Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

CAFF-CIL: Causality-Aware Freedom Forgetting Approach for Class-Incremental Learning.

Xinyu Zhou, Jing Yang, Xiaoli Ruan

    IEEE Transactions on Neural Networks and Learning Systems
    |June 29, 2026
    PubMed
    Summary
    This summary is machine-generated.

    Related Concept Videos

    You might also read

    Related Articles

    Articles linked to this work by shared authors, journal, and citation graph.

    Sort by
    Same author

    [Effects of a glucocorticoid on development of kidney deficiency syndrome in a rat model of asthma].

    Zhong xi yi jie he xue bao = Journal of Chinese integrative medicine·2010
    Same author

    [A case of respiratory epithelial adenomatoid hamartoma in nasal cavity.].

    Zhonghua er bi yan hou tou jing wai ke za zhi = Chinese journal of otorhinolaryngology head and neck surgery·2010
    Same author

    [Construct cosmid libraries by isolating large genomic DNA fragments from Monascus ruber].

    Wei sheng wu xue bao = Acta microbiologica Sinica·2010
    Same author

    Retinal tissue engineering using mouse retinal progenitor cells and a novel biodegradable, thin-film poly(e-caprolactone) nanowire scaffold.

    Journal of ocular biology, diseases, and informatics·2010
    Same author

    [Correlation between MR diffusion weighted imaging with malignant degree of rabbit liver VX2 tumor models].

    Zhonghua yi xue za zhi·2010
    Same author

    [Immune response in BALB/c mice immunized with BCG expressing HBV truncated C gene and preS1 gene].

    Xi bao yu fen zi mian yi xue za zhi = Chinese journal of cellular and molecular immunology·2010
    Same journal

    Harmonic Autoencoding Framework for Multiple Tasks in Magnetic Particle Imaging Reconstruction.

    IEEE transactions on neural networks and learning systems·2026
    Same journal

    A Survey on Human-Centric Voice-Face Multimodal Learning.

    IEEE transactions on neural networks and learning systems·2026
    Same journal

    Vision-Assisted Foundation Model for Solving Multitask Vehicle Routing Problems.

    IEEE transactions on neural networks and learning systems·2026
    Same journal

    FP3O: Enabling Proximal Policy Optimization in Multiagent Cooperation With Parameter-Sharing Versatility.

    IEEE transactions on neural networks and learning systems·2026
    Same journal

    Hierarchical Semantic Concept Modeling for Generalizable Myocardial Pathology Segmentation on Multisequence CMR Images.

    IEEE transactions on neural networks and learning systems·2026
    Same journal

    Stability of Time-Varying Impulsive Systems With State-Dependent Delay and Its Application in Complex Networks.

    IEEE transactions on neural networks and learning systems·2026
    See all related articles

    This study introduces a causal reasoning approach for class-incremental learning (CIL) to overcome forgetting and bias. The CAFF-CIL framework significantly reduces forgetting and improves accuracy in dynamic learning scenarios.

    Area of Science:

    • Artificial Intelligence
    • Machine Learning
    • Computer Vision

    Background:

    • Class-incremental learning (CIL) aims to learn new tasks without forgetting previous ones.
    • Dynamic task sequences present challenges like unclear category boundaries and context bias in CIL.
    • Existing CIL methods often struggle with effective knowledge retention and adaptation.

    Purpose of the Study:

    • To propose a novel class-incremental learning approach that supports causal reasoning and mitigates forgetting.
    • To introduce the Causal Inference Framework for CIL (CAFF-CIL) to address limitations in current CIL methods.
    • To enhance model performance in dynamic learning environments by improving category discriminative boundaries and reducing context bias.

    Main Methods:

    • The proposed CAFF-CIL framework integrates three key components: Task-Adaptive Causal Feature Selection (TAFS), Causal Dual-Path Modulation (CDPM), and Task-Adaptive Hyperparameter Tuning (TAHT).

    Related Experiment Videos

  • TAFS quantifies feature causality and creates a forgetting channel for redundant features.
  • CDPM stabilizes base class representations while adapting novel class features, supported by TAHT's stage-aware optimization strategy.

    • Main Results:

    • CAFF-CIL demonstrated a reduction in the forgetting rate by 7.91%.
    • The framework achieved an accuracy improvement of 4.8% on the CIFAR-100 dataset.
    • Experiments across eight benchmark datasets validated the effectiveness of the proposed approach.

    Conclusions:

    • The CAFF-CIL framework effectively addresses forgetting and context bias in class-incremental learning through causal reasoning.
    • The integration of TAFS, CDPM, and TAHT components leads to significant performance gains in dynamic learning scenarios.
    • This causal inference approach offers a promising direction for advancing robust and efficient class-incremental learning systems.