mlsanityData to 14 Oct 2026

Learning to Prompt Knowledge Transfer for Open-World Continual Learning

arXiv 2312.14990 ↗First posted 22 Dec 2023cs.LG cs.AI cs.CVcited by 15

Not on the map. Why?

Abstract (arXiv)

This paper studies the problem of continual learning in an open-world scenario, referred to as Open-world Continual Learning (OwCL). OwCL is increasingly rising while it is highly challenging in two-fold: i) learning a sequence of tasks without forgetting knowns in the past, and ii) identifying unknowns (novel objects/classes) in the future. Existing OwCL methods suffer from the adaptability of task-aware boundaries between knowns and unknowns, and do not consider the mechanism of knowledge transfer. In this work, we propose Pro-KT, a novel prompt-enhanced knowledge transfer model for OwCL. Pro-KT includes two key components: (1) a prompt bank to encode and transfer both task-generic and task-specific knowledge, and (2) a task-aware open-set boundary to identify unknowns in the new tasks. Experimental results using two real-world datasets demonstrate that the proposed Pro-KT outperforms the state-of-the-art counterparts in both the detection of unknowns and the classification of knowns markedly.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Builds on 19 of its 32 references that are in the map. First posted on arXiv 22 Dec 2023.

Builds on

19 of 32 references.

References · 19

  1. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  2. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,915
  3. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
  4. 2016Learning without Forgettingcited by 2,496
  5. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  6. 2017Gradient Episodic Memory for Continual Learningcited by 1,898
  7. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
  8. 2020Energy-based Out-of-distribution Detectioncited by 1,299
  9. 2017Memory Aware Synapses: Learning what (not) to forgetcited by 1,105
  10. 2020Dark Experience for General Continual Learning: a Strong, Simple Baselinecited by 911
  11. 2018Overcoming catastrophic forgetting with hard attention to the taskcited by 681
  12. 2021Towards Open World Object Detectioncited by 297
7 more
  1. 2014Towards Open World Recognitioncited by 226
  2. 2020Adversarial Continual Learningcited by 142
  3. 2020Entropy Maximization and Meta Classification for Out-Of-Distribution Detection in Semantic Segmentationcited by 133
  4. 2019Unsupervised Out-of-Distribution Detection by Maximum Classifier Discrepancycited by 112
  5. 2021Continual Learning of a Mixed Sequence of Similar and Dissimilar Taskscited by 81
  6. 2023Open-World Continual Learning: Unifying Novelty Detection and Continual Learningcited by 22
  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: 2024: 5; 2025: 8; 2026: 2.

15 papers.

Sort:

By area:

  1. 2024Personalized Federated Continual Learning via Multi-granularity Promptcited by 20
  2. 2024DAM: Dynamic Adapter Merging for Continual Video QA Learningcited by 19
  3. 2024Continual Learning for Smart City: A Surveycited by 9
  4. 2024Handling Spatial-Temporal Data Heterogeneity for Federated Continual Learning via Tail Anchorcited by 9
  5. 2025Order-Robust Class Incremental Learning: Graph-Driven Dynamic Similarity Groupingcited by 7
  6. 2024Multi-granularity Knowledge Transfer for Continual Reinforcement Learningcited by 6
  7. 2025ErrorEraser: Unlearning Data Bias for Improved Continual Learningcited by 3
  8. 2025ProtoConNet: Prototypical Augmentation and Alignment for Open-Set Few-Shot Image Classificationcited by 3
  9. 2025Exploring Open-world Continual Learning with Knowns-Unknowns Knowledge Transfercited by 2
  10. 2025Improving Open-world Continual Learning under the Constraints of Scarce Labeled Datacited by 2
  11. 2025The Lie of the Average: How Class Incremental Learning Evaluation Deceives You?cited by 2
  12. 2025An Attention-based Feature Memory Design for Energy-Efficient Continual Learningcited by 2
3 more
  1. 2025Action-Adaptive Continual Learning: Enabling Policy Generalization under Dynamic Action Spacescited by 1
  2. 2026MAND: Modality-Aware Novelty Detection for Open-World Egocentric Activity Recognitioncited by 0
  3. 2026ProTPS: Prototype-Guided Text Prompt Selection for Continual Learningcited by 0