Related work

The foundational work on continual learning, 1980 to 2026: methods, theory, benchmarks, surveys, and the neuroscience of memory. Updated weekly; some carry our notes.

187 papers of 8,653 · showing 151–187Sort Recent · Most cited

2018 Clear all

2018
Riemannian Walk for Incremental Learning: Understanding Forgetting and IntransigenceArslan Chaudhry, Puneet K. Dokania, Thalaiyasingam Ajanthan, Philip H. S. TorrSpringer LNCS · University of Oxford
PDF ↗
2018
End-to-End Incremental LearningFrancisco M. Castro, Manuel J. Marín‐Jiménez, Nicolás Guil … Karteek AlahariSpringer LNCS · Universidad de Málaga · University of Córdoba · +5
PDF ↗
2018
Lifelong Machine Learning, Second EditionZhiyuan Chen, Bing LiuMachine Learning · Google (United States) · University of Illinois Chicago
2018
Lifelong Learning via Progressive Distillation and RetrospectionSaihui Hou, Xinyu Pan, Chen Change Loy … Dahua LinSpringer LNCS · University of Science and Technology of China · Chinese University of Hong Kong · +1
2018
Keep and Learn: Continual Learning by Constraining the Latent Space for Knowledge Preservation in Neural NetworksHyoeun Kim, Seungwook Kim, John J. LeeSpringer LNCS
PDF ↗
2018
Catastrophic Forgetting: Still a Problem for DNNsBenedikt Pfülb, Alexander Gepperth, Syahrul Afzal Che Abdullah, Axel KilianSpringer LNCS · Fulda University of Applied Sciences
PDF ↗
2018
Enriching Translation-Based Knowledge Graph Embeddings Through Continual LearningHyun-Je Song, Seong-Bae ParkIEEE Access · Naver (South Korea) · Kyung Hee University
2018
Overcoming Catastrophic Forgetting in Convolutional Neural Networks by Selective Network AugmentationAbel Zacarias, Luı́s A. AlexandreSpringer LNCS · University of Beira Interior · Instituto de Telecomunicações
PDF ↗
2018
The effects of morphology and fitness on catastrophic interferenceJoshua Powers, Sam Kriegman, Josh BongardThe 2018 Conference on Artificial Life · University of Vermont · Morpho (United States)
2018
A Broad Neural Network Structure for Class Incremental LearningWenzhang Liu, Haiqin Yang, Yuewen Sun, Changyin SunSpringer LNCS · Southeast University · Hang Seng University of Hong Kong
2018
Continuous Learning in a Hierarchical Multiscale Neural NetworkThomas Wolf, Julien Chaumond, Clément DelangueACL · Central European University · Bio Signal Group (United States)
PDF ↗
2018
Characteristics of contrastive Hebbian learning with pseudorehearsal for multilayer neural networks on reduction of catastrophic forgettingShunta Nakano, Motonobu HattoriInternational Journal of Computational Intelligence Studies · Takeda (Japan) · University of Yamanashi
2018
Overcoming Catastrophic Forgetting with Self-adaptive IdentifiersFangzhou Xiong, Zhiyong Liu, Xu YangSpringer LNCS · Shandong Institute of Automation · University of Chinese Academy of Sciences · +2
2018
Investigation of Incremental Learning as Temporal Feature ExtractionShoya Matsumori, Yuki Abe, Masahiko Osawa, Michita ImaiProcedia Computer Science · Keio University · Japan Society for the Promotion of Science
2018
Alleviating Catastrophic Forgetting with Modularity for Continuously Learning Linked Open DataLu Chen, Masayuki MurataInternational Journal of Computer Theory and Engineering · The University of Osaka
PDF ↗
2018
Lifelong Learning with the Feedback-loop between Emotions and Actions via Internal RewardDharani Punithan, Byoung‐Tak ZhangProcedia Computer Science · Seoul National University
2018
On Capacity with Incremental Learning by Simplified Chaotic Neural NetworkToshinori Deguchi, Naohiro IshiiSpringer LNCS · National Institute of Technology, Gifu College · Aichi Institute of Technology
2018
Exemplar-Supported Generative Reproduction for Class Incremental LearningChen He, Ruiping Wang, S. Shan, Xilin ChenBMVC
2018
Natural Variational Continual LearningHanna TseranPreprint
2018
Continual Learning with Generative Replay via Discriminative Variational AutoencoderWoo-Young KangPreprint
2018
Catastrophic Interference in Neural Embedding ModelsPrudhvi Raj Dachapally, Michael N. JonesCognitive Science
2018
Incremental learning with deep neural networks using a test-time oracleA. Gepperth, S. GondalThe European Symposium on Artificial Neural Networks
2018
Continual Learning Through Expandable Elastic Weight ConsolidationAndrew Jones, Nathan SpraguePreprint
2018
Overcoming Catastrophic Forgetting in Neural Machine TranslationGregory KellPreprint
2018
Incremental Segmentation on Private Data without Catastrophic ForgettingTao Hu, PekingPreprint
2018
3 Our Proposal : Reinforced Continual LearningJu XuPreprint
2018
Developing Toward Generality : Overcoming Catastrophic Forgetting with Developmental CompressionShawn BeaulieuPreprint
2018
Developing Toward Generality: Combating Catastrophic Forgetting with Developmental CompressionShawn BeaulieuPreprint
2018
Exemplar-Supported Generative Reproduction for Class Incremental Learning Supplementary MaterialChen HePreprint
2018
Generative Adversarial Networks and Continual Learning ∗Kevin J Liang, Chunyuan Li, Guoyin Wang, L. CarinPreprint
2018
Incremental On-Line Learning: A Review and Comparison of State of the Art AlgorithmsAuthors pendingNeurocomputing
2018
Less-Forgetful Learning for Domain Expansion in Deep Neural NetworksAuthors pendingAAAI
2018
Not-so-Catastrophic Forgetting in Deep Reinforcement Learning on Sequential AtariGiacomo SpiglerPreprint
2018
Preventing Catastrophic Forgetting in an Online Learning SettingAyon Borthakur, M. Einhorn, Nikhil DhawanPreprint
2018
Tackling Transfer Learning and Catastrophic Forgetting Using Asynchronous Methods for Deep Reinforcement LearningJoao G. RibeiroPreprint
2018
Using Deep Learning to create a Universal Game Player Tackling Transfer Learning and Catastrophic Forgetting Using Asynchronous Methods for Deep Reinforcement LearningJoao G. RibeiroPreprint
2018
The Role of Sequences for Incremental LearningSusanne Wenzel, Lothar HotzInternational Conference on Agents and Artificial Intelli… · University of Bonn · Universität Hamburg

About this index

We keep this list because we read the field and wanted one place to see it. It covers work on continual learning itself, in the core areas of machine learning, and leaves out papers that apply it inside another field, such as medical imaging or fault diagnosis. It is seeded from the community lists kept by ContinualAI and by Xialei Liu, then filled out from OpenAlex, and every week a script looks for new papers on OpenAlex and arXiv. A model reads each candidate and decides whether it belongs; a person reviews the additions before they go live. Authors and affiliations come from OpenAlex, so a recent preprint can lack its institutions for a week or two.

Missing something, or filed under the wrong venue? Write to hello@unify.ai with the arXiv id or DOI.