mlsanityData to 14 Oct 2026

Continual Learning with Knowledge Transfer for Sentiment Classification

arXiv 2112.10021 ↗First posted 18 Dec 2021cs.CL cs.AI cs.LGcited by 12

Not on the map. Why?

Abstract (arXiv)

This paper studies continual learning (CL) for sentiment classification (SC). In this setting, the CL system learns a sequence of SC tasks incrementally in a neural network, where each task builds a classifier to classify the sentiment of reviews of a particular product category or domain. Two natural questions are: Can the system transfer the knowledge learned in the past from the previous tasks to the new task to help it learn a better model for the new task? And, can old models for previous tasks be improved in the process as well? This paper proposes a novel technique called KAN to achieve these objectives. KAN can markedly improve the SC accuracy of both the new task and the old tasks via forward and backward knowledge transfer. The effectiveness of KAN is demonstrated through extensive experiments.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 19 of its 33 references that are in the map. First posted on arXiv 18 Dec 2021.

Builds on

19 of 33 references.

References · 19

  1. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  2. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,333
  3. 2017Gradient Episodic Memory for Continual Learningcited by 1,898
  4. 2015Show, Attend and Tell: Neural Image Caption Generation with Visual Attentioncited by 1,423
  5. 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,330
  6. 2017Continual Learning with Deep Generative Replaycited by 1,158
  7. 2018Efficient Lifelong Learning with A-GEMcited by 1,058
  8. 2017PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruningcited by 898
  9. 2018Overcoming catastrophic forgetting with hard attention to the taskcited by 681
  10. 2017PathNet: Evolution Channels Gradient Descent in Super Neural Networkscited by 364
  11. 2017Overcoming Catastrophic Forgetting by Incremental Moment Matchingcited by 243
  12. 2018Continual Learning of Context-dependent Processing in Neural Networkscited by 179
7 more
  1. 2019A continual learning survey: Defying forgetting in classification taskscited by 118
  2. 2017Deep Generative Dual Memory Network for Continual Learningcited by 59
  3. 2017Continual Learning in Generative Adversarial Netscited by 51
  4. 2019Complementary Learning for Overcoming Catastrophic Forgetting Using Experience Replaycited by 51
  5. 2018Lifelong Learning for Sentiment Classificationcited by 21
  6. 2017Lifelong Learning CRF for Supervised Aspect Extractioncited by 9
  7. 2019Forward and Backward Knowledge Transfer for Sentiment Classificationcited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 3; 2023: 3; 2024: 4; 2025: 1; 2026: 1.

12 papers.

  1. 2023Revisiting Out-of-distribution Robustness in NLP: Benchmark, Analysis, and LLMs Evaluationscited by 97
  2. 2022Wild-Time: A Benchmark of in-the-Wild Distribution Shift over Timecited by 90
  3. 2022Continual Learning of Natural Language Processing Tasks: A Surveycited by 83
  4. 2022Memory Efficient Continual Learning with Transformerscited by 43
  5. 2023Catastrophic Forgetting in Deep Learning: A Comprehensive Taxonomycited by 24
  6. 2024Boosting Large Language Models with Continual Learning for Aspect-based Sentiment Analysiscited by 11
  7. 2024ChronosLex: Time-aware Incremental Training for Temporal Generalization of Legal Classification Taskscited by 11
  8. 2024CLoG: Benchmarking Continual Learning of Image Generation Modelscited by 5
  9. 2024HOP to the Next Tasks and Domains for Continual Learning in NLPcited by 3
  10. 2023Context selectivity with dynamic availability enables lifelong continual learningcited by 0
  11. 2025OpenCML: End-to-End Framework of Open-world Machine Learning to Learn Unknown Classes Incrementallycited by 0
  12. 2026Relative Parameter Importance in Task-Agnostic Replay-Free Continual Learningcited by 0