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/kvmduc/TEAM-topo-evo-traffic-forecasting

공식 코드

TEAM: Topological Evolution-aware Framework for Traffic Forecasting--Extended Version

https://github.com/ky-ah/layup

공식 코드

Read Between the Layers: Leveraging Multi-Layer Representations for Rehearsal-Free Continual Learning with Pre-Trained Models

https://github.com/ky-ah/selective-lilac

공식 코드

Visually Grounded Continual Language Learning with Selective Specialization

https://github.com/lain810/dce

공식 코드

Addressing Imbalanced Domain-Incremental Learning through Dual-Balance Collaborative Experts

https://github.com/laisong-22004009/paretocl

공식 코드

Pareto Continual Learning: Preference-Conditioned Learning and Adaption for Dynamic Stability-Plasticity Trade-off

https://github.com/lamda-rl/imaginebench

공식 코드

ImagineBench: Evaluating Reinforcement Learning with Large Language Model Rollouts

https://github.com/lassino/fedbnn_code

공식 코드

Variational Bayes for Federated Continual Learning

https://github.com/lazarvalkov/picle

공식 코드

A Probabilistic Framework for Modular Continual Learning

https://github.com/learninginvision/lorac-ipc

공식 코드

LoRA-Based Continual Learning with Constraints on Critical Parameter Changes

https://github.com/lebrice/Sequoia

공식 코드

Sequoia: A Software Framework to Unify Continual Learning Research

https://github.com/lehaifeng/Learning_by_memory

공식 코드

Overcoming Catastrophic Forgetting by Soft Parameter Pruning

https://github.com/leonardbereska/multiheadreservoir

공식 코드

Continual Learning of Dynamical Systems with Competitive Federated Reservoir Computing

https://github.com/lexili24/NLUProject

공식 코드

Meta-Learning for Natural Language Understanding under Continual Learning Framework

https://github.com/liangyanshuo/InfLoRA

공식 코드

InfLoRA: Interference-Free Low-Rank Adaptation for Continual Learning

https://github.com/liangyanshuo/gainlora

공식 코드

Gated Integration of Low-Rank Adaptation for Continual Learning of Language Models

https://github.com/liangzu/loranpac

공식 코드

LoRanPAC: Low-rank Random Features and Pre-trained Models for Bridging Theory and Practice in Continual Learning

https://github.com/libo-huang/PrePrompt

공식 코드

PrePrompt: Predictive prompting for class incremental learning

https://github.com/lifelong-learning-systems/l2explorer

공식 코드

L2Explorer: A Lifelong Reinforcement Learning Assessment Environment

https://github.com/lifelong-ml/mendez2022modularlifelongrl

공식 코드

Lifelong Machine Learning of Functionally Compositional Structures

https://github.com/lifelong-ml/shels

공식 코드

SHELS: Exclusive Feature Sets for Novelty Detection and Continual Learning Without Class Boundaries

https://github.com/lifelonglab/lifelong-anomaly-detection-scenarios

공식 코드

Lifelong Continual Learning for Anomaly Detection: New Challenges, Perspectives, and Insights

https://github.com/lifelonglab/m2i_i2m_benchmark

공식 코드

From MNIST to ImageNet and Back: Benchmarking Continual Curriculum Learning

https://github.com/lifelonglab/tinysubnets

공식 코드

TinySubNets: An efficient and low capacity continual learning strategy

https://github.com/lihong2303/atlas

공식 코드

ATLAS: Adapter-Based Multi-Modal Continual Learning with a Two-Stage Learning Strategy

https://github.com/lijiaqi/halrp

공식 코드

Hessian Aware Low-Rank Perturbation for Order-Robust Continual Learning

https://github.com/lijincm/CoCa

공식 코드

Complementary Calibration: Boosting General Continual Learning with Collaborative Distillation and Self-Supervision

https://github.com/lijy373/cclis

공식 코드

Contrastive Continual Learning with Importance Sampling and Prototype-Instance Relation Distillation

https://github.com/lil-lab/clif_cb

공식 코드

Continual Learning for Instruction Following from Realtime Feedback

https://github.com/lilanpei/continual-calibration

공식 코드

Calibration of Continual Learning Models

https://github.com/lilyht/cil-mgrb

공식 코드

Multi-Granularity Regularized Re-Balancing for Class Incremental Learning

https://github.com/lilyht/create

공식 코드

Reducing Class-wise Confusion for Incremental Learning with Disentangled Manifolds

https://github.com/linghan1997/regression-based-analytic-incremental-learning

공식 코드

Advancing Cross-domain Discriminability in Continual Learning of Vision-Language Models

https://github.com/linhaowei1/clog

공식 코드

CLoG: Benchmarking Continual Learning of Image Generation Models

https://github.com/linhaowei1/tpl

공식 코드

Class Incremental Learning via Likelihood Ratio Based Task Prediction

https://github.com/linhaowei1/tplr

공식 코드

Class Incremental Learning via Likelihood Ratio Based Task Prediction

https://github.com/linlany/rapf

공식 코드

Class-Incremental Learning with CLIP: Adaptive Representation Adjustment and Parameter Fusion

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