paper-with-me

Papers

Consistency is the key to further mitigating catastrophic forgetting in continual learning

2022-07-11 · Prashant Bhat, Bahram Zonooz, Elahe Arani

Deep neural networks struggle to continually learn multiple sequential tasks due to catastrophic forgetting of previously learned tasks. Rehearsal-based methods which explicitly store previous task samples in the buffer and interleave them with the current task samples have proven to be the most effective in mitigating forgetting. However, Experience Replay (ER) does not perform well under low-buffer regimes and longer task sequences as its performance is commensurate with the buffer size. Consistency in predictions of soft-targets can assist ER in preserving information pertaining to previous tasks better as soft-targets capture the rich similarity structure of the data. Therefore, we examine the role of consistency regularization in ER framework under various continual learning scenarios. We also propose to cast consistency regularization as a self-supervised pretext task thereby enabling the use of a wide variety of self-supervised learning methods as regularizers. While simultaneously enhancing model calibration and robustness to natural corruptions, regularizing consistency in predictions results in lesser forgetting across all continual learning scenarios. Among the different families of regularizers, we find that stricter consistency constraints preserve previous task information in ER better.

📄 PDF Abstract BibTeX arXiv:2207.04998

Code (1)

neurai-lab/consistencycl 공식 구현 pytorch

Tasks

Continual LearningSelf-Supervised Learning

Methods 이 논문이 사용한 방법론

Experience Replay Experience Replay is a replay memory technique used in reinforcement learning where we store the agent’s experiences at each time-step, $e\_{t} = \left(s\_{t}, a\_{t}, r\_{t},…

Similar Papers 제목 키워드 기반

Contrastive Supervised Distillation for Continual Representation Learning

2022-05-11 · Tommaso Barletti, Niccolo' Biondi, Federico Pernici, Matteo Bruni 외

In this paper, we propose a novel training procedure for the continual representation learning problem in which a neural network model is sequentially learned to alleviate catastrophic forgetting in visual search tasks. …

Representation LearningRetrieval

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

FPPL: An Efficient and Non-IID Robust Federated Continual Learning Framework

2024-11-04 · Yuchen He, Chuyun Shen, Xiangfeng Wang, Bo Jin

Federated continual learning (FCL) aims to learn from sequential data stream in the decentralized federated learning setting, while simultaneously mitigating the catastrophic forgetting issue in classical continual learn…

Continual LearningContrastive LearningFederated LearningPrompt Learning

How Efficient Are Today's Continual Learning Algorithms?

2023-03-29 · Md Yousuf Harun, Jhair Gallardo, Tyler L. Hayes, Christopher Kanan

Supervised Continual learning involves updating a deep neural network (DNN) from an ever-growing stream of labeled data. While most work has focused on overcoming catastrophic forgetting, one of the major motivations beh…

Continual Learning

CURLoRA: Stable LLM Continual Fine-Tuning and Catastrophic Forgetting Mitigation

2024-08-26 · Muhammad Fawi

This paper introduces CURLoRA, a novel approach to fine-tuning large language models (LLMs) that leverages CUR matrix decomposition in the context of Low-Rank Adaptation (LoRA). Our method addresses two critical challeng…

Continual Learning