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/maPiche/ANML-Project

Learning to Continually Learn

https://github.com/mengxiangming/BayesBiNN

Training Binary Neural Networks using the Bayesian Learning Rule

https://github.com/mindspore-ai/contrib/blob/master/application/EWC-Overcoming-catastrophic-forgetting/demo.ipynb

Overcoming catastrophic forgetting in neural networks

https://github.com/miv-xjtu/speed

Dataset Condensation with Distribution Matching

https://github.com/modelfusion/otfusion

Model Fusion via Optimal Transport

https://github.com/mostafaelaraby/Real-DEEL-Dark-Experience

Rethinking Experience Replay: a Bag of Tricks for Continual Learning

https://github.com/mu-y/lll-tts

Overcoming catastrophic forgetting in neural networks

https://github.com/neurai-lab/dare

BiRT: Bio-inspired Replay in Vision Transformers for Continual Learning

https://github.com/neuraptic/cpe-clip

Multimodal Parameter-Efficient Few-Shot Class Incremental Learning

https://github.com/ngailapdi/LWF

Learning without Forgetting

https://github.com/npurg/faknow

Graph Neural Networks with Continual Learning for Fake News Detection from Social Media

https://github.com/nvshrao/Elastic-Weight-Consolidation

Overcoming catastrophic forgetting in neural networks

https://github.com/oakdata/benchmark

Wanderlust: Online Continual Object Detection in the Real World

https://github.com/p0werweirdo/tagfcl

Compacting, Picking and Growing for Unforgetting Continual Learning

https://github.com/paddorch/SupContrast.paddle

Supervised Contrastive Learning

https://github.com/parvex/residual-continual-learning-benchmark

Residual Continual Learning

https://github.com/pavliclab/neurips2023-unireps-hong-tgsh-randomly_weighted_neuromodulation_in_neural_networks

Learning to Modulate Random Weights: Neuromodulation-inspired Neural Networks For Efficient Continual Learning

https://github.com/pennfranc/hypnettorch

Continual learning with hypernetworks

https://github.com/peymanbateni/simple-cnaps

Beyond Simple Meta-Learning: Multi-Purpose Models for Multi-Domain, Active and Continual Few-Shot Learning

https://github.com/phunterlau/paper_without_code/tree/main/examples/InCA

In-context Continual Learning Assisted by an External Continual Learner

https://github.com/pihey1995/VariationalContinualLearning

Variational Continual Learning

https://github.com/prateekstark/training-binary-neural-network

Training Binary Neural Networks using the Bayesian Learning Rule

https://github.com/pwc-1/Paper-8/tree/main/blenderbot

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

https://github.com/raymin0223/self-contrastive-learning

Supervised Contrastive Learning

https://github.com/renato145/ContrastiveLoss

Supervised Contrastive Learning

https://github.com/rokmr/TACLE

TACLE: Task and Class-aware Exemplar-free Semi-supervised Class Incremental Learning

https://github.com/rvl-lab-utoronto/HyperCRL

Continual learning with hypernetworks

https://github.com/safe-graph/GNN-FakeNews

Graph Neural Networks with Continual Learning for Fake News Detection from Social Media

https://github.com/sairin1202/BIC

Large Scale Incremental Learning

https://github.com/salarim/Semi-Supervised-CL

Supervised Contrastive Learning

https://github.com/salesforce/GeDi

Generative and Discriminative Text Classification with Recurrent Neural Networks

https://github.com/salmank255/ROAD_Waymo_Baseline

ROAD: The ROad event Awareness Dataset for Autonomous Driving

https://github.com/salt-nlp/adaptive-compositional-modules

Continual Sequence Generation with Adaptive Compositional Modules

https://github.com/sarthakTUM/progressive-neural-networks-for-nlp

Progressive Neural Networks

https://github.com/sayakpaul/Supervised-Constrastive-Learning-in-TensorFlow-2

Supervised Contrastive Learning

https://github.com/sebamenabar/oaml-jax

Meta-Learning Representations for Continual Learning

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