-
Notifications
You must be signed in to change notification settings - Fork 82
/
Copy pathbibtex.bib
3488 lines (3095 loc) · 141 KB
/
bibtex.bib
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
@article{rebuffi2017learning,
title={Learning multiple visual domains with residual adapters},
author={Rebuffi, Sylvestre-Alvise and Bilen, Hakan and Vedaldi, Andrea},
journal={Advances in neural information processing systems},
volume={30},
year={2017}
}
@inproceedings{bonicelli2022effectiveness,
title={On the Effectiveness of Lipschitz-Driven Rehearsal in Continual Learning},
author={Bonicelli, Lorenzo and Boschini, Matteo and Porrello, Angelo and Spampinato, Concetto and Calderara, Simone},
booktitle = {Advances in Neural Information Processing Systems 35},
year={2022},
url={https://arxiv.org/abs/2210.06443},
keywords={Rehearsal}
}
@article{boschini2022class,
author={Boschini, Matteo and Bonicelli, Lorenzo and Buzzega, Pietro and Porrello, Angelo and Calderara, Simone},
journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
title={Class-Incremental Continual Learning into the eXtended DER-verse},
year={2022},
publisher={IEEE},
url={https://arxiv.org/abs/2201.00766},
doi={https://doi.org/10.1109/TPAMI.2022.3206549},
keywords={Rehearsal, Distillation}
}
@inproceedings{rahman2022limitations,
title={On the Limitations of Continual Learning for Malware Classification},
author={Rahman, Mohammad Saidur and Coull, Scott E and Wright, Matthew},
booktitle={Conference on Lifelong Learning Agents (CoLLAs)},
year={2022},
url={https://arxiv.org/abs/2208.06568},
keywords={Applications}
}
@string(rahman2022limitations="This paper investigates overcoming catastrophic forgetting for malware classification")
@article{boschini2022continual,
title = {Continual semi-supervised learning through contrastive interpolation consistency},
journal = {Pattern Recognition Letters},
volume = {162},
pages = {9-14},
year = {2022},
issn = {0167-8655},
doi = {https://doi.org/10.1016/j.patrec.2022.08.006},
url={https://arxiv.org/abs/2108.06552},
author = {Boschini, Matteo and Buzzega, Pietro and Bonicelli, Lorenzo and Porrello, Angelo and Calderara, Simone},
keywords = {Rehearsal},
}
@inproceedings{boschini2022transfer,
title={Transfer without Forgetting},
author={Boschini, Matteo and Bonicelli, Lorenzo and Porrello, Angelo and Bellitto, Giovanni and Pennisi, Matteo and Palazzo, Simone and Spampinato, Concetto and Calderara, Simone},
booktitle={European Conference on Computer Vision},
year={2022},
url={https://arxiv.org/abs/2206.00388},
keywords={Rehearsal, Distillation}
}
@article{bagus2022study,
title={A Study of Continual Learning Methods for Q-Learning},
author={Bagus, Benedikt and Gepperth, Alexander},
journal={arXiv preprint arXiv:2206.03934},
year={2022},
url={https://arxiv.org/abs/2206.03934},
keywords={CRL, empirical},
}
@String{bagus2022study = "Studies Q-Learning methods in CRL environments. When there's no task interference, (A-)GEM can outperform Experience Replay"}
@article{wortsman2020supermasks,
title={Supermasks in superposition},
author={Wortsman, Mitchell and Ramanujan, Vivek and Liu, Rosanne and Kembhavi, Aniruddha and Rastegari, Mohammad and Yosinski, Jason and Farhadi, Ali},
journal={Advances in Neural Information Processing Systems},
volume={33},
pages={15173--15184},
year={2020},
url={https://arxiv.org/abs/2006.14769},
keywords={routing},
}
@String(wortsman2020supermasks="a binary mask over the network is inferred based on the input, and only the masked part of the network is used to train/infer")
@article{iyer2022avoiding,
title={Avoiding Catastrophe: Active Dendrites Enable Multi-Task Learning in Dynamic Environments},
author={Iyer, Abhiram and Grewal, Karan and Velu, Akash and Souza, Lucas Oliveira and Forest, Jeremy and Ahmad, Subutai},
journal={Frontiers in neurorobotics},
volume={16},
year={2022},
publisher={Frontiers Media SA},
url={https://www.frontiersin.org/articles/10.3389/fnbot.2022.846219/full},
keywords={bio, routing}
}
@String(iyer2022avoiding="bio-inspired method which dynamically restrict and route information in a context-specific manner")
@article{masse2018alleviating,
title={Alleviating catastrophic forgetting using context-dependent gating and synaptic stabilization},
author={Masse, Nicolas Y and Grant, Gregory D and Freedman, David J},
journal={Proceedings of the National Academy of Sciences},
volume={115},
number={44},
pages={E10467--E10475},
year={2018},
publisher={National Acad Sciences},
url={https://www.pnas.org/doi/pdf/10.1073/pnas.1803839115},
keywords={bio, routing}
}
@String(masse2018alleviating="a network trained to do CL where select subnetworks are used to learn each task; these subnetworks are chosen a priori")
@article{Sezener2021ARA,
title={A rapid and efficient learning rule for biological neural circuits},
author={Eren Sezener and Agnieszka Grabska-Barwinska and Dimitar Kostadinov and Maxime Beau and Sanjukta Krishnagopal and David Budden and Marcus Hutter and Joel Veness and Matthew M. Botvinick and Claudia Clopath and Michael H{\"a}usser and Peter E. Latham},
journal={bioRxiv},
year={2021},
url={https://www.biorxiv.org/content/10.1101/2021.03.10.434756v1.full.pdf},
keywords={bio}
}
@article{Kessler2021SameSD,
title={Same State, Different Task: Continual Reinforcement Learning without Interference},
author={Samuel Kessler and Jack Parker-Holder and Philip J. Ball and Stefan Zohren and Stephen J. Roberts},
journal={ArXiv},
year={2021},
volume={abs/2106.02940},
url={https://arxiv.org/abs/2106.02940},
keywords={TACRL}
}
@String(Kessler2021SameSD="learns multiple policies and cast policy-retrieval as a multi-arm bandit problem")
@inproceedings{
berseth2022comps,
title={Co{MPS}: Continual Meta Policy Search},
author={Glen Berseth and Zhiwei Zhang and Grace Zhang and Chelsea Finn and Sergey Levine},
booktitle={International Conference on Learning Representations},
year={2022},
url={https://openreview.net/forum?id=PVJ6j87gOHz},
keywords={TACRL}
}
@String(berseth2022comps="Co{MPS} is a novel meta-policy search algorithm for task-agnostic continual RL")
@article{caccia2022task,
title={Task-Agnostic Continual Reinforcement Learning: In Praise of a Simple Baseline},
author={Caccia, Massimo and Mueller, Jonas and Kim, Taesup and Charlin, Laurent and Fakoor, Rasool},
journal={arXiv preprint arXiv:2205.14495},
year={2022},
keywords={TACRL},
url={https://arxiv.org/abs/2205.14495}
}
@String(caccia2022task="combines replay and an RNN to set a simple baseline for TACRL: shows that the baselines matches and surpasses previously thought upper bounds")
@article{Xu2020TaskAgnosticOR,
title={Task-Agnostic Online Reinforcement Learning with an Infinite Mixture of Gaussian Processes},
author={Mengdi Xu and Wenhao Ding and Jiacheng Zhu and Zuxin Liu and Baiming Chen and Ding Zhao},
journal={ArXiv},
year={2020},
volume={abs/2006.11441},
url={https://arxiv.org/abs/2006.11441},
keywords={TACRL},
}
@String(Xu2020TaskAgnosticOR="uses an infinite mixture of Gaussian Processes to learn a task-agnostic policy")
@inproceedings{bellitto2022effects,
title={Effects of Auxiliary Knowledge on Continual Learning},
author={Bellitto, Giovanni and Pennisi, Matteo and Palazzo, Simone and Bonicelli, Lorenzo and Boschini, Matteo and Calderara, Simone and Spampinato, Concetto},
booktitle={International Conference on Pattern Recognition},
year={2022},
url={https://arxiv.org/abs/2206.02577},
keywords={Empirical Study, Rehearsal}
}
@article{hadsell2020embracing,
author = {Hadsell, Raia and Rao, Dushyant and Rusu, Andrei and Pascanu, Razvan},
year = {2020},
month = {12},
pages = {1028-1040},
title = {Embracing Change: Continual Learning in Deep Neural Networks},
volume = {24},
journal = {Trends in Cognitive Sciences},
doi = {10.1016/j.tics.2020.09.004},
keywords={Survey}
}
@inproceedings{
mendez2022modular,
title={Modular Lifelong Reinforcement Learning via Neural Composition},
author={Jorge A Mendez and Harm van Seijen and ERIC EATON},
booktitle={International Conference on Learning Representations},
year={2022},
url={https://openreview.net/forum?id=5XmLzdslFNN},
keywords={CRL, modular}
}
@article{berseth2021comps,
title={CoMPS: Continual Meta Policy Search},
author={Glen Berseth and Zhiwei Zhang and Grace Zhang and Chelsea Finn and Sergey Levine},
year={2021},
eprint={2112.04467},
archivePrefix={arXiv},
primaryClass={cs.LG},
url={https://arxiv.org/abs/2112.04467},
keywords={CRL, TACRL}
}
@article{mendez2020lifelong,
title={Lifelong Policy Gradient Learning of Factored Policies for Faster Training Without Forgetting},
author={Jorge A. Mendez and Boyu Wang and Eric Eaton},
year={2020},
eprint={2007.07011},
archivePrefix={arXiv},
journal={NeurIPS 2020},
primaryClass={cs.LG},
url={https://arxiv.org/abs/2007.07011},
keywords={CRL}
}
@inproceedings{pierre2018incremental,
author={Pierre, John M.},
booktitle={2018 21st International Conference on Intelligent Transportation Systems (ITSC)},
title={Incremental Lifelong Deep Learning for Autonomous Vehicles},
year={2018},
volume={},
number={},
pages={3949-3954},
doi={10.1109/ITSC.2018.8569992},
keywords={Applications},
url={https://ieeexplore.ieee.org/document/8569992},
}
@article{kirichenko2021taskagnostic,
title={Task-agnostic Continual Learning with Hybrid Probabilistic Models},
author={Polina Kirichenko and Mehrdad Farajtabar and Dushyant Rao and Balaji Lakshminarayanan and Nir Levine and Ang Li and Huiyi Hu and Andrew Gordon Wilson and Razvan Pascanu},
year={2021},
eprint={2106.12772},
archivePrefix={arXiv},
primaryClass={cs.LG},
url={https://arxiv.org/abs/2106.12772},
keywords={TACL}
}
@article{javed2020learning,
title={Learning causal models online},
author={Javed, Khurram and White, Martha and Bengio, Yoshua},
journal={arXiv preprint arXiv:2006.07461},
year={2020},
url={https://arxiv.org/abs/2006.07461},
keywords={Misc}
}
@article{von2021learning,
title={Learning where to learn: Gradient sparsity in meta and continual learning},
author={Von Oswald, Johannes and Zhao, Dominic and Kobayashi, Seijin and Schug, Simon and Caccia, Massimo and Zucchet, Nicolas and Sacramento, Jo{\~a}o},
journal={Advances in Neural Information Processing Systems},
volume={34},
year={2021},
url={https://proceedings.neurips.cc/paper/2021/hash/2a10665525774fa2501c2c8c4985ce61-Abstract.html},
keywords={Meta-Continual Learning, Continual-Meta Learning, TACL}
}
@inproceedings{buzzega2021rethinking,
author={Buzzega, Pietro and Boschini, Matteo and Porrello, Angelo and Calderara, Simone},
booktitle={2020 25th International Conference on Pattern Recognition (ICPR)},
title={Rethinking Experience Replay: a Bag of Tricks for Continual Learning},
year={2021},
volume={},
number={},
pages={2180-2187},
doi={10.1109/ICPR48806.2021.9412614},
url={https://ieeexplore.ieee.org/abstract/document/9412614},
keywords={Rehearsal, Empirical Study}
}
@incollection{buzzega2020dark,
author = {Buzzega, Pietro and Boschini, Matteo and Porrello, Angelo and Abati, Davide and Calderara, Simone},
booktitle = {Advances in Neural Information Processing Systems 33},
editor = {H. Larochelle and M. Ranzato and R. Hadsell and M. F. Balcan and H. Lin},
pages = {15920--15930},
publisher = {Curran Associates, Inc.},
title = {Dark Experience for General Continual Learning: a Strong, Simple Baseline},
year = {2020},
url={https://papers.nips.cc/paper/2020/file/b704ea2c39778f07c617f6b7ce480e9e-Paper.pdf},
keywords={Rehearsal, Distillation}
}
@inproceedings{prabhu2020gdumb,
title={GDumb: A simple approach that questions our progress in continual learning},
author={Prabhu, Ameya and Torr, Philip HS and Dokania, Puneet K},
booktitle={European Conference on Computer Vision},
pages={524--540},
year={2020},
organization={Springer},
keywords={Empirical Study, Rehearsal}
}
@String(prabhu2020gdumb="introduces a super simple methods that outperforms almost all methods in all of the CL benchmarks. We need new better benchamrks")
@article{khetarpal2020continual,
title={Towards Continual Reinforcement Learning: A Review and Perspectives},
author={Khimya Khetarpal and Matthew Riemer and Irina Rish and Doina Precup},
year={2020},
eprint={2012.13490},
archivePrefix={arXiv},
keywords={Survey, Reinforcement},
primaryClass={cs.LG}
}
@String(khetarpal2020continual="A review on continual reinforcement learning")
@inproceedings{ostapenko2019learning,
title={Learning to remember: A synaptic plasticity driven framework for continual learning},
author={Ostapenko, Oleksiy and Puscas, Mihai and Klein, Tassilo and Jahnichen, Patrick and Nabi, Moin},
booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
pages={11321--11329},
year={2019},
url={https://openaccess.thecvf.com/content_CVPR_2019/html/Ostapenko_Learning_to_Remember_A_Synaptic_Plasticity_Driven_Framework_for_Continual_CVPR_2019_paper.html},
keywords={Generative Replay}
}
@String(ostapenko2019learning="introdudes Dynamic generative memory (DGM) which relies on conditional generative adversarial networks with learnable connection plasticity realized with neural masking")
@inproceedings{Gupta2020LaMAMLLM,
title={La-MAML: Look-ahead Meta Learning for Continual Learning},
author={Gunshi Gupta and Karmesh Yadav and Liam Paull},
url={https://arxiv.org/abs/2007.13904},
year={2020},
keywords={"Meta-Continual Learning"}
}
@String(Gupta2020LaMAMLLM="Proposes an online replay-based meta-continual learning algorithm with learning-rate modulation to mitigate catastrophic forgetting")
@article{Ren2020WanderingWA,
title={Wandering Within a World: Online Contextualized Few-Shot Learning},
author={Mengye Ren and Michael L. Iuzzolino and Michael C. Mozer and Richard S. Zemel},
journal={ArXiv},
year={2020},
volume={abs/2007.04546},
url={https://arxiv.org/abs/2007.04546},
keywords={Continual Few-Shot Learning, Setting}
}
@String(Ren2020WanderingWA="proposes a new continual few-shot setting where spacial and temporal context can be leveraged to and unseen classes need to be predicted")
@article{lesort2020continual,
title={Continual Learning: Tackling Catastrophic Forgetting in Deep Neural Networks with Replay Processes},
author={Timothée Lesort},
year={2020},
eprint={2007.00487},
archivePrefix={arXiv},
primaryClass={cs.LG},
url={https://arxiv.org/abs/2007.00487},
keywords={Thesis, Rehearsal, Generative Replay},
}
@article{clicml2020,
title={Workshop on Continual Learning at ICML 2020},
author={Rahaf Aljundi and Haytham Fayek and Eugene Belilovsky and David Lopez-Paz and Arslan Chaudhry and Marc Pickett and Puneet Dokania and Jonathan Schwarz and Sayna Ebrahimi},
journal={ICML},
year={2020},
url={https://sites.google.com/view/cl-icml/organizers?authuser=0},
keywords={Workshops},
}
@article{lifelongml2020,
title={4th Lifelong Machine Learning Workshop at ICML 2020},
author={Shagun Sodhani and Sarath Chandar and Balaraman Ravindran and Doina Precup},
journal={ICML},
year={2020},
url={https://openreview.net/group?id=ICML.cc/2020/Workshop/LifelongML#accept},
keywords={Workshops},
}
@article{antoniou2020defining,
title={Defining Benchmarks for Continual Few-Shot Learning},
author={Antoniou, Antreas and Patacchiola, Massimiliano and Ochal, Mateusz and Storkey, Amos},
journal={arXiv preprint arXiv:2004.11967},
year={2020},
url={https://arxiv.org/abs/2004.11967},
keywords={Continual Few-Shot Learning, Setting},
}
@String(antoniou2020defining="(title is a good enough summary)")
@article{ahmad2017unsupervised,
title={Unsupervised real-time anomaly detection for streaming data},
author={Ahmad, Subutai and Lavin, Alexander and Purdy, Scott and Agha, Zuha},
journal={Neurocomputing},
volume={262},
pages={134--147},
year={2017},
publisher={Elsevier},
url={https://www.sciencedirect.com/science/article/pii/S0925231217309864},
keywords={Applications}
}
@String(ahmad2017unsupervised="HTM applied to real-world anomaly detection problem")
@article{cui2016continuous,
title={Continuous online sequence learning with an unsupervised neural network model},
author={Cui, Yuwei and Ahmad, Subutai and Hawkins, Jeff},
journal={Neural computation},
volume={28},
number={11},
pages={2474--2504},
year={2016},
publisher={MIT Press},
url={https://arxiv.org/abs/1512.05463},
keywords={Applications}
}
@String(cui2016continuous="HTM applied to a prediction problem of taxi passenger demand")
@article{kiyasseh2020clops,
title={CLOPS: Continual Learning of Physiological Signals},
author={Kiyasseh, Dani and Zhu, Tingting and Clifton, David A},
journal={arXiv preprint arXiv:2004.09578},
year={2020},
url={https://arxiv.org/abs/2004.09578},
keywords={Applications}
}
@String(kiyasseh2020clops="a healthcare-specific replay-based method to mitigate destructive interference during continual learning")
@article{vanbrain,
title={Brain-Like Replay For Continual Learning With Artificial Neural Networks},
author={van de Ven, Gido M and Siegelmann, Hava T and Tolias, Andreas S},
year={2020},
url={https://baicsworkshop.github.io/pdf/BAICS_8.pdf},
keywords={Generative Replay},
}
@incollection{Thrun95,
title={Lifelong robot learning},
author={Thrun, Sebastian and Mitchell, Tom M},
booktitle={The biology and technology of intelligent autonomous agents},
pages={165--196},
year={1995},
publisher={Springer},
keywords={Classics, Robotics},
url={http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.71.3723&rep=rep1&type=pdf}
}
@String(Thrun95="Argues knowledge transfer is essential if robots are to learn control with moderate learning times")
@article{Farquhar18,
title={Towards Robust Evaluations of Continual Learning},
author={Farquhar, Sebastian and Gal, Yarin},
journal={arXiv preprint arXiv:1805.09733},
year={2018},
keywords={Influentials, Empirical Study},
url={https://arxiv.org/abs/1805.09733},
}
@String(Farquhar18="Proposes desideratas and reexamines the evaluation protocol")
@inproceedings{Chaudhry19,
title={Efficient Lifelong Learning with A-GEM},
author={Chaudhry, Arslan and Ranzato, Marc’Aurelio and Rohrbach, Marcus and Elhoseiny, Mohamed},
booktitle={ICLR},
year={2019},
url={https://arxiv.org/abs/1812.00420},
keywords={Rehearsal, Influential}
}
@String(Chaudhry19="More efficient GEM; Introduces online continual learning")
@article{kirkpatrick2017overcoming,
title={Overcoming catastrophic forgetting in neural networks},
author={Kirkpatrick, James and Pascanu, Razvan and Rabinowitz, Neil and Veness, Joel and Desjardins, Guillaume and Rusu, Andrei A and Milan, Kieran and Quan, John and Ramalho, Tiago and Grabska-Barwinska, Agnieszka and others},
journal={Proc. of the national academy of sciences},
year={2017},
publisher={National Acad Sciences},
keywords={Regularization, Influential, General},
url={https://www.pnas.org/content/pnas/114/13/3521.full.pdf},
}
@String(Kirkpatrick17="Introduces prior-focused methods (Elastic Weight Consolidation)")
@incollection{Lopez-Paz17,
title={Gradient Episodic Memory for Continual Learning},
author={Lopez-Paz, David and Ranzato, Marc-Aurelio},
booktitle={Advances in Neural Information Processing Systems 30},
editor={I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
pages={6467--6476},
year={2017},
publisher={Curran Associates, Inc.},
url={http://papers.nips.cc/paper/7225-gradient-episodic-memory-for-continual-learning.pdf},
keywords={Rehearsal, Influential}
}
@String(Lopez-Paz17="A model that alliviates CF via constrained optimization")
@inproceedings{shin2017continual,
title={Continual learning with deep generative replay},
author={Shin, Hanul and Lee, Jung Kwon and Kim, Jaehong and Kim, Jiwon},
booktitle={Advances in Neural Information Processing Systems},
pages={2990--2999},
year={2017},
keywords={Generative Replay, Influential},
url={https://arxiv.org/abs/1705.08690},
}
@String(shin2017continual="Introduces generative replay")
@ARTICLE{Goodfellow13,
author={Goodfellow, I.~J. and Mirza, M. and Xiao, D. and Courville, A. and Bengio, Y.},
title="An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks",
journal={ArXiv e-prints},
archivePrefix="arXiv",
eprint={1312.6211},
primaryClass="stat.ML",
keywords={Statistics - Machine Learning, Computer Science - Learning, Computer Science - Neural and Evolutionary Computing, Empirical Study, Influential},
year={2013},
month={dec},
adsurl={http://adsabs.harvard.edu/abs/2013arXiv1312.6211G},
adsnote={Provided by the SAO/NASA Astrophysics Data System},
url={https://arxiv.org/abs/1312.6211},
}
@String(Goodfellow13="Investigates CF in neural networks")
@article{deLange2019continual,
title={Continual learning: A comparative study on how to defy forgetting in classification tasks},
author={Matthias De Lange and Rahaf Aljundi and Marc Masana and Sarah Parisot and Xu Jia and Ales Leonardis and Gregory Slabaugh and Tinne Tuytelaars},
year={2019},
eprint={1909.08383},
archivePrefix={arXiv},
primaryClass={cs.CV},
keywords="Empirical Study",
url={https://arxiv.org/abs/1909.08383},
}
@String(deLange2019continual="Extensive empirical study of CL methods (in the multi-head setting)")
@article{Parisi18review,
title="Continual lifelong learning with neural networks: A review",
journal="Neural Networks",
volume="113",
pages="54 - 71",
year="2019",
issn="0893-6080",
doi="https://doi.org/10.1016/j.neunet.2019.01.012",
url="http://www.sciencedirect.com/science/article/pii/S0893608019300231",
author="German I. Parisi and Ronald Kemker and Jose L. Part and Christopher Kanan and Stefan Wermter",
keywords="Continual learning, Lifelong learning, Catastrophic forgetting, Developmental systems, Memory consolidation, Survey"
}
@String(Parisi18review="An extensive review of CL")
@inproceedings{hung2019compacting,
title={Compacting, Picking and Growing for Unforgetting Continual Learning},
author={Hung, Ching-Yi and Tu, Cheng-Hao and Wu, Cheng-En and Chen, Chien-Hung and Chan, Yi-Ming and Chen, Chu-Song},
booktitle={Advances in Neural Information Processing Systems},
pages={13647--13657},
year={2019},
keywords={Hybrid},
url={https://arxiv.org/abs/1910.06562}
}
@String(hung2019compacting="Approach leverages the principles of deep model compression, critical weights selection, and progressive networks expansion. All enforced in an iterative manner")
@article{Swaroop2019ImprovingAU,
title={Improving and Understanding Variational Continual Learning},
author={Siddharth Swaroop and Cuong V. Nguyen and Thang D. Bui and Richard E. Turner},
journal={ArXiv},
year={2019},
volume={abs/1905.02099},
keywords={Regularization},
url="https://arxiv.org/abs/1905.02099"
})
@String(Swaroop2019ImprovingAU="Improved results and interpretation of VCL.")
@inproceedings{Ebrahimi2020Uncertainty-guided,
title={Uncertainty-guided Continual Learning with Bayesian Neural Networks},
author={Sayna Ebrahimi and Mohamed Elhoseiny and Trevor Darrell and Marcus Rohrbach},
booktitle={International Conference on Learning Representations},
year={2020},
url={https://openreview.net/forum?id=HklUCCVKDB},
keywords={TACL}
}
@String(Ebrahimi2020Uncertainty-guided="Uses Bayes by Backprop for variational Continual Learning.")
@incollection{NIPS2019_8690,
title={Uncertainty-based Continual Learning with Adaptive Regularization},
author={Ahn, Hongjoon and Cha, Sungmin and Lee, Donggyu and Moon, Taesup},
booktitle={Advances in Neural Information Processing Systems 32},
editor={H. Wallach and H. Larochelle and A. Beygelzimer and F. d\textquotesingle Alch\'{e}-Buc and E. Fox and R. Garnett},
pages={4394--4404},
year={2019},
publisher={Curran Associates, Inc.},
url={http://papers.nips.cc/paper/8690-uncertainty-based-continual-learning-with-adaptive-regularization.pdf},
keywords={Regularization}
}
@String(NIPS2019_8690="Introduces VCL with uncertainty measured for neurons instead of weights.")
@article{zeno2018task,
title={Task Agnostic Continual Learning Using Online Variational Bayes},
author={Chen Zeno and Itay Golan and Elad Hoffer and Daniel Soudry},
year={2018},
eprint={1803.10123},
archivePrefix={arXiv},
primaryClass={stat.ML},
keywords={Regularization, TACL},
url={https://arxiv.org/pdf/1803.10123.pdf}
}
@String(zeno2018task="Introduces an optimizer for CL that relies on closed form updates of mu and sigma of BNN; introduce label trick for class learning (single-head) but warning: it isn't really task-agnostic")
@article{DBLP:journals/corr/abs-1902-09432,
author ={Jaehong Yoon and
Saehoon Kim and
Eunho Yang and
Sung Ju Hwang},
title ={ORACLE: Order Robust Adaptive Continual Learning},
journal ={CoRR},
volume ={abs/1902.09432},
year ={2019},
url ={http://arxiv.org/abs/1902.09432},
archivePrefix={arXiv},
eprint ={1902.09432},
timestamp={Tue, 21 May 2019 18:03:36 +0200},
biburl ={https://dblp.org/rec/journals/corr/abs-1902-09432.bib},
bibsource={dblp computer science bibliography, https://dblp.org},
keywords={Dynamic Architecture}
}
@article{Rajasegaran2019Random,
title={Random path selection for incremental learning},
author={Rajasegaran, Jathushan and Hayat, Munawar and Khan, Salman and Khan, Fahad Shahbaz and Shao, Ling},
journal={Advances in Neural Information Processing Systems},
year={2019}
}
@String(Rajasegaran2019Random="Proposes a random path selection algorithm, called RPSnet, that progressively chooses optimal paths for the new tasks while encouraging parameter sharing and reuse")
@inproceedings{He18,
title={Overcoming Catastrophic Interference using Conceptor-Aided Backpropagation},
author={Xu He and Herbert Jaeger},
booktitle={International Conference on Learning Representations},
year={2018},
url={https://openreview.net/forum?id=B1al7jg0b},
keywords={Regularization}
}
@String(He18="Conceptor-Aided Backprop (CAB): gradients are shielded by conceptors against degradation of previously learned tasks")
@inproceedings{Pentina15,
title={Lifelong learning with non-iid tasks},
author={Pentina, Anastasia and Lampert, Christoph H},
booktitle={Advances in Neural Information Processing Systems},
pages={1540--1548},
year={2015},
keywords={}
}
@article{serra2018overcoming,
title= {Overcoming Catastrophic Forgetting with Hard Attention to the Task},
author= {Serra, Joan and Suris, Didac and Miron, Marius and Karatzoglou, Alexandros},
journal ={ICML},
booktitle= {Proceedings of the 35th International Conference on Machine Learning},
pages= {4548--4557},
year= {2018},
editor= {Dy, Jennifer and Krause, Andreas},
volume= {80},
series= {Proceedings of Machine Learning Research},
address= {Stockholmsmässan, Stockholm Sweden},
month= {10--15 Jul},
publisher= {PMLR},
pdf= {http://proceedings.mlr.press/v80/serra18a/serra18a.pdf},
url= {http://proceedings.mlr.press/v80/serra18a.html},
keywords={Regularization}
}
@String(serra2018overcoming="Introducing a hard attention idea with binary masks")
@inproceedings{chaudhry2018riemannian,
title={Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence},
author={Chaudhry, Arslan and Dokania, Puneet K and Ajanthan, Thalaiyasingam and Torr, Philip HS},
booktitle={ECCV},
year={2018},
keywords={Regularization},
url={https://arxiv.org/abs/1801.10112}
}
@String(chaudhry2018riemannian="Formalizes the shortcomings of multi-head evaluation, as well as the importance of replay in single-head setup. Presenting an improved version of EWC.")
@article{Aljundi17,
author ={Rahaf Aljundi and Francesca Babiloni and Mohamed Elhoseiny and Marcus Rohrbach and Tinne Tuytelaars},
title ={Memory Aware Synapses: Learning what (not) to forget},
journal ={CoRR},
volume ={abs/1711.09601},
year ={2017},
url ={http://arxiv.org/abs/1711.09601},
archivePrefix={arXiv},
eprint ={1711.09601},
timestamp={Mon, 13 Aug 2018 16:47:14 +0200},
biburl ={https://dblp.org/rec/bib/journals/corr/abs-1711-09601},
bibsource={dblp computer science bibliography, https://dblp.org},
keywords={Regularization}
}
@String(Aljundi17="Importance of parameter measured based on their contribution to change in the learned prediction function")
@inproceedings{nguyen2017variational,
title={Variational Continual Learning},
author={Cuong V. Nguyen and Yingzhen Li and Thang D. Bui and Richard E. Turner},
booktitle={International Conference on Learning Representations},
year={2018},
keywords={Regularization},
url={https://arxiv.org/abs/1710.10628}
}
@String(Nguyen17="Introduces the idea of using previous task's posterior as the new task's prior in a BNN.")
@inproceedings{schwarz2018progress,
title={Progress \& compress: A scalable framework for continual learning},
author={Schwarz, Jonathan and Luketina, Jelena and Czarnecki, Wojciech M and Grabska-Barwinska, Agnieszka and Teh, Yee Whye and Pascanu, Razvan and Hadsell, Raia},
booktitle={ICML},
year={2018},
keywords={Regularization},
url={https://arxiv.org/abs/1805.06370}
}
@String(schwarz2018progress="A new P\&C architecture; online EWC for keeping the knowledge about the previous task, knowledge for keeping the knowledge about the current task (Multi-head setting, RL)")
@InProceedings{Zenke17,
title= {Continual Learning Through Synaptic Intelligence},
author= {Zenke, Friedeman and Poole, Ben and Ganguli, Surya },
booktitle= {Proceedings of the 34th International Conference on Machine Learning},
pages= {3987--3995},
year= {2017},
editor= {Doina Precup and Yee Whye Teh},
volume= {70},
series= {Proceedings of Machine Learning Research},
address= {International Convention Centre, Sydney, Australia},
month= {06--11 Aug},
publisher= {PMLR},
pdf= {http://proceedings.mlr.press/v70/zenke17a/zenke17a.pdf},
url= {http://proceedings.mlr.press/v70/zenke17a.html},
keywords={Regularization}
}
@String(Zenke17="Synaptic Intelligence (SI). Importance of parameter measured based on their contribution to change in the loss. ")
@article{Li17learning,
title={Learning without forgetting},
author={Li, Zhizhong and Hoiem, Derek},
journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
year={2017},
publisher={IEEE},
keywords={Distillation},
url={https://arxiv.org/abs/1606.09282}
}
@String(Li17learning="Functional regularization through distillation (keeping the output of the updated network on the new data close to the output of the old network on the new data)")
@article{li2019continual,
title={Continual Learning Using Bayesian Neural Networks},
author={HongLin Li and Payam Barnaghi and Shirin Enshaeifar and Frieder Ganz},
year={2019},
eprint={1910.04112},
archivePrefix={arXiv},
primaryClass={cs.LG},
keywords={}
}
@article{
rosenfeld2018incremental,
title={Incremental Learning through Deep Adaptation},
author={Amir Rosenfeld and John K. Tsotsos},
year={2018},
url={https://openreview.net/forum?id=ryj0790hb},
keywords={Dynamic Architecture}
}
@ARTICLE{Rusu16progressive,
author={Rusu, A.~A. and Rabinowitz, N.~C. and Desjardins, G. and
Soyer, H. and Kirkpatrick, J. and Kavukcuoglu, K. and
Pascanu, R. and Hadsell, R.},
title={Progressive Neural Networks},
journal={ArXiv e-prints},
archivePrefix="arXiv",
eprint={1606.04671},
primaryClass="cs.LG",
keywords={Computer Science - Learning, Dynamic Architecture},
year=2016,
month={jun},
adsurl={http://adsabs.harvard.edu/abs/2016arXiv160604671R},
adsnote={Provided by the SAO/NASA Astrophysics Data System},
url={https://arxiv.org/abs/1606.04671}
}
@String(Rusu16progressive="Each task have a specific model connected to the previous ones")
@article{Rusu16sim2real,
author = {Andrei A. Rusu and
Matej Vecerik and
Thomas Roth{\"{o}}rl and
Nicolas Heess and
Razvan Pascanu and
Raia Hadsell},
title = {Sim-to-Real Robot Learning from Pixels with Progressive Nets},
journal = {CoRR},
volume = {abs/1610.04286},
year = {2016},
url = {http://arxiv.org/abs/1610.04286},
archivePrefix = {arXiv},
eprint = {1610.04286},
timestamp = {Mon, 13 Aug 2018 16:48:16 +0200},
biburl = {https://dblp.org/rec/bib/journals/corr/RusuVRHPH16},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{farajtabar2019orthogonal,
title={Orthogonal Gradient Descent for Continual Learning},
author={Mehrdad Farajtabar and Navid Azizan and Alex Mott and Ang Li},
year={2019},
eprint={1910.07104},
archivePrefix={arXiv},
primaryClass={cs.LG},
keywords={Rehearsal},
url={https://arxiv.org/abs/1910.07104},
}
@String(farajtabar2019orthogonal="projecting the gradients from new tasks onto a subspace in which the neural network output on previous task does not change and the projected gradient is still in a useful direction for learning the new task")
@incollection{Aljundi2019Gradient,
title={Gradient based sample selection for online continual learning},
author={Aljundi, Rahaf and Lin, Min and Goujaud, Baptiste and Bengio, Yoshua},
booktitle={Advances in Neural Information Processing Systems 32},
editor={H. Wallach and H. Larochelle and A. Beygelzimer and F. d\textquotesingle Alch\'{e}-Buc and E. Fox and R. Garnett},
pages={11816--11825},
year={2019},
publisher={Curran Associates, Inc.},
url={http://papers.nips.cc/paper/9354-gradient-based-sample-selection-for-online-continual-learning.pdf},
keywords={Rehearsal}
}
@String(Aljundi2019Gradient="sample selection as a constraint reduction problem based on the constrained optimization view of continual learning")
@incollection{aljundi2019online,
title ={Online Continual Learning with Maximal Interfered Retrieval},
author={Aljundi, Rahaf and
, Lucas and Belilovsky, Eugene and Caccia, Massimo and Lin, Min and Charlin, Laurent and Tuytelaars, Tinne},
booktitle={Advances in Neural Information Processing Systems 32},
editor={H. Wallach and H. Larochelle and A. Beygelzimer and F. d\textquotesingle Alch\'{e}-Buc and E. Fox and R. Garnett},
pages={11849--11860},
year={2019},
publisher={Curran Associates, Inc.},
url={http://papers.nips.cc/paper/9357-online-continual-learning-with-maximal-interfered-retrieval.pdf},
keywords={Rehearsal}
}
@String(aljundi2019online="Controlled sampling of memories for replay to automatically rehearse on tasks currently undergoing the most forgetting")
@article{caccia2019online,
title={Online Learned Continual Compression with Adaptative Quantization Module},
author={Caccia, Lucas and Belilovsky, Eugene and Caccia, Massimo and Pineau, Joelle},
journal={arXiv preprint arXiv:1911.08019},
year={2019},
keywords={Rehearsal},
url={https://arxiv.org/abs/1911.08019}
}
@String(caccia2019online="Uses stacks of VQ-VAE modules to progressively compress the data stream, enabling better rehearsal")
@article{Ven2018GenerativeRW,
title={Generative replay with feedback connections as a general strategy for continual learning},
author={Michiel van der Ven and Andreas S. Tolias},
journal={ArXiv},
year={2018},
volume={abs/1809.10635},
keywords={Generative Replay},
url={https://arxiv.org/abs/1809.10635}
}
@String(Ven2018GenerativeRW="smarter Generative Replay")
@incollection{Javed2019Meta,
title={Meta-Learning Representations for Continual Learning},
author={Javed, Khurram and White, Martha},
booktitle={Advances in Neural Information Processing Systems 32},
editor={H. Wallach and H. Larochelle and A. Beygelzimer and F. d\textquotesingle Alch\'{e}-Buc and E. Fox and R. Garnett},
pages={1818--1828},
year={2019},
publisher={Curran Associates, Inc.},
url={http://papers.nips.cc/paper/8458-meta-learning-representations-for-continual-learning.pdf},
keywords={Meta-Continual Learning}
}
@String(Javed2019Meta="Introduces Learns how to continually learn (OML) i.e. learns how to do online updates without forgetting.")
@article{luo2019learning,
title={Learning from the Past: Continual Meta-Learning via Bayesian Graph Modeling},
author={Yadan Luo and Zi Huang and Zheng Zhang and Ziwei Wang and Mahsa Baktashmotlagh and Yang Yang},
year={2019},
eprint={1911.04695},
archivePrefix={arXiv},
primaryClass={cs.LG},
keywords={Continual-Meta Learning},
url={https://arxiv.org/abs/1911.04695}
}
@inproceedings{
Kurle2020Continual,
title={Continual Learning with Bayesian Neural Networks for Non-Stationary Data},
author={Richard Kurle and Botond Cseke and Alexej Klushyn and Patrick van der Smagt and Stephan Günnemann},
booktitle={International Conference on Learning Representations},
year={2020},
url={https://openreview.net/forum?id=SJlsFpVtDB},
keywords={Regularization}
}
@String(Kurle2020Continual="continual learning for non-stationary data using Bayesian neural networks and memory-based online variational Bayes")
@InProceedings{pmlr-v97-finn19a,
title= {Online Meta-Learning},
author= {Finn, Chelsea and Rajeswaran, Aravind and Kakade, Sham and Levine, Sergey},
booktitle= {Proceedings of the 36th International Conference on Machine Learning},
pages= {1920--1930},
year= {2019},
editor= {Chaudhuri, Kamalika and Salakhutdinov, Ruslan},
volume= {97},
series= {Proceedings of Machine Learning Research},
address= {Long Beach, California, USA},
month= {09--15 Jun},
publisher= {PMLR},
pdf= {http://proceedings.mlr.press/v97/finn19a/finn19a.pdf},
url= {http://proceedings.mlr.press/v97/finn19a.html},
keywords={Continual-Meta Learning}
}
@String(pmlr-v97-finn19a="defines Online Meta-learning; propsoses Follow the Meta Leader (FTML) (~ Online MAML)")
@incollection{NIPS2019_9112,
title={Reconciling meta-learning and continual learning with online mixtures of tasks},
author={Jerfel, Ghassen and Grant, Erin and Griffiths, Tom and Heller, Katherine A},
booktitle={Advances in Neural Information Processing Systems 32},
editor={H. Wallach and H. Larochelle and A. Beygelzimer and F. d\textquotesingle Alch\'{e}-Buc and E. Fox and R. Garnett},
pages={9119--9130},
year={2019},
publisher={Curran Associates, Inc.},
url={http://papers.nips.cc/paper/9112-reconciling-meta-learning-and-continual-learning-with-online-mixtures-of-tasks.pdf},
keywords={Continual-Meta Learning}
}
@String(NIPS2019_9112="Meta-learns a tasks structure; continual adaptation via non-parametric prior")
@inproceedings{
nagabandi2018deep,
title={Deep Online Learning Via Meta-Learning: Continual Adaptation for Model-Based RL},
author={Anusha Nagabandi and Chelsea Finn and Sergey Levine},
booktitle={International Conference on Learning Representations},
year={2019},
url={https://openreview.net/forum?id=HyxAfnA5tm},
keywords={Lifelong Reinforcement Learning, TACRL, Continual-Meta }
}
@String(nagabandi2018deep="Formulates an online learning procedure that uses SGD to update model parameters, and an EM with a Chinese restaurant process prior to develop and maintain a mixture of models to handle non-stationary task distribution")
@article{rao2019continual,
title={Continual Unsupervised Representation Learning},
author={Dushyant Rao and Francesco Visin and Andrei A. Rusu and Yee Whye Teh and Razvan Pascanu and Raia Hadsell},
year={2019},
eprint={1910.14481},
archivePrefix={arXiv},
primaryClass={cs.LG},
keywords={Generative Modeling, TACL},
url={https://arxiv.org/pdf/1910.14481.pdf}
}
@String(rao2019continual="Introduces unsupervised continual learning (no task label and no task boundaries)")
@inproceedings{lesort2018generative,
title={Generative Models from the perspective of Continual Learning},
AUTHOR={Lesort, Timothée and Caselles-Dupré, Hugo and Garcia-Ortiz, Michael and Goudou, Jean-Fran{\c c}ois and Filliat, David},
URL={https://hal.archives-ouvertes.fr/hal-01951954},
booktitle={IJCNN - International Joint Conference on Neural Networks},
ADDRESS={Budapest, Hungary},
year={2019},
MONTH={Jul},
PDF={https://hal.archives-ouvertes.fr/hal-01951954/file/_NIPS_CL_Workshop__Continual_learning_for_generative_models.pdf},
HAL_ID={hal-01951954},
keywords={"Generative Modeling", "Generative Replay"},
HAL_VERSION={v1},
}
@String(lesort2018generative="Extensive evaluation of CL methods for generative modeling")
@article{ramapuram2017lifelong,
title={Lifelong Generative Modeling},
author={Ramapuram, Jason and Gregorova, Magda and Kalousis, Alexandros},
journal={arXiv preprint arXiv:1705.09847},
year={2017},
keywords={Generative Modeling},
url={https://arxiv.org/abs/1705.09847}
}
@String(Ramapuram17="first to focus on continual generative modeling (DGR's focus was still on continual supervised learning)")
@inproceedings{Alet2018ModularM,
title={Modular meta-learning},
author={Ferran Alet and Tom{\'a}s Lozano-Pérez and Leslie Pack Kaelbling},
booktitle={CoRL},
year={2018},
keywords={}
}
@inproceedings{
toneva2018an,
title={An Empirical Study of Example Forgetting during Deep Neural Network Learning},
author={Mariya Toneva and Alessandro Sordoni and Remi Tachet des Combes and Adam Trischler and Yoshua Bengio and Geoffrey J. Gordon},
booktitle={International Conference on Learning Representations},
year={2019},