Layerwise Optimization by Gradient Decomposition for Continual Learning
Open accessThe DOI matches its Crossref record; 25 of the 25 references it cites were found in a registry or an index.
Abstract
Deep neural networks achieve state-of-the-art and sometimes super-human performance across various domains. However, when learning tasks sequentially, the networks easily forget the knowledge of previous tasks, known as "catastrophic forgetting". To achieve the consistencies between the old tasks and the new task, one effective solution is to modify the gradient for update. Previous methods enforce independent gradient constraints for different tasks, while we consider these gradients contain complex information, and propose to leverage inter-task information by gradient decomposition. In particular, the gradient of an old task is decomposed into a part shared by all old tasks and a part specific to that task. The gradient for update should be close to the gradient of the new task, consistent with the gradients shared by all old tasks, and orthogonal to the space spanned by the gradients specific to the old tasks. In this way, our approach encourages common knowledge consolidation without impairing the task-specific knowledge. Furthermore, the optimization is performed for the gradients of each layer separately rather than the concatenation of all gradients as in previous works. This effectively avoids the influence of the magnitude variation of the gradients in different layers. Extensive experiments validate the effectiveness of both gradient-decomposed optimization and layer-wise updates. Our proposed method achieves state-of-the-art results on various benchmarks of continual learning.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472
Overcoming catastrophic forgetting in neural networks
Kirkpatrick, J., Pascanu, R., Rabinowitz, N., Veness, J., Desjardins, G., Rusu, A. A., Milan, K., Quan, J., Ramalho, T., Grabska-Barwinska, A., et al. (2017) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1611835114 · Cited by 7,899
Large-Scale Machine Learning with Stochastic Gradient Descent
Bottou, L. (2010) · Proceedings of COMPSTAT'2010 · doi:10.1007/978-3-7908-2604-3_16 · Cited by 5,795 · cited 1×
“Stochastic Gradient Descent is the most widely used optimization techniques for training DNNs [3, 31, 2].”
SGDR: Stochastic Gradient Descent with Warm Restarts
Loshchilov, I., & Hutter, F. (2016) · arXiv · doi:10.48550/arxiv.1608.03983 · Cited by 5,309
Li, Z., & Hoiem, D. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2773081 · Cited by 4,202
iCaRL: Incremental Classifier and Representation Learning
Rebuffi, S.-A., Kolesnikov, A., Sperl, G., & Lampert, C. H. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.587 · Cited by 3,988 · cited 6×
“The size of replay buffer is restricted to be 2000 images and the memory update strategy is the same as that in [38, 5] for fair comparison.”
InfluentialCatastrophic Interference in Connectionist Networks: The Sequential Learning Problem
McCloskey, M., & Cohen, N. J. (1989) · Psychology of Learning and Motivation · doi:10.1016/s0079-7421(08)60536-8 · Cited by 3,770
Continual lifelong learning with neural networks: A review
Parisi, G. I., Kemker, R., Part, J. L., Kanan, C., & Wermter, S. (2019) · Neural Networks · doi:10.1016/j.neunet.2019.01.012 · Cited by 3,117
Continual Learning Through Synaptic Intelligence
Zenke, F., Poole, B., & Ganguli, S. (2017) · arXiv · doi:10.48550/arxiv.1703.04200 · Cited by 1,784
Memory Aware Synapses: Learning What (not) to Forget
Aljundi, R., Babiloni, F., Elhoseiny, M., Rohrbach, M., & Tuytelaars, T. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01219-9_9 · Cited by 1,590
Gradient Episodic Memory for Continual Learning
Lopez-Paz, D., & Ranzato, M. (2017) · arXiv · doi:10.48550/arxiv.1706.08840 · Cited by 1,403
Continual Learning with Deep Generative Replay
Shin, H., Lee, J. K., Kim, J., & Kim, J. (2017) · arXiv · doi:10.48550/arxiv.1705.08690 · Cited by 1,385 · cited 1×
“This phenomenon, known as catastrophic forgetting , invokes more effective algorithms for continual learning (CL), the goal of which is to learn consecutive tasks without severe performance degradation on previous tasks [5, 30, 34, 38, 44, 43, 57, 57, 50].”
Large Scale Incremental Learning
Wu, Y., Chen, Y., Wang, L., Ye, Y., Liu, Z., Guo, Y., & Fu, Y. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00046 · Cited by 1,313
Learning a Unified Classifier Incrementally via Rebalancing
Hou, S., Pan, X., Loy, C. C., Wang, Z., & Lin, D. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00092 · Cited by 1,195 · cited 2×
“We compare our approach with other competing methods, including LWF [29], iCarl [38], DR [17], End2End [5], LUCR 2 [18], GD [26], MUC [11] and TPL [51].”
End-to-End Incremental Learning
Castro, F. M., Marín-Jiménez, M. J., Guil, N., Schmid, C., & Alahari, K. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01258-8_15 · Cited by 1,184
Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence
Chaudhry, A., Dokania, P. K., Ajanthan, T., & Torr, P. H. S. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01252-6_33 · Cited by 1,091 · cited 1×
“Following [6, 30, 7], we measure the performance by mean classification accuracy (ACC) and Backward Transfer (BWT).”
Efficient Lifelong Learning with A-GEM
Chaudhry, A., Ranzato, M., Rohrbach, M., & Elhoseiny, M. (2018) · arXiv · doi:10.48550/arxiv.1812.00420 · Cited by 852
Incremental Learning of Object Detectors without Catastrophic Forgetting
Shmelkov, K., Schmid, C., & Alahari, K. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.368 · Cited by 559
Variational Continual Learning
Nguyen, C. V., Li, Y., Bui, T. D., & Turner, R. E. (2017) · arXiv · doi:10.48550/arxiv.1710.10628 · Cited by 491 · cited 1×
“The former approaches, such as EWC [22], SI [55], MAS [1] and ALASSO [35] relied on different estimations of parameters importance, which was usually conducted by exhaustive search [42] or variational Bayesian methods [33, 56].”
Variational Continual Learning
Turner, R., Bui, T., Li, Y., & Cuong, N. (2019) · Apollo - University of Cambridge Repository · doi:10.17863/cam.35471 · Cited by 438
Re-evaluating Continual Learning Scenarios: A Categorization and Case for Strong Baselines
Hsu, Y.-C., Liu, Y.-C., Ramasamy, A., & Kira, Z. (2018) · arXiv · doi:10.48550/arxiv.1810.12488 · Cited by 211
Lifelong Learning via Progressive Distillation and Retrospection
Hou, S., Pan, X., Loy, C. C., Wang, Z., & Lin, D. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01219-9_27 · Cited by 190
Topology-Preserving Class-Incremental Learning
Tao, X., Chang, X., Hong, X., Wei, X., & Gong, Y. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58529-7_16 · Cited by 162 · cited 1×
“We compare our approach with other competing methods, including LWF [29], iCarl [38], DR [17], End2End [5], LUCR 2 [18], GD [26], MUC [11] and TPL [51].”
Cited by
A Comprehensive Survey of Continual Learning: Theory, Method and Application
Wang, L., Zhang, X., Su, H., & Zhu, J. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3367329 · Cited by 1,113
“LOGD [401] decomposes the gradient of each task into task-sharing and task-specific components to leverage inter-task information.”
BackgroundMethodInfluentialSelf-citationClass-Incremental Learning: A Survey
Zhou, D.-W., Wang, Q.-W., Qi, Z.-H., Ye, H.-J., Zhan, D.-C., & Liu, Z. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3429383 · Cited by 376
“LOGD [57] further decomposes the gradients into shared and task-specific ones.”
BackgroundInfluentialCatastrophic Forgetting in Deep Learning: A Comprehensive Taxonomy
Aleixo, E. L., Colonna, J. G., Cristo, M., & Fernandes, E. (2023) · arXiv · doi:10.48550/arxiv.2312.10549 · Cited by 54
Catastrophic Forgetting in Deep Learning: A Comprehensive Taxonomy
Aleixo, E. L., Colonna, J. G., Cristo, M., & Fernandes, E. (2024) · Journal of the Brazilian Computer Society · doi:10.5753/jbcs.2024.3966 · Cited by 54
Metadata
- Authors
- Tang, S., Chen, D., Zhu, J., Yu, S., & Ouyang, W.
- Venue
- 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2021-06
- Pages
- 9629-9638
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W3184046586
- Cited by
- 64
- References
- 25
- FWCI
- 5.31
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.