity to leverage task-level metadata, such as lake depth and temperature, explicitly. We show empirically that Multi-Task Hypernetworks outperform existing multi-task learning architectures for water quality remote sensing and other tabular data problems, and leverages metadata more effectively than existing methods.","doi":"10.24963/ijcai.2024/806","url":"https://ijcai.org/proceedings/2024/806","pdf":"https://ijcai.org/proceedings/2024/0806.pdf","markdown":"https://ijcai.org/proceedings/2024/806.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/806","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 for Good","track":"AI for Good","number":806,"pages":{"first":7287,"last":7295},"keywords":["Machine Learning: General","Multidisciplinary Topics and Applications: General"],"videos":[],"references":[{"position":1,"raw":"[Bhattacharjee et al., 2022] Deblina Bhattacharjee, Tong Zhang, Sabine Süsstrunk, and Mathieu Salzmann. Mult: an end-to-end multitask learning transformer. In Proceed- ings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 12031-12041, 2022.","title":"Mult: an end-to-end multitask learning transformer","authors":"Deblina Bhattacharjee, Tong Zhang, Sabine Süsstrunk, Mathieu Salzmann","year":"2022","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Brazdil et al., 1994] Pavel Brazdil, Joāo Gama, and Bob Henery. Characterizing the applicability of classification algorithms using meta-level learning. In European Confer- ence on Machine Learning, pages 83-102. Springer, 1994.","title":"Characterizing the applicability of classification algorithms using meta-level learning","authors":"Brazdil","year":"1994","venue":"European Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Caruana, 1997] Rich Caruana. Multitask learning. Machine learning, 28(1):41-75, 1997.","title":"Multitask learning","authors":"Caruana","year":"1997","venue":"Machine learning","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Duka, 2014] Adrian-Vasile Duka. Neural network based inverse kinematics solution for trajectory tracking of a robotic arm. Procedia Technology, 12:20-27, 2014.","title":"Neural network based inverse kinematics solution for trajectory tracking of a robotic arm","authors":"Adrian-Vasile Duka","year":"2014","venue":"Procedia Technology","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Graffeuille et al., 2022] Olivier Graffeuille, Yun Sing Koh, Jörg Wicker, and Moritz K Lehmann. Semi-supervised conditional density estimation with wasserstein laplacian regularisation. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, pages 6746-6754, 2022.","title":"Semi-supervised conditional density estimation with wasserstein laplacian regularisation","authors":"Olivier Graffeuille, Yun Sing Koh, Jörg Wicker, Moritz K Lehmann","year":"2022","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Guo et al., 2020] Pengsheng Guo, Chen-Yu Lee, and Daniel Ulbricht. Learning to branch for multi-task learning. In International Conference on Machine Learning, pages 3854-3863. PMLR, 2020.","title":"Learning to branch for multi-task learning","authors":"Guo","year":"2020","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Ha et al., 2017] David Ha, Andrew Dai, and Quoc V Le. Hypernetworks. In Proceedings of the 5th International Conference on Learning Representations, 2017.","title":"Hypernetworks","authors":"David Ha, Andrew Dai, Quoc V Le","year":"2017","venue":"Proceedings of the 5th International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Hou et al., 2022] Xuejiao Hou, Lian Feng, Yanhui Dai, Chuanmin Hu, Luke Gibson, Jing Tang, Zhongping Lee, Ying Wang, Xiaobin Cai, Junguo Liu, et al. Global map- ping reveals increase in lacustrine algal blooms over the past decade. Nature Geoscience, 15(2):130-134, 2022.","title":"Global mapping reveals increase in lacustrine algal blooms over the past decade","authors":"Hou","year":"2022","venue":"Nature Geoscience","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Lehmann et al., 2023] Moritz K. Lehmann, Daniela Gurlin, Nima Pahlevan, Krista Alikas, Janet Anstee, Sundara- balan V. Balasubramanian, Cláudio C.F. Barbosa, Caren Binding, Astrid Bracher, Mariano Bresciani, Ashley Burt- ner, Zhigang Cao, Arnold G. Dekker, Nathan Drayson, Reagan M. Errera, Virginia Fernandez, Cédric G. Fi- chot, Peter Gege, Claudia Giardino, Anatoly A. Gitelson, Steven R. Greb, Hayden Henderson, Hiroto Higa, Abol- fazl Irani Rahaghi, Cédric Jamet, Dalin Jiang, Kersti Kan- gro, Raphael Kudela, Lin Li, Martin Ligi, Hubert Loisel, Steven Lohrenz, Ronghua Ma, Daniel A. Maciel, Tim J. Malthus, Bunkei Matsushita, Camille Minaudo, Deepak R. Mishra, Sachidananda Mishra, Tim Moore, Wesley J. Moses, Hà Nguyẽn, Evlyn M.L.M. Novo, Stéfani Novoa, Daniel Odermatt, David M. O'Donnell, Leif G. Ol- manson, Michael Ondrusek, Natascha Oppelt, Water- loo Pereira Filho, Stefan Plattner, Antonio Ruiz Verdú, Salem I. Salem, John F. Schalles, Stefan G.H. Simis, Eko Siswanto, Brandon Smith, Ian Somlai-Schweiger, Mari- ana A. Soppa, Evangelos Spyrakos, Hendrik J. van der Woerd, Andrea Vander Woude, Vincent Vantrepotte, Mar- cel R. Wernand, Mortimer Werther, Linwei Yue, Thomas Jordan, Jeremy A. Kravitz, Arne S. Kristoffersen, Mark Matthews, Elinor Tessin, Ryan A. Vandermeulen, Dariusz Ficek, Courtney Di Vittorio, and Kyana Young. Gloria-a globally representative hyperspectral in situ dataset for op- tical sensing of water quality. Scientific Data, 10(1):100, 2023.","title":"Gloria-a globally representative hyperspectral in situ dataset for optical sensing of water quality","authors":"K Moritz, Daniela Lehmann, Nima Gurlin, Krista Pahlevan, Janet Alikas, Anstee, V Sundarabalan, Balasubramanian, C F Cláudio, Caren Barbosa, Astrid Binding, Mariano Bracher, Ashley Bresciani, Zhigang Burtner, Arnold G Cao, Nathan Dekker, Reagan M Drayson, Virginia Errera, Cédric G Fernandez, Peter Fichot, Claudia Gege, Anatoly A Giardino, Steven R Gitelson, Hayden Greb, Hiroto Henderson, Abolfazl Higa, Cédric Irani Rahaghi, Dalin Jamet, Kersti Jiang, Raphael Kangro, Lin Kudela, Martin Li, Hubert Ligi, Steven Loisel, Ronghua Lohrenz, Daniel A Ma, Tim J Maciel, Bunkei Malthus, Camille Matsushita, Minaudo, R Deepak, Sachidananda Mishra, Tim Mishra, Wesley J Moore, Hà Moses, Nguyẽn, M L M Evlyn, Stéfani Novo, Daniel Novoa, David M Odermatt, Leif G O'donnell, Michael Olmanson, Natascha Ondrusek, Waterloo Oppelt, Stefan Pereira Filho, Antonio Ruiz Plattner, Salem I Verdú, John F Salem, Schalles, G H Stefan, Eko Simis, Brandon Siswanto, Ian Smith, Mariana A Somlai-Schweiger, Evangelos Soppa, Hendrik J Spyrakos, Andrea Van Der Woerd, Vincent Vander Woude, Marcel R Vantrepotte, Mortimer Wernand, Linwei Werther, Thomas Yue, Jeremy A Jordan, Arne S Kravitz, Mark Kristoffersen, Elinor Matthews, Ryan A Tessin, Dariusz Vandermeulen, Courtney Di Ficek, Kyana Vittorio, Young","year":"2023","venue":"Scientific Data","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Lehner et al., 2022] Bernhard Lehner, Mathis L Messager, Maartje C Korver, and Simon Linke. Global hydro- environmental lake characteristics at high spatial resolu- tion. Scientific Data, 9(1):1-19, 2022.","title":"Global hydroenvironmental lake characteristics at high spatial resolution","authors":"Bernhard Lehner, Maartje C Mathis L Messager, Simon Korver, Linke","year":"2022","venue":"Scientific Data","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Lin et al., 2020] Xi Lin, Zhiyuan Yang, Qingfu Zhang, and Sam Kwong. Controllable pareto multi-task learning. arXiv preprint arXiv:2010.06313, 2020.","title":"Controllable pareto multi-task learning","authors":"Xi Lin, Zhiyuan Yang, Qingfu Zhang, Sam Kwong","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Littwin and Wolf, 2019] Gidi Littwin and Lior Wolf. Deep meta functionals for shape representation. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 1824-1833, 2019.","title":"Deep meta functionals for shape representation","authors":"Wolf ; Littwin, Gidi Littwin, Lior Wolf","year":"2019","venue":"Proceedings of the IEEE/CVF International Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Liu et al., 2019] Shikun Liu, Edward Johns, and Andrew J Davison. End-to-end multi-task learning with attention. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 1871-1880, 2019.","title":"End-to-end multi-task learning with attention","authors":"Shikun Liu, Edward Johns, Andrew J Davison","year":"2019","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Liu et al., 2022] Yen-Cheng Liu, Chih-Yao Ma, Junjiao Tian, Zijian He, and Zsolt Kira. Polyhistor: Parameter- efficient multi-task adaptation for dense vision tasks. Advances in Neural Information Processing Systems, 35:36889-36901, 2022.","title":"Polyhistor: Parameterefficient multi-task adaptation for dense vision tasks","authors":"Yen-Cheng Liu, Chih-Yao Ma, Junjiao Tian, Zijian He, Zsolt Kira","year":"2022","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Long et al., 2017] Mingsheng Long, Zhangjie Cao, Jianmin Wang, and Philip S Yu. Learning multiple tasks with mul- tilinear relationship networks. Advances in Neural Infor- mation Processing Systems, 30, 2017.","title":"Learning multiple tasks with multilinear relationship networks","authors":"Mingsheng Long, Zhangjie Cao, Jianmin Wang, Philip S Yu","year":"2017","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Lopes et al., 2023] Ivan Lopes, Tuan-Hung Vu, and Raoul de Charette. Cross-task attention mechanism for dense multi-task learning. In Proceedings of the IEEE/CVF Win- ter Conference on Applications of Computer Vision, pages 2329-2338, 2023.","title":"Cross-task attention mechanism for dense multi-task learning","authors":"Ivan Lopes, Tuan-Hung Vu, Raoul De Charette","year":"2023","venue":"Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Ma et al., 2018] Jiaqi Ma, Zhe Zhao, Xinyang Yi, Jilin Chen, Lichan Hong, and Ed H Chi. Modeling task rela- tionships in multi-task learning with multi-gate mixture- of-experts. In Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining, pages 1930-1939, 2018.","title":"Modeling task relationships in multi-task learning with multi-gate mixtureof-experts","authors":"Jiaqi Ma, Zhe Zhao, Xinyang Yi, Jilin Chen, Lichan Hong, Ed H Chi","year":"2018","venue":"Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Misra et al., 2016] Ishan Misra, Abhinav Shrivastava, Abhi- nav Gupta, and Martial Hebert. Cross-stitch networks for multi-task learning. In Proceedings of the IEEE Confer- ence on Computer Vision and Pattern Recognition, pages 3994-4003, 2016.","title":"Cross-stitch networks for multi-task learning","authors":"Ishan Misra, Abhinav Shrivastava, Abhinav Gupta, Martial Hebert","year":"2016","venue":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Navon et al., 2020] Aviv Navon, Aviv Shamsian, Ethan Fe- taya, and Gal Chechik. Learning the pareto front with hypernetworks. In International Conference on Learning Representations, 2020.","title":"Learning the pareto front with hypernetworks","authors":"Navon","year":"2020","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Neil et al., 2019] Claire Neil, Evangelos Spyrakos, Peter D Hunter, and Andrew N Tyler. A global approach for chlorophyll-a retrieval across optically complex inland wa- ters based on optical water types. Remote Sensing of Envi- ronment, 229:159-178, 2019.","title":"A global approach for chlorophyll-a retrieval across optically complex inland waters based on optical water types","authors":"Claire Neil, Evangelos Spyrakos, Peter D Hunter, Andrew N Tyler","year":"2019","venue":"Remote Sensing of Environment","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Pahlevan et al., 2020] Nima Pahlevan, Brandon Smith, John Schalles, Caren Binding, Zhigang Cao, Krista Ma, Ronghua anfd Alikas, Kersti Kangro, Daniela Gurlin, Nguyẽn Hà, et al. Seamless retrievals of chlorophyll-a from sentinel-2 (msi) and sentinel-3 (olci) in inland and coastal waters: A machine-learning approach. Remote Sensing of Environment, 240:111604, 2020.","title":"Seamless retrievals of chlorophyll-a from sentinel-2 (msi) and sentinel-3 (olci) in inland and coastal waters: A machine-learning approach","authors":"Nima Pahlevan, Brandon Smith, John Schalles, Caren Binding, Zhigang Cao, Krista Ma, Kersti Ronghua Anfd Alikas, Daniela Kangro, Nguyẽn Gurlin, Hà","year":"2020","venue":"Remote Sensing of Environment","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Pascal et al., 2021] Lucas Pascal, Pietro Michiardi, Xavier Bost, Benoit Huet, and Maria A Zuluaga. Maximum roam- ing multi-task learning. In Proceedings of the AAAI Con- ference on Artificial Intelligence, volume 35, pages 9331- 9341, 2021.","title":"Maximum roaming multi-task learning","authors":"Lucas Pascal, Pietro Michiardi, Xavier Bost, Benoit Huet, Maria A Zuluaga","year":"2021","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Raychaudhuri et al., 2022] Dripta S Raychaudhuri, Yumin Suh, Samuel Schulter, Xiang Yu, Masoud Faraki, Amit K Roy-Chowdhury, and Manmohan Chandraker. Control- lable dynamic multi-task architectures. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pat- tern Recognition, pages 10955-10964, 2022.","title":"Controllable dynamic multi-task architectures","authors":"Yumin Dripta S Raychaudhuri, Samuel Suh, Xiang Schulter, Masoud Yu, Faraki, K Amit, Manmohan Roy-Chowdhury, Chandraker","year":"2022","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Ruder et al., 2019] Sebastian Ruder, Joachim Bingel, Is- abelle Augenstein, and Anders Søgaard. Latent multi-task architecture learning. In Proceedings of the AAAI Con- ference on Artificial Intelligence, volume 33, pages 4822- 4829, 2019.","title":"Latent multi-task architecture learning","authors":"Sebastian Ruder, Joachim Bingel, Isabelle Augenstein, Anders Søgaard","year":"2019","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Ruder, 2017] Sebastian Ruder. An overview of multi- task learning in deep neural networks. arXiv preprint arXiv:1706.05098, 2017.","title":"An overview of multitask learning in deep neural networks","authors":"Sebastian Ruder","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Shamsian et al., 2021] Aviv Shamsian, Aviv Navon, Ethan Fetaya, and Gal Chechik. Personalized federated learn- ing using hypernetworks. In International Conference on Machine Learning, pages 9489-9502. PMLR, 2021.","title":"Personalized federated learning using hypernetworks","authors":"Shamsian","year":"2021","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Shui et al., 2019] Changjian Shui, Mahdieh Abbasi, Louis- Émile Robitaille, Boyu Wang, and Christian Gagné. A principled approach for learning task similarity in multi- task learning. In Proceedings of the 28th International Joint Conference on Artificial Intelligence, pages 3446- 3452, 2019.","title":"A principled approach for learning task similarity in multitask learning","authors":"Shui","year":"2019","venue":"Proceedings of the 28th International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2019/478"},{"position":28,"raw":"[Sodhani et al., 2021] Shagun Sodhani, Amy Zhang, and Joelle Pineau. Multi-task reinforcement learning with context-based representations. In International Confer- ence on Machine Learning, pages 9767-9779. PMLR, 2021.","title":"Multi-task reinforcement learning with context-based representations","authors":"Shagun Sodhani, Amy Zhang, Joelle Pineau","year":"2021","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Sun et al., 2020] Ximeng Sun, Rameswar Panda, Rogerio Feris, and Kate Saenko. Adashare: Learning what to share for efficient deep multi-task learning. Advances in Neural Information Processing Systems, 33:8728-8740, 2020.","title":"Adashare: Learning what to share for efficient deep multi-task learning","authors":"Sun","year":"2020","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Sun et al., 2021] Guolei Sun, Thomas Probst, Danda Pani Paudel, Nikola Popović, Menelaos Kanakis, Jagruti Patel, Dengxin Dai, and Luc Van Gool. Task switching network for multi-task learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 8291-8300, 2021.","title":"Task switching network for multi-task learning","authors":"Sun","year":"2021","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Tay et al., 2021] Yi Tay, Zhe Zhao, Dara Bahri, Donald Metzler, and Da-Cheng Juan. Hypergrid transformers: To- wards a single model for multiple tasks. In International Conference on Learning Representations, 2021.","title":"Hypergrid transformers: Towards a single model for multiple tasks","authors":"Yi Tay, Zhe Zhao, Dara Bahri, Donald Metzler, Da-Cheng Juan","year":"2021","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[United Nations, 2015] United Nations. Transforming our world: the 2030 agenda for sustainable development, 2015. Accessed: 2014-01-15.","title":"United Nations. Transforming our world: the 2030 agenda for sustainable development","authors":null,"year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Üstün et al., 2022] Ahmet Üstün, Arianna Bisazza, Gosse Bouma, Gertjan van Noord, and Sebastian Ruder. Hyper- x: A unified hypernetwork for multi-task multilingual transfer. In Proceedings of EMNLP 2022. Association for Computational Linguistics, 2022.","title":"Hyperx: A unified hypernetwork for multi-task multilingual transfer","authors":"Ahmet Üstün, Arianna Bisazza, Gosse Bouma, Gertjan Van Noord, Sebastian Ruder","year":"2022","venue":"Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[von Oswald et al., 2020] Johannes von Oswald, Christian Henning, Benjamin F Grewe, and João Sacramento. Con- tinual learning with hypernetworks. In Proceedings of the 8th International Conference on Learning Represen- tations, 2020.","title":"Continual learning with hypernetworks","authors":"Oswald Von","year":"2020","venue":"Proceedings of the 8th International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Yang and Hospedales, 2017] Yongxin Yang and Timothy Hospedales. Deep multi-task representation learning: A tensor factorisation approach. In 5th International Confer- ence on Learning Representations, 2017.","title":"Deep multi-task representation learning: A tensor factorisation approach","authors":"Yang, Hospedales ;, Yongxin Yang, Timothy Hospedales","year":"2017","venue":"5th International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Yang et al., 2022] Xiao Yang, Catherine M. O'Reilly, John R. Gardner, Matthew R. V. Ross, Simon N. Topp, Jida Wang, and Tamlin M. Pavelsky. The color of earth's lakes. Geophysical Research Letters, 49, 2022.","title":"The color of earth's lakes","authors":"Xiao Yang, Catherine M O'reilly, John R Gardner, R V Matthew, Simon N Ross, Jida Topp, Tamlin M Wang, Pavelsky","year":"2022","venue":"Geophysical Research Letters","doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Ye and Ren, 2021] Qinyuan Ye and Xiang Ren. Learning to generate task-specific adapters from task description. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, pages 646-653, 2021.","title":"Qinyuan Ye and Xiang Ren. Learning to generate task-specific adapters from task description","authors":"Ren Ye","year":"2021","venue":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing","doi":null,"url":null,"internal_url":null},{"position":38,"raw":"[You et al., 2016] Qiang You, Ou Wu, Guan Luo, and Weim- ing Hu. Metadata-based clustered multi-task learning for thread mining in web communities. In Machine Learning and Data Mining in Pattern Recognition: 12th Interna- tional Conference, MLDM 2016, New York, NY, USA, July 16-21, 2016, Proceedings, pages 421-434. Springer, 2016.","title":"Metadata-based clustered multi-task learning for thread mining in web communities","authors":"Qiang You, Ou Wu, Guan Luo, Weiming Hu","year":"2016","venue":"Machine Learning and Data Mining in Pattern Recognition: 12th International Conference, MLDM 2016","doi":null,"url":null,"internal_url":null},{"position":39,"raw":"[Zamir et al., 2018] Amir R Zamir, Alexander Sax, William Shen, Leonidas J Guibas, Jitendra Malik, and Silvio Savarese. Taskonomy: Disentangling task transfer learn- ing. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 3712-3722, 2018.","title":"Taskonomy: Disentangling task transfer learning","authors":"Alexander Amir R Zamir, William Sax, Leonidas J Shen, Jitendra Guibas, Silvio Malik, Savarese","year":"2018","venue":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":"/proceedings/2019/871"},{"position":40,"raw":"[Zhang et al., 2018] Yu Zhang, Ying Wei, and Qiang Yang. Learning to multitask. Advances in Neural Information Processing Systems, 31, 2018.","title":"Learning to multitask","authors":"Yu Zhang, Ying Wei, Qiang Yang","year":"2018","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":41,"raw":"[Zheng et al., 2019] Zimu Zheng, Yuqi Wang, Quanyu Dai, Huadi Zheng, and Dan Wang. Metadata-driven task rela- tion discovery for multi-task learning. In Proceedings of the Twenty-Eighth International Joint Conference on Arti- ficial Intelligence, pages 4426-4431, 2019.","title":"Metadata-driven task relation discovery for multi-task learning","authors":"Zheng","year":"2019","venue":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2019/615"}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}