unify

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.

59 papers of 8,653 · showing 51–59Sort Recent · Most cited
University of Science and Technology of China All papers Clear all
  1. 2020
    Deep Inhomogeneous Regularization For Transfer LearningWen Wang, Wei Zhai, Yang CaoICIP · University of Science and Technology of China
  2. 2020
    Incremental learning imbalanced data streams with concept drift: The dynamic updated ensemble algorithmLi Zeng, Wenchao Huang, Yan Xiong … Tuanfei ZhuKnowledge-Based Systems · University of Science and Technology of China · Zhejiang Gongshang University · +1
  3. 2020
    Memory Protection Generative Adversarial Network (MPGAN): A Framework to Overcome the Forgetting of GANs Using Parameter Regularization MethodsYifan Chang, Wenbo Li, Jian Peng … Yingliang HuangIEEE Access · University of Science and Technology of China · Hefei Institute of Technology Innovation · +3
  4. 2019
    Extensible Cross-Modal HashingTianyi Chen, Lan Zhang, Shi-cong Zhang … Bai-chuan HuangIJCAI · University of Science and Technology of China · Northeastern University · +1
  5. 2019
    Learning a Unified Classifier Incrementally via RebalancingSaihui Hou, Xinyu Pan, Chen Change Loy … Dahua LinCVPR · University of Science and Technology of China · XLAB (Slovenia) · +3
  6. 2018
    Lifelong Learning Memory Networks for Aspect Sentiment ClassificationShuai Wang, Guangyi Lv, Sahisnu Mazumder … Bing LiuIEEE International Conference on Big Data (Big Data) · University of Illinois Chicago · University of Science and Technology of China
  7. 2019
    Learning to Learn without Forgetting By Maximizing Transfer and Minimizing InterferenceMatthew Riemer, Ignacio Cases, Robert Ajemian … Gerald TesauroICLR · IBM (United States) · Stanford University · +2
    PDF ↗
  8. 2018
    Lifelong Learning via Progressive Distillation and RetrospectionSaihui Hou, Xinyu Pan, Chen Change Loy … Dahua LinECCV · University of Science and Technology of China · Chinese University of Hong Kong · +1
  9. 2017
    Selective further learning of hybrid ensemble for class imbalanced increment learningMinlong Lin, Ke Tang, HeFei, AnHui 230027, China, Springfield, MO 65801-2604, USABig Data and Information Analytics · University of Science and Technology of China
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. By default it shows the papers we have a reason to trust: published at a venue like NeurIPS, ICML, ICLR, CVPR or TPAMI, or written by someone who has published there, or cited a few hundred times. The rest are one click away under “All papers”. 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.