paper-with-me

홈 › Papers

Mitigating Catastrophic Forgetting in Long Short-Term Memory Networks

2023-05-26 · Ketaki Joshi, Raghavendra Pradyumna Pothukuchi, Andre Wibisono, Abhishek Bhattacharjee

Continual learning on sequential data is critical for many machine learning (ML) deployments. Unfortunately, LSTM networks, which are commonly used to learn on sequential data, suffer from catastrophic forgetting and are limited in their ability to learn multiple tasks continually. We discover that catastrophic forgetting in LSTM networks can be overcome in two novel and readily-implementable ways -- separating the LSTM memory either for each task or for each target label. Our approach eschews the need for explicit regularization, hypernetworks, and other complex methods. We quantify the benefits of our approach on recently-proposed LSTM networks for computer memory access prefetching, an important sequential learning problem in ML-based computer system optimization. Compared to state-of-the-art weight regularization methods to mitigate catastrophic forgetting, our approach is simple, effective, and enables faster learning. We also show that our proposal enables the use of small, non-regularized LSTM networks for complex natural language processing in the offline learning scenario, which was previously considered difficult.

📄 PDF Abstract BibTeX arXiv:2305.17244

Code (0)

등록된 구현이 없습니다.

Tasks

Continual Learning

Methods 이 논문이 사용한 방법론

Tanh Activation 설명 없음
Sigmoid Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

Similar Papers 제목 키워드 기반

Continual Learning Long Short Term Memory

2020-11-01 · Findings of the Association for Computational Linguistics 2020 · Xin Guo, Yu Tian, Qinghan Xue, Panos Lampropoulos 외

Catastrophic forgetting in neural networks indicates the performance decreasing of deep learning models on previous tasks while learning new tasks. To address this problem, we propose a novel Continual Learning Long Shor…

Continual LearningDeep LearningSpoken Language Understanding

The Importance of Robust Features in Mitigating Catastrophic Forgetting

2023-06-29 · Hikmat Khan, Nidhal C. Bouaynaya, Ghulam Rasoom

Continual learning (CL) is an approach to address catastrophic forgetting, which refers to forgetting previously learned knowledge by neural networks when trained on new tasks or data distributions. The adversarial robus…

Adversarial RobustnessContinual Learning

Dynamic Orthogonal Continual Fine-tuning for Mitigating Catastrophic Forgettings

2025-09-28 · Zhixin Zhang, Zeming Wei, Meng Sun arxiv

Catastrophic forgetting remains a critical challenge in continual learning for large language models (LLMs), where models struggle to retain performance on historical tasks when fine-tuning on new sequential data without…

Continual Learning

Conditions for Catastrophic Forgetting in Multilingual Translation

2025-10-22 · Danni Liu, Jan Niehues arxiv

Fine-tuning multilingual foundation models on specific languages often induces catastrophic forgetting, degrading performance on languages unseen in fine-tuning. While this phenomenon is widely-documented, the literature…

parameter-efficient fine-tuningMachine Translation

LongReD: Mitigating Short-Text Degradation of Long-Context Large Language Models via Restoration Distillation

2025-02-11 · Zican Dong, Junyi Li, Jinhao Jiang, Mingyu Xu 외

Large language models (LLMs) have gained extended context windows through scaling positional encodings and lightweight continual pre-training. However, this often leads to degraded performance on short-text tasks, while …