paper-with-me

홈 › Papers

A comprehensive, application-oriented study of catastrophic forgetting in DNNs

2019-05-20 · ICLR 2019 5 · B. Pfülb, A. Gepperth

We present a large-scale empirical study of catastrophic forgetting (CF) in modern Deep Neural Network (DNN) models that perform sequential (or: incremental) learning. A new experimental protocol is proposed that enforces typical constraints encountered in application scenarios. As the investigation is empirical, we evaluate CF behavior on the hitherto largest number of visual classification datasets, from each of which we construct a representative number of Sequential Learning Tasks (SLTs) in close alignment to previous works on CF. Our results clearly indicate that there is no model that avoids CF for all investigated datasets and SLTs under application conditions. We conclude with a discussion of potential solutions and workarounds to CF, notably for the EWC and IMM models.

📄 PDF Abstract BibTeX arXiv:1905.08101

Code (1)

BPfuelb/CF_in_DNNs tf

Tasks

General ClassificationIncremental Learning

Methods 이 논문이 사용한 방법론

EWC The methon to overcome catastrophic forgetting in neural network while continual learning

Similar Papers 제목 키워드 기반

Continual Learning for Natural Language Generation in Task-oriented Dialog Systems

2020-10-02 · Findings of the Association for Computational Linguistics 2020 · Fei Mi, LiangWei Chen, Mengjie Zhao, Minlie Huang 외

Natural language generation (NLG) is an essential component of task-oriented dialog systems. Despite the recent success of neural approaches for NLG, they are typically developed in an offline manner for particular domai…

Continual LearningText Generation

Catastrophic forgetting: still a problem for DNNs

2019-05-20 · B. Pfülb, A. Gepperth, S. Abdullah, A. Kilian

We investigate the performance of DNNs when trained on class-incremental visual problems consisting of initial training, followed by retraining with added visual classes. Catastrophic forgetting (CF) behavior is measured…

Incremental LearningModel Selection

A Methodology-Oriented Study of Catastrophic Forgetting in Incremental Deep Neural Networks

2024-05-11 · Ashutosh Kumar, Sonali Agarwal, D Jude Hemanth

Human being and different species of animals having the skills to gather, transferring knowledge, processing, fine-tune and generating information throughout their lifetime. The ability of learning throughout their lifes…

Incremental Learning

Overcoming Catastrophic Forgetting by Exemplar Selection in Task-oriented Dialogue System

2024-05-16 · Chen Chen, Ruizhe Li, Yuchen Hu, YuanYuan Chen 외

Intelligent task-oriented dialogue systems (ToDs) are expected to continuously acquire new knowledge, also known as Continual Learning (CL), which is crucial to fit ever-changing user needs. However, catastrophic forgett…

Continual LearningTask-Oriented Dialogue Systems

UFO: A Unified Flow-Oriented Framework for Robust Continual Graph Learning

2026-05-11 · Danhui Zhang, Zhe Wang, Qing Qing, Jiarui Liu 외 arxiv

Graph learning research has increasingly shifted toward continual graph learning (CGL), which better reflects real-world scenarios where graphs evolve over time. However, existing CGL methods largely assume clean supervi…

Graph Learning