paper-with-me

Papers

A Multi-Head Model for Continual Learning via Out-of-Distribution Replay

2022-08-20 · Gyuhak Kim, Zixuan Ke, Bing Liu

This paper studies class incremental learning (CIL) of continual learning (CL). Many approaches have been proposed to deal with catastrophic forgetting (CF) in CIL. Most methods incrementally construct a single classifier for all classes of all tasks in a single head network. To prevent CF, a popular approach is to memorize a small number of samples from previous tasks and replay them during training of the new task. However, this approach still suffers from serious CF as the parameters learned for previous tasks are updated or adjusted with only the limited number of saved samples in the memory. This paper proposes an entirely different approach that builds a separate classifier (head) for each task (called a multi-head model) using a transformer network, called MORE. Instead of using the saved samples in memory to update the network for previous tasks/classes in the existing approach, MORE leverages the saved samples to build a task specific classifier (adding a new classification head) without updating the network learned for previous tasks/classes. The model for the new task in MORE is trained to learn the classes of the task and also to detect samples that are not from the same data distribution (i.e., out-of-distribution (OOD)) of the task. This enables the classifier for the task to which the test instance belongs to produce a high score for the correct class and the classifiers of other tasks to produce low scores because the test instance is not from the data distributions of these classifiers. Experimental results show that MORE outperforms state-of-the-art baselines and is also naturally capable of performing OOD detection in the continual learning setting.

📄 PDF Abstract BibTeX arXiv:2208.09734

Code (3)

k-gyuhak/more 공식 구현 pytorch
k-gyuhak/clom pytorch
k-gyuhak/wptp pytorch

Tasks

class-incremental learningClass Incremental LearningContinual LearningIncremental LearningOut of Distribution (OOD) Detection

Methods 이 논문이 사용한 방법론

Test 설명 없음

Similar Papers 제목 키워드 기반

Continual Offline Reinforcement Learning via Diffusion-based Dual Generative Replay

2024-04-16 · Jinmei Liu, Wenbin Li, Xiangyu Yue, Shilin Zhang 외

We study continual offline reinforcement learning, a practical paradigm that facilitates forward transfer and mitigates catastrophic forgetting to tackle sequential offline tasks. We propose a dual generative replay fram…

Continual Learningreinforcement-learningReinforcement Learning

Canonicalized Stable-List Replay for Private Federated Continual Learning over Language-Model Embeddings

2026-05-29 · Ibne Farabi Shihab, Abu Sa-Adat Mohamed Moon-Im Al Ahsan, Anuj Sharma arxiv

Federated continual learning (FCL) lets distributed clients adapt language-model heads to evolving NLP tasks without sharing raw text. Under user-level differential privacy (DP), replay-based continual learning faces a s…

Continual Learning

Stable Continual Reinforcement Learning via Diffusion-based Trajectory Replay

2024-11-16 · Feng Chen, Fuguang Han, Cong Guan, Lei Yuan 외

Given the inherent non-stationarity prevalent in real-world applications, continual Reinforcement Learning (RL) aims to equip the agent with the capability to address a series of sequentially presented decision-making ta…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Revisiting Replay and Gradient Alignment for Continual Pre-Training of Large Language Models

2025-08-03 · Istabrak Abbes, Gopeshh Subbaraj, Matthew Riemer, Nizar Islah 외 arxiv

Training large language models (LLMs) typically involves pre-training on massive corpora, only to restart the process entirely when new data becomes available. A more efficient and resource-conserving approach would be c…

Continual Learning

FETCH: A Memory-Efficient Replay Approach for Continual Learning in Image Classification

2024-07-17 · Markus Weißflog, Peter Protzel, Peer Neubert

Class-incremental continual learning is an important area of research, as static deep learning methods fail to adapt to changing tasks and data distributions. In previous works, promising results were achieved using repl…

BenchmarkingContinual Learningimage-classificationImage Classification+1