A Survey on Multi-Task Learning

IEEE Transactions on Knowledge and Data Engineering - Tập 34 Số 12 - Trang 5586-5609 - 2022
Yu Zhang1, Qiang Yang2
1Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, Guangdong, China
2Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Hong Kong

Tóm tắt

Từ khóa


Tài liệu tham khảo

10.1137/1.9781611975673.2

honorio, 2010, Multi-task learning of Gaussian graphical models, Proc Int Conf Mach Learn, 447

niculescu-mizil, 2012, Inductive transfer for Bayesian network structure learning, Proc Mach Learn, 167

10.1145/2939672.2939834

oyen, 2012, Leveraging domain knowledge in multitask Bayesian network structure learning, Proc AAAI Conf Artif Intell, 1091

10.1007/11776420_34

10.1109/ICDM.2015.130

lugosi, 2009, Online multi-task learning with hard constraints, Proc 22nd Conf Learn Theory

dekel, 2007, Online learning of multiple tasks with a shared loss, J Mach Learn Res, 8, 2233

10.1109/TKDE.2016.2603983

10.1109/TCYB.2015.2403356

hernández-lobato, 2015, A probabilistic model for dirty multi-task feature selection, Proc Int Conf Mach Learn, 1073

hernández-lobato, 2013, Learning feature selection dependencies in multi-task learning, Proc Int Conf Neural Inf Process, 746

10.1609/aaai.v28i1.9009

wang, 2014, On multiplicative multitask feature learning, Proc Int Conf Neural Inf Process, 2411

lozano, 2012, Multi-level lasso for sparse multi-task regression, Proc 29th Int Conf Mach Learn, 595

gong, 2013, Multi-stage multi-task feature learning, J Mach Learn Res, 14, 2979

zhang, 2010, Probabilistic multi-task feature selection, Proc Int Conf Neural Inf Process, 2559

zhou, 2010, Exclusive lasso for multi-task feature selection, Proc 13th Int Conf Artif Intell Statist, 988

kim, 2010, Tree-guided group lasso for multi-task regression with structured sparsity, Proc 27th Int Conf Mach Learn, 543

10.1007/978-1-4419-9011-2

saha, 2011, Online learning of multiple tasks and their relationships, Proc Int Conf Artif Intell Statist, 643

10.1109/TPAMI.2008.297

10.1609/aaai.v33i01.33015636

10.24963/ijcai.2017/253

10.1109/TKDE.2017.2703106

murugesan, 2016, Adaptive smoothed online multi-task learning, Proc Int Conf Neural Inf Process, 4303

smith, 2017, Federated multi-task learning, Proc Int Conf Neural Inf Process, 4427

10.1145/3097983.3098152

10.1145/3097983.3098136

wang, 2016, Distributed multi-task learning, Proc Int Conf Artif Intell Statist, 751

wang, 2015, Safe screening for multi-task feature learning with multiple data matrices, Proc Int Conf Mach Learn, 1747

10.1145/2623330.2623641

cavallanti, 2010, Linear algorithms for online multitask classification, J Mach Learn Res, 11, 2901

10.1145/1553374.1553458

10.21437/Interspeech.2016-879

10.1109/CVPR.2016.433

10.18653/v1/P17-1001

liu, 2009, Multi-task feature learning via efficient $l_{2,1}$l2,1-norm minimization, Proc 25th Conf Uncertainty Artif Intell, 339

obozinski, 2006, Multi-task feature selection

rao, 2013, Sparse overlapping sets lasso for multitask learning and its application to fMRI analysis, Proc Int Conf Neural Inf Process, 2202

lee, 2010, Adaptive multi-task lasso: With application to eQTL detection, Proc Int Conf Neural Inf Process, 1306

bakker, 2003, Task clustering and gating for Bayesian multitask learning, J Mach Learn Res, 4, 83

10.1145/1102351.1102479

teh, 2017, Distral: Robust multitask reinforcement learning, Proc Int Conf Neural Inf Process, 4499

omidshafiei, 2017, Deep decentralized multi-task multi-agent reinforcement learning under partial observability, Proc Int Conf Mach Learn, 2681

sharma, 2017, Online multi-task learning using active sampling, Proc Int Conf Learn Representations Workshop

bsat, 2017, Scalable multitask policy gradient reinforcement learning, Proc AAAI Conf Artif Intell, 1847

igl, 2020, Multitask soft option learning, Proc Conf Uncertainty Artif Intell, 969

rusu, 2016, Policy distillation, Proc Int Conf Learn Representations

parisotto, 2016, Actor-mimic: Deep multitask and transfer reinforcement learning, Proc Int Conf Learn Representations

deshmukh, 2017, Multi-task learning for contextual bandits, Proc Int Conf Neural Inf Process, 4851

saxe, 2017, Hierarchy through composition with multitask LMDPs, Proc Int Conf Mach Learn, 3017

bräm, 2019, Attentive multi-task deep reinforcement learning, Proc Eur Conf Mach Learn Knowl Discovery Databases, 134

10.24963/ijcai.2019/505

10.1109/TSP.2008.924798

10.1145/1273496.1273583

10.1145/1390156.1390253

10.1109/ICASSP.2011.5946926

10.1145/1273496.1273630

xue, 2007, Multi-task learning for classification with Dirichlet process priors, J Mach Learn Res, 8, 35

lian, 2015, A multitask point process predictive model, Proc Int Conf Mach Learn, 2030

yu, 2007, Robust multi-task learning with t-processes, Proc 24th Int Conf Mach Learn, 1103

ando, 2005, A framework for learning predictive structures from multiple tasks and unlabeled data, J Mach Learn Res, 6, 1817

zhang, 2015, Multi-task multi-view clustering for non-negative data, Proc Int Joint Conf Artif Intell, 4055

10.1145/2339530.2339617

he, 2011, A graph-based framework for multi-task multi-view learning, Proc Int Conf Mach Learn, 25

guo, 2020, Bootstrap latent-predictive representations for multitask reinforcement learning, Proc Int Conf Mach Learn, 3875

10.1609/aaai.v33i01.33013796

shu, 2018, Hierarchical and interpretable skill acquisition in multi-task reinforcement learning, Proc Int Conf Learn Representations

d’eramo, 2020, Sharing knowledge in multi-task deep reinforcement learning, Proc Int Conf Learn Representations, 1

lin, 2019, Adaptive auxiliary task weighting for reinforcement learning, Proc Int Conf Neural Inf Process, 4773

10.1016/j.neunet.2019.01.012

10.1109/TKDE.2013.39

yang, 2009, Heterogeneous multitask learning with joint sparsity constraints, Proc Int Conf Neural Inf Process, 2151

10.1093/nsr/nwx105

liao, 2005, Radial basis function network for multi-task learning, Proc Int Conf Neural Inf Process, 792

tutunov, 2018, Distributed multitask reinforcement learning with quadratic convergence, Proc Int Conf Neural Inf Process, 8921

crammer, 2012, Learning multiple tasks using shared hypotheses, Proc 25th Int Conf Neural Inf Process Syst, 1475

10.1145/1390156.1390164

sharma, 2018, Learning to multi-task by active sampling, Proc Int Conf Learn Representations

10.1007/s10994-008-5088-0

espeholt, 2018, IMPALA: Scalable distributed deep-RL with importance weighted actor-learner architectures, Proc Int Conf Mach Learn, 1406

mcdonald, 2014, Spectral $k$k-support norm regularization, Proc 27th Int Conf Neural Inf Process Syst, 3644

10.1609/aaai.v30i1.10261

thrun, 1996, Discovering structure in multiple learning tasks: The TC algorithm, Proc 13th Int Conf Mach Learn, 489

yang, 2017, Trace norm regularised deep multi-task learning, Proc 5th Int Conf Learn Representation Workshop Track

agarwal, 2010, Learning multiple tasks using manifold regularization, Proc Adv Neural Inf Process Syst, 46

10.1145/1553374.1553392

10.1137/090763184

zhang, 2005, Learning multiple related tasks using latent independent component analysis, Proc Int Conf Neural Inf Process, 1585

feldman, 2014, Revisiting Stein's paradox: Multi-task averaging, J Mach Learn Res, 15, 3621

kato, 2007, Multi-task learning via conic programming, Proc Int Conf Neural Inf Process, 737

evgeniou, 2005, Learning multiple tasks with kernel methods, J Mach Learn Res, 6, 615

parameswaran, 2010, Large margin multi-task metric learning, Proc Int Conf Neural Inf Process, 1867

bonilla, 2007, Multi-task Gaussian process prediction, Proc Int Neural Inf Process Syst, 153

chai, 2009, Generalization errors and learning curves for regression with multi-task Gaussian processes, Proc 22nd Int Conf Neural Inf Process Syst, 279

10.1162/NECO_a_00844

görnitz, 2011, Hierarchical multitask structured output learning for large-scale sequence segmentation, Proc 24th Int Conf Neural Inf Process Syst, 2690

zhang, 2010, Multi-task learning using generalized $t$t process, Proc 13th Int Conf Artif Intell Statist, 964

zhang, 2010, A convex formulation for learning task relationships in multi-task learning, Proc 26th Conf Uncertainty Artif Intell, 733

passos, 2012, Flexible modeling of latent task structures in multitask learning, Proc 29th Int Conf Mach Learn, 1283

kang, 2011, Learning with whom to share in multi-task feature learning, Proc 28th Int Conf Mach Learn, 521

jacob, 2008, Clustered multi-task learning: A convex formulation, Proc 18th Int Conf Artif Intell Statist, 745

10.1609/aaai.v29i1.9581

barzilai, 2015, Convex multi-task learning by clustering, Proc Artif Intell Statist

10.1109/TPAMI.2015.2452911

kumar, 2012, Learning task grouping and overlap in multi-task learning, Proc 29th Int Conf Mach Learn

yang, 2017, Deep multi-task representation learning: A tensor factorisation approach, Proc Int Conf Mach Representations

zhou, 2011, Clustered multi-task learning via alternating structure optimization, Proc Int Conf Neural Inf Process

10.1145/1014052.1014067

10.1145/1645953.1646169

ghosn, 1996, Multi-task learning for stock selection, Proc Int Conf Neural Inf Process, 946

10.1109/CVPR.2013.61

10.1007/s11263-012-0582-z

10.1109/TCBB.2010.22

10.1109/ICASSP.2015.7178814

10.21437/Interspeech.2015-265

long, 2017, Learning multiple tasks with multilinear relationship networks, Proc 31st Int Conf Neural Inf Process Syst, 1593

gonçalves, 2016, Multi-task sparse structure learning with Gaussian copula models, J Mach Learn Res, 7, 1

10.1007/s10994-017-5676-y

rakitsch, 2013, It is all in the noise: Efficient multi-task Gaussian process inference with structured residuals, Proc 26th Int Conf Neural Inf Process Syst, 1466

10.1145/1553374.1553516

rai, 2012, Simultaneously leveraging output and task structures for multiple-output regression, Proc 25th Int Conf Neural Inf Process Syst, 3185

zhang, 2012, Robust visual tracking via multi-task sparse learning, Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit, 2042

zhang, 2013, Learning high-order task relationships in multi-task learning, Proc 23rd Int Joint Conf Artif Intell, 1917

yang, 2013, Multi-task learning with Gaussian matrix generalized inverse Gaussian model, Proc Int Conf Mach Learn, 423

jalali, 2010, A dirty model for multi-task learning, Proc 23rd Int Conf Neural Inf Process Syst, 964

10.1145/1835804.1835952

zhang, 2013, Heterogeneous-neighborhood-based multi-task local learning algorithms, Proc Int Conf Neural Inf Process, 1896

lee, 2016, Asymmetric multi-task learning based on task relatedness and loss, Proc Int Conf Mach Learn, 230

10.1145/2499907.2499910

10.1007/978-3-642-33460-3_50

ciliberto, 2015, Convex learning of multiple tasks and their structure, Proc 32nd Int Conf Mach Learn, 1548

dinuzzo, 2011, Learning output kernels with block coordinate descent, Proc 28th Int Conf Mach Learn, 49

10.1145/2538028

archambeau, 2011, Sparse Bayesian multi-task learning, Proc Int Conf Neural Inf Process, 1755

10.1109/CVPR.2015.7298608

jawanpuria, 2015, Efficient output kernel learning for multiple tasks, Proc Int Conf Neural Process Syst, 1189

10.1609/aaai.v31i1.10820

zhang, 2010, Learning multiple tasks with a sparse matrix-normal penalty, Proc 23rd Int Conf Neural Inf Process Syst, 2550

10.1093/bioinformatics/btq394

10.1145/2339530.2339672

10.1145/2020408.2020423

10.1109/ICCV.2015.383

zheng, 2008, Transferring multi-device localization models using latent multi-task learning, Proc AAAI Conf Artif Intell, 1427

10.1145/1390156.1390177

10.1109/ICASSP.2015.7178780

10.21437/Interspeech.2015-659

luong, 2016, Multi-task sequence to sequence learning, Proc Int Conf Learn Representations

yim, 2015, Rotating your face using multi-task deep neural network, Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit, 676

10.1109/CVPR.2014.186

10.1109/TMM.2015.2477680

10.1109/CVPR.2010.5539967

wang, 2009, Boosted multi-task learning for face verification with applications to web image and video search, Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit, 142

10.1186/1471-2105-11-181

10.1145/2396761.2398508

wang, 2011, Sparse multi-task regression and feature selection to identify brain imaging predictors for memory performance, Proc IEEE Int Conf Comput Vis, 557

10.1093/bioinformatics/btq191

10.1145/2020408.2020549

wan, 2012, Sparse Bayesian multi-task learning for predicting cognitive outcomes from neuroimaging measures in Alzheimer's disease, Proc IEEE Conf Comput Vis Pattern Recognit, 940

10.1093/bioinformatics/btw249

10.1093/bioinformatics/btq181

10.1109/ICCV.2011.6126528

10.1109/TIP.2011.2169274

10.1137/1.9781611974348.74

10.1109/TPAMI.2016.2537337

10.1109/ICCV.2015.430

10.1137/1.9781611974010.56

10.1109/CVPR.2010.5539975

alamgir, 2010, Multitask learning for brain-computer interfaces, Mach Learn Res, 17

10.1145/1390156.1390159

wang, 2012, High-order multi-task feature learning to identify longitudinal phenotypic markers for Alzheimer's disease progression prediction, Proc Adv Neural Inf Process Syst, 1277

10.1137/1.9781611974010.57

10.1137/1.9781611973440.22

reichart, 2008, Multi-task active learning for linguistic annotations, Proc Annual Meeting of the Assoc Computational Linguistics, 861

10.1007/978-3-642-04174-7_40

10.1109/ICDM.2016.0035

li, 2009, Active learning for semi-supervised multi-task learning, Proc IEEE Int Conf Acoust Speech Signal Process, 1637

pentina, 2017, Multi-task learning with labeled and unlabeled tasks, Proc Int Conf Mach Learn, 2807

10.1145/2747879

10.1609/aaai.v25i1.7914

10.1609/aaai.v24i1.7674

10.1609/aaai.v27i1.8557

10.1007/978-3-642-12683-3_34

zhang, 2010, Multi-domain collaborative filtering, Proc Conf Uncertainty Artif Intell, 725

10.1109/ICDM.2015.68

10.1145/1835804.1835953

10.1109/TITS.2016.2598356

10.1609/aaai.v27i1.8577

10.1007/978-0-387-85774-9_8

chai, 2008, Multi-task Gaussian process learning of robot inverse dynamics, Proc Int Conf Neural Inf Process, 265

10.1145/2556195.2556264

10.1186/1471-2105-11-S8-S5

wang, 2015, Multi-task learning for subspace segmentation, Proc Int Conf Mach Learn, 1209

10.1109/TPAMI.2014.2343221

10.1109/TCYB.2014.2344015

zhang, 2016, Self-adapted multi-task clustering, Proc Int Joint Conf Artif Intell, 2357

10.1109/TNNLS.2016.2521602

10.24963/ijcai.2018/435

10.1145/1273496.1273624

li, 2009, Multi-task reinforcement learning in partially observable stochastic environments, J Mach Learn Res, 10, 1131

lazaric, 2010, Bayesian multi-task reinforcement learning, Proc Int Conf Mach Learn, 599

calandriello, 2014, Sparse multi-task reinforcement learning, Proc Int Conf Neural Inf Process, 5

10.1017/9781139061773

andreas, 2017, Modular multitask reinforcement learning with policy sketches, Proc Int Conf Mach Learn, 166

10.1023/A:1007379606734

10.1109/TKDE.2017.2662006

10.1093/bioinformatics/btt245

10.1093/bioinformatics/bty457

10.1109/ICCV.2013.86

10.1186/1471-2105-12-389

zhang, 2017, A survey on multi-task learning

10.1109/TPAMI.2017.2679002

10.1089/cmb.2016.0201

10.1109/ICCV.2013.150

10.1145/225298.225336

10.1609/aaai.v25i1.7909

zhang, 2018, Learning to multitask, Proc 32nd Int Conf Neural Inf Process Syst, 5776

solnon, 2012, Multi-task regression using minimal penalties, J Mach Learn Res, 13, 2773

gong, 2012, Geodesic flow kernel for unsupervised domain adaptation, Proc IEEE Conf Comput Vis Pattern Recognit, 2066

jawanpuria, 2012, A convex feature learning formulation for latent task structure discovery, Proc 29th Int Conf Mach Learn, 1531

10.1145/2783258.2783393

zweig, 2013, Hierarchical regularization cascade for joint learning, Proc Int Conf Mach Learn, 37

zhong, 2012, Convex multitask learning with flexible task clusters, Proc 18th Int Conf Artif Intell Statist, 65

10.1007/s10994-013-5379-y

quadrianto, 2010, Multitask learning without label correspondences, Proc 23rd Int Conf Neural Inf Process Syst, 1957

han, 2012, Cross-domain multitask learning with latent probit models, Proc 29th Int Conf Mach Learn, 363

10.1613/jair.731

maurer, 2006, Bounds for linear multi-task learning, J Mach Learn Res, 7, 117

10.1007/s10994-007-5043-5

kakade, 2012, Regularization techniques for learning with matrices, J Mach Learn Res, 13, 1865

10.1007/11776420_8

10.1145/1143844.1143900

10.1007/978-3-319-24486-0_13

pontil, 2013, Excess risk bounds for multitask learning with trace norm regularization, Proc Annu Conf Learn Theory, 55

maurer, 2016, The benefit of multitask representation learning, J Mach Learn Res, 17, 1

10.1007/s10994-007-5040-8

10.1609/aaai.v29i1.9558

argyriou, 2007, A spectral regularization framework for multi-task structure learning, Proc Int Conf Neural Inf Process

maurer, 2013, Sparse coding for multitask and transfer learning, Proc 30th Int Conf Mach Learn, 343

zhu, 2011, Infinite latent SVM for classification and multi-task learning, Proc 24th Int Conf Neural Inf Process Syst, 1620

titsias, 2011, Spike and slab variational inference for multi-task and multiple kernel learning, Proc 24th Int Conf Neural Inf Process Syst, 2339

10.1007/978-3-319-10599-4_7

10.1109/CVPR.2015.7298994

10.1561/2400000003

10.1109/TBDATA.2016.2573280

chen, 2018, Gradnorm: Gradient normalization for adaptive loss balancing in deep multitask networks, Proc Int Conf Mach Learn, 794

mrksic, 2015, Multi-domain dialog state tracking using recurrent neural networks, Proc Annual Meeting of the Assoc Computational Linguistics, 794

10.1007/s11263-014-0767-8

10.1145/2783258.2783377

wimalawarne, 2014, Multitask learning meets tensor factorization: Task imputation via convex optimization, Proc 27th Int Conf Neural Inf Process Syst, 2825

romera-paredes, 2013, Multilinear multitask learning, Proc 30th Int Conf Mach Learn, 1444

yu, 2020, Gradient surgery for multi-task learning, Proc Int Conf Neural Inf Process

sener, 2018, Multi-task learning as multi-objective optimization, Proc Int Conf Neural Inf Process, 525

10.1145/2939672.2939857

10.1109/TKDE.2017.2657624

liu, 2007, Semi-supervised multitask learning, Proc Int Conf Neural Inf Process, 937

10.1109/TPAMI.2008.296

yousefi, 2018, Local Rademacher complexity-based learning guarantees for multi-task learning, J Mach Learn Res, 19, 1

argyriou, 2009, When is there a representer theorem? Vector versus matrix regularizers, J Mach Learn Res, 10, 2507

argyriou, 2010, On spectral learning, J Mach Learn Res, 11, 935

lounici, 2009, Taking advantage of sparsity in multi-task learning, Proc Annu Conf Learn Theory

10.1214/09-AOS776

kolar, 2011, Union support recovery in multi-task learning, J Mach Learn Res, 12, 2415