Papers with Code 아카이브

Continual Learning

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 5
평가표: 33
보존된 평가 기록: 133

Continual Learning (also known as Incremental Learning, Life-long Learning) is a concept to learn a model for a large number of tasks sequentially without forgetting knowledge obtained from the preceding tasks, where the data in the old tasks are not available anymore during training new ones.
If not mentioned, the benchmarks here are Task-CL, where task-id is provided on validation.

Source:
Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation
Three scenarios for continual learning
Lifelong Machine Learning
Continual lifelong learning with neural networks: A review

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/Tiiiger/QPyTorch

Training and Inference with Integers in Deep Neural Networks

https://github.com/TsingZ0/PFL-Non-IID

Preservation of the Global Knowledge by Not-True Distillation in Federated Learning

https://github.com/WangTianduo/lifelong-learning-3-cases

Generative replay with feedback connections as a general strategy for continual learning

https://github.com/XG293/SupConLoss

Supervised Contrastive Learning

https://github.com/XSMUBC/DNC-lifelong-learning

Generative replay with feedback connections as a general strategy for continual learning

https://github.com/XSMUBC/Lifelong-learning_xsm

Generative replay with feedback connections as a general strategy for continual learning

https://github.com/YuWang24/MultiTune

Learning multiple visual domains with residual adapters

https://github.com/ZIZUN/CPFT

Supervised Contrastive Learning

https://github.com/abhaskumarsinha/Keras-Blenderbot

BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage

https://github.com/agentic-learning-ai-lab/memory-storyboard

Memory Storyboard: Leveraging Temporal Segmentation for Streaming Self-Supervised Learning from Egocentric Videos

https://github.com/ago109/ContinualPTNCN

Continual Learning of Recurrent Neural Networks by Locally Aligning Distributed Representations

https://github.com/ahq1993/MPNet

Motion Planning Networks: Bridging the Gap Between Learning-based and Classical Motion Planners

https://github.com/ai-med/MAS-LR

Importance Driven Continual Learning for Segmentation Across Domains

https://github.com/alsgkals2/CoReD_Released

CoReD: Generalizing Fake Media Detection with Continual Representation using Distillation

https://github.com/alsgkals2/cored

CoReD: Generalizing Fake Media Detection with Continual Representation using Distillation

https://github.com/aml-team-2/aml-reproducability-challenge

Variational Continual Learning

https://github.com/arazd/residualprompts

Progressive Prompts: Continual Learning for Language Models

https://github.com/arcosin/Doric

Progressive Neural Networks

https://github.com/ariseff/overcoming-catastrophic

Overcoming catastrophic forgetting in neural networks

https://github.com/barbua/PPCA

https://github.com/bigdata-ustc/Zero-1-to-3

FedJudge: Federated Legal Large Language Model

https://github.com/blues-lin/fin-analyze

Learning to Continually Learn

https://github.com/boluoweifenda/CNN

Convolution with even-sized kernels and symmetric padding

https://github.com/brjathu/RPSnet

https://github.com/caesarea38/doclangid

Supervised Contrastive Learning

https://github.com/caotians1/OD-test-master

A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks

https://github.com/cardiffnlp/tweeteval

TimeLMs: Diachronic Language Models from Twitter

https://github.com/catid/never_forget

Overcoming catastrophic forgetting in neural networks

https://github.com/cdjkim/ConFrag

Continual Learning on Noisy Data Streams via Self-Purified Replay

https://github.com/chaht01/co2l

Co$^2$L: Contrastive Continual Learning

https://github.com/chandar-lab/IIRC

IIRC: Incremental Implicitly-Refined Classification

https://github.com/chengyuehuang511/frames-vqa

Fast Trainable Projection for Robust Fine-Tuning

https://github.com/chilung/hat

Overcoming catastrophic forgetting with hard attention to the task

https://github.com/chrhenning/hypnettorch

Continual learning with hypernetworks

https://github.com/clam004/intro_continual_learning

Overcoming catastrophic forgetting in neural networks

https://github.com/codelion/adaptive-classifier/blob/main/src/adaptive_classifier/ewc.py

Overcoming catastrophic forgetting in neural networks

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.