└── README.md /README.md: -------------------------------------------------------------------------------- 1 | # A Collection of Main Papers on Gradient-based-Multi-objective-optimization-and-Deep-Learning 2 | 3 | 4 | ## Algorithms 5 | 6 | | Paper Title | Venue | Year | Authors | Materials | Comment | 7 | | ------------------------------------------------------------ | ----- | ---- | -------------- | ------------------------------------------------------------ | ------------------------------------------------------------ | 8 | | 1. Multi-Task Learning as Multi-Objective Optimization | NIPS | 2018 | _Sener et al._ | [[paper](https://arxiv.org/pdf/1810.04650.pdf)] [[code](https://github.com/isl-org/MultiObjectiveOptimization)] | [[blog](https://zhuanlan.zhihu.com/p/352461938)] | 9 | | 2. Pareto Multi-Task Learning | NIPS | 2019 | _Lin st al._ | [[paper](https://proceedings.neurips.cc/paper/2019/file/685bfde03eb646c27ed565881917c71c-Paper.pdf)] [[code](https://github.com/Xi-L/ParetoMTL)] | [[blog](https://zhuanlan.zhihu.com/p/352461938)] | 10 | | 3. Effcient Continuous Pareto Exploration in Multi-Task Learning | ICML | 2020 | _Ma st al._ | [[paper](http://proceedings.mlr.press/v119/ma20a/ma20a.pdf)][[code](https://github.com/mit-gfx/ContinuousParetoMTL)] | [[blog](https://zhuanlan.zhihu.com/p/352461938)] | 11 | | 4. Multi-Task Learning with User Preferences Gradient Descent with Controlled Ascent in Pareto Optimization | ICML | 2020 | _Mahapatra st al._ | [[paper](http://proceedings.mlr.press/v119/mahapatra20a/mahapatra20a.pdf)] [[code](https://github.com/dbmptr/EPOSearch)] | | 12 | | 5. Controllable Pareto Multi-Task Learning | arxiv | 2021 | _Lin st al._ | [[paper](https://arxiv.org/pdf/2010.06313.pdf)]| | 13 | | 6. Learning the pareto front with hypernetworks | ICLR | 2021 | _Navon st al._ | [[paper](https://arxiv.org/pdf/2010.04104.pdf)] [[code](https://github.com/AvivNavon/pareto-hypernetworks)] | | 14 | | 7. Profiling Pareto Front With Multi-Objective Stein Variational Gradient Descent | NIPS | 2021 | _Liu st al._ | [[paper](https://proceedings.neurips.cc/paper/2021/file/7bb16972da003e87724f048d76b7e0e1-Paper.pdf)] [[code](https://github.com/gnobitab/MultiObjectiveSampling)]| | 15 | | 8. Scalable Pareto Front Approximation for Deep Multi-Objective Learning | ICDM | 2021 | _Ruchte st al._ | [[paper](https://128.84.4.13/pdf/2103.13392.pdf)] [[code](https://github.com/ruchtem/cosmos)] | | 16 | | 9. Multi-Objective Learning to Predict Pareto Fronts Using Hypervolume Maximization | arxiv | 2021 | _Deist st al._ | [[paper](https://arxiv.org/pdf/2102.04523.pdf)] [[code](https://github.com/timodeist/multi_objective_learning)] [[PPT](https://www.cwi.nl/events/cwi-scientific-meetings/deist_cwi_scientific_meeting.pdf)]| | 17 | | 10. Self-Evolutionary Optimization for Pareto Front Learning | arxiv | 2021 | _Chang st al._ | [[paper](https://arxiv.org/pdf/2110.03461.pdf)] | | 18 | | 11. Pareto Navigation Gradient Descent: a First-Order Algorithm for Optimization in Pareto Set | UAI | 2022 | _Ye st al._ | [[paper](https://proceedings.mlr.press/v180/ye22a.html)] [[code](https://github.com/lushleaf/ParetoNaviGrad)] | | 19 | | 12. A Multi-objective Multi-task Learning Framework Induced by Pareto Stationarity | ICML | 2022 | _Momma st al._ | [[paper](https://proceedings.mlr.press/v162/momma22a.html)] | | 20 | | 13. Generalization In Multi-Objective Machine Learning | arxiv | 2022 | _Súkeník st al._ | [[paper](https://arxiv.org/pdf/2208.13499.pdf)] | | 21 | | 14. Multi-objective Optimization by Learning Space Partition | ICLR | 2022 | _Zhao st al._ | [[paper](https://openreview.net/forum?id=FlwzVjfMryn)] [[open](https://openreview.net/forum?id=FlwzVjfMryn)] | | 22 | | 15. A Two-Stage Neural-Filter Pareto Front Extractor and the need for Benchmarking | ICLR_Reject | 2022 | _Gupta st al._ | [[paper](https://openreview.net/forum?id=UOj0MV__Cr)] [[open](https://openreview.net/forum?id=UOj0MV__Cr)] | | 23 | | 16. Improving Pareto Front Learning via Multi-Sample Hypernetworks | AAAI | 2023 | _Hoang st al._ | [[paper](https://ojs.aaai.org/index.php/AAAI/article/view/25953)] | | 24 | | 17. A Framework for Controllable Pareto Front Learning with Completed Scalarization Functions and its Applications | arxiv | 2023 | _Tuan st al._ | [[paper](https://arxiv.org/abs/2302.12487)] | | 25 | | 18. Pareto Manifold Learning: Tackling multiple tasks via ensembles of single-task models | ICML | 2023 | _Dimitriadis st al._ | [[paper](https://proceedings.mlr.press/v202/dimitriadis23a.html)] [[code](https://github.com/nik-dim/pamal)] | | 26 | | 19. Multi-objective Learning Using HV Maximization | EMO | 2023 | _Deist st al._ | [[paper](https://link.springer.com/chapter/10.1007/978-3-031-27250-9_8)] [[code](https://github.com/timodeist/multi_objective_learning)] | | 27 | | 20. LibMOON: A Gradient-based MultiObjective OptimizatioN Library in PyTorch | | 2024 | _Zhang st al._ | [[code](https://github.com/xzhang2523/libmoon)] | | 28 | 29 | 30 | ## Applications 31 | | Paper Title | Venue | Year | Authors | Materials | Comment | 32 | | ------------------------------------------------------------ | ----- | ---- | -------------- | ------------------------------------------------------------ | ------------------------------------------------------------ | 33 | | 1. A pareto-efficient algorithm for multiple objective optimization in e-commerce recommendation| RecSys | 2019 | _Lin st al._ | [[paper](https://dl.acm.org/doi/abs/10.1145/3298689.3346998)] | | 34 | | 2. Prediction-Guided Multi-Objective Reinforcement Learning for Continuous Robot Control| ICML | 2020 | _Xu st al._ | [[paper](http://pgmorl.csail.mit.edu/)] [[code](https://github.com/mit-gfx/PGMORL)] | | 35 | | 3. Controllable Dynamic Multi-Task Architectures| CVPR | 2022 | _Raychaudhuri st al._ | [[paper](https://openaccess.thecvf.com/content/CVPR2022/html/Raychaudhuri_Controllable_Dynamic_Multi-Task_Architectures_CVPR_2022_paper.html)] [[code](https://www.nec-labs.com/˜mas/DYMU)] | | 36 | | 4. Pareto Policy Adaptation| ICLR | 2022 | _Kyriakis st al._ | [[paper](https://openreview.net/forum?id=wfZGut6e09)] [[open](https://openreview.net/forum?id=wfZGut6e09)] | | 37 | | 5. Pareto Set Learning for Neural Multi-Objective Combinatorial Optimization| ICLR | 2022 | _Lin st al._ | [[paper](https://openreview.net/forum?id=QuObT9BTWo)] [[open](https://openreview.net/forum?id=QuObT9BTWo)] [[code](https://github.com/Xi-L/PMOCO)] | | 38 | | 6. Pareto Policy Pool for Model-based Offline Reinforcement Learning| ICLR | 2022 | _Yang st al._ | [[paper](https://openreview.net/forum?id=OqcZu8JIIzS)] [[open](https://openreview.net/forum?id=OqcZu8JIIzS)] [[code](https://github.com/OverEuro/P3)] | | 39 | | 7. Multi-Objective Online Learning| ICLR_Reject | 2022 | _Jiang st al._ | [[paper](https://openreview.net/forum?id=YfFWrndRGQx)] [[open](https://openreview.net/forum?id=YfFWrndRGQx)] [[code](https://github.com/OverEuro/P3)] | | 40 | | 8. On Multi-objective Policy Optimization as a Tool for Reinforcement Learning: Case Studies in Offline RL and Finetuning| ICLR_Reject | 2022 | _Abdolmaleki st al._ | [[paper](https://openreview.net/forum?id=bilHNPhT6-)] [[open](https://openreview.net/forum?id=bilHNPhT6-)] | | 41 | | 9. Multi-Objective Model Selection for Time Series Forecasting | ICLR_Reject | 2022 | _Borchert st al._ | [[paper](https://openreview.net/forum?id=4XtpgPsvxE8)] [[open](https://openreview.net/forum?id=4XtpgPsvxE8)] | | 42 | | 10. Multi-Objective Meta Learning | NIPS | 2022 | _Ye st al._ | [[paper](https://openreview.net/forum?id=wKf9iSu_TEm)] [[open](https://openreview.net/forum?id=wKf9iSu_TEm)] [[code](https://github.com/Baijiong-Lin/MOML)]| | 43 | | 11. On the Pareto Front of Multilingual Neural Machine Translation | arxiv | 2023 | _Chen st al._ | [[paper](https://arxiv.org/abs/2304.03216)] [[code](https://github.com/chenllliang/ParetoMNMT)]| | 44 | 45 | 46 | **Disclaimer** 47 | 48 | If you have any questions, please feel free to contact us. 49 | Emails: xiaofengxd@126.com 50 | 51 | --------------------------------------------------------------------------------