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/NeurAI-Lab/CLS-ER

공식 코드

Learning Fast, Learning Slow: A General Continual Learning Method based on Complementary Learning System

https://github.com/NeurAI-Lab/MultiModal-CL

공식 코드

Beyond Unimodal Learning: The Importance of Integrating Multiple Modalities for Lifelong Learning

https://github.com/NeurAI-Lab/TriRE

공식 코드

TriRE: A Multi-Mechanism Learning Paradigm for Continual Knowledge Retention and Promotion

https://github.com/NeuralCollapseApplications/FSCIL

공식 코드

Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class Incremental Learning

https://github.com/Nic5472K/MetaLearnCC2021_AAAI_MetaSGD-CL

공식 코드

Learning to Continually Learn Rapidly from Few and Noisy Data

https://github.com/NishanthVAnand/prediction_and_control_in_continual_reinforcement_learning

공식 코드

Prediction and Control in Continual Reinforcement Learning

https://github.com/Nithin-Holla/MetaLifelongLanguage

공식 코드

Meta-Learning with Sparse Experience Replay for Lifelong Language Learning

https://github.com/PSSF23/scikit-learn-stream

공식 코드

Simplest Streaming Trees

https://github.com/PatrickZH/Continual-Representation-Learning-for-Biometric-Identification

공식 코드

Continual Representation Learning for Biometric Identification

https://github.com/Pervasive-AI-Lab/ContinualLearning-EchoStateNetworks

공식 코드

Continual Learning with Echo State Networks

https://github.com/Programmergg/NTK-FSCIL

공식 코드

NTK-Guided Few-Shot Class Incremental Learning

https://github.com/QFerdi/FECIL

공식 코드

Feature Expansion and enhanced Compression for Class Incremental Learning

https://github.com/QIU023/SATS_Continual_Semantic_Seg

공식 코드

SATS: Self-Attention Transfer for Continual Semantic Segmentation

https://github.com/QiWang98/PromptCGL

공식 코드

Prompt-Driven Continual Graph Learning

https://github.com/RAIVNLab/InTheWild

공식 코드

FLUID: A Unified Evaluation Framework for Flexible Sequential Data

https://github.com/RPD123-byte/Demonstrating-the-Continual-Learning-Capabilities-and-Practical-Application-of-Discrete-Time-Active

공식 코드

Demonstrating the Continual Learning Capabilities and Practical Application of Discrete-Time Active Inference

https://github.com/Rain9876/ShareLoRA

공식 코드

ShareLoRA: Parameter Efficient and Robust Large Language Model Fine-tuning via Shared Low-Rank Adaptation

https://github.com/RaptorMai/CVPR20_CLVision_challenge

공식 코드

Batch-level Experience Replay with Review for Continual Learning

https://github.com/RaptorMai/online-continual-learning

공식 코드

Online Class-Incremental Continual Learning with Adversarial Shapley Value

https://github.com/Red-Hat-AI-Innovation-Team/orthogonal-subspace-learning

공식 코드

Sculpting Subspaces: Constrained Full Fine-Tuning in LLMs for Continual Learning

https://github.com/Rhyssiyan/DER-ClassIL.pytorch

공식 코드

DER: Dynamically Expandable Representation for Class Incremental Learning

https://github.com/RobinLu1209/Geometer

공식 코드

Geometer: Graph Few-Shot Class-Incremental Learning via Prototype Representation

https://github.com/SaharR1372/DM_Style_matching

공식 코드

Decomposed Distribution Matching in Dataset Condensation

https://github.com/SaynaEbrahimi/Remembering-for-the-Right-Reasons

공식 코드

Remembering for the Right Reasons: Explanations Reduce Catastrophic Forgetting

https://github.com/SaynaEbrahimi/UCB

공식 코드

Uncertainty-guided Continual Learning with Bayesian Neural Networks

https://github.com/SebFar/radial_bnn

공식 코드

Radial Bayesian Neural Networks: Beyond Discrete Support In Large-Scale Bayesian Deep Learning

https://github.com/ShipengWang/Adam-NSCL

공식 코드

Training Networks in Null Space of Feature Covariance for Continual Learning

https://github.com/ShuangLI59/ebm-continual-learning

공식 코드

Energy-Based Models for Continual Learning

https://github.com/StonyBrookNLP/attention-sink-cl

공식 코드

Does RoBERTa Perform Better than BERT in Continual Learning: An Attention Sink Perspective

https://github.com/SunWenJu123/DCPOC

공식 코드

Exemplar-free Class Incremental Learning via Discriminative and Comparable One-class Classifiers

https://github.com/Sweety-dm/RECALL

공식 코드

Replay-enhanced Continual Reinforcement Learning

https://github.com/TLESORT/Generative_Continual_Learning

공식 코드

Generative Models from the perspective of Continual Learning

https://github.com/TimmHess/OCDVAEContinualLearning

공식 코드

A Procedural World Generation Framework for Systematic Evaluation of Continual Learning

https://github.com/TomVeniat/MNTDP

공식 코드

Efficient Continual Learning with Modular Networks and Task-Driven Priors

https://github.com/ToyotaCRDL/OneShotDIL

공식 코드

One-Shot Domain Incremental Learning

https://github.com/UIC-Liu-Lab/ContinualLM

공식 코드

Continual Pre-training of Language Models

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