Papers with Code 아카이브

Active Learning

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 1
평가표: 1
보존된 평가 기록: 7

Active Learning is a paradigm in supervised machine learning which uses fewer training examples to achieve better optimization by iteratively training a predictor, and using the predictor in each iteration to choose the training examples which will increase its chances of finding better configurations and at the same time improving the accuracy of the prediction model

Source: Polystore++: Accelerated Polystore System for Heterogeneous Workloads

코드

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

https://github.com/yyysbysb/al_obs_neurips19

공식 코드

The Label Complexity of Active Learning from Observational Data

https://github.com/zacps/al-stopping-conditions

공식 코드

Hitting the Target: Stopping Active Learning at the Cost-Based Optimum

https://github.com/zalanborsos/bilevel_coresets

공식 코드

Semi-supervised Batch Active Learning via Bilevel Optimization

https://github.com/zeyademam/active_learning

공식 코드

Active Learning at the ImageNet Scale

https://github.com/zhang-fengzhuo/active-lathe

공식 코드

Active-LATHE: An Active Learning Algorithm for Boosting the Error Exponent for Learning Homogeneous Ising Trees

https://github.com/zhangrenyuuchicago/balance

공식 코드

Scalable Batch-Mode Deep Bayesian Active Learning via Equivalence Class Annealing

https://github.com/zhangxulu1996/gal4personalization

공식 코드

Generative Active Learning for Image Synthesis Personalization

https://github.com/zhangyuanhan-ai/bamboo

공식 코드

Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy

https://github.com/zhenyutang2023/data_selection

공식 코드

Exploring Data Redundancy in Real-world Image Classification through Data Selection

https://github.com/zhesna/EMMA

공식 코드

Mindful Active Learning

https://github.com/zi-w/Kitchen2D

공식 코드

Active model learning and diverse action sampling for task and motion planning

https://github.com/ziatdinovmax/ActiveChannelLearning

공식 코드

Active learning in open experimental environments: selecting the right information channel(s) based on predictability in deep kernel learning

https://github.com/ziatdinovmax/neurobayes

공식 코드

Active Learning with Fully Bayesian Neural Networks for Discontinuous and Nonstationary Data

https://github.com/zixy17/limeqo

공식 코드

Low Rank Learning for Offline Query Optimization

https://github.com/zjw700/mus-cdb

공식 코드

MUS-CDB: Mixed Uncertainty Sampling with Class Distribution Balancing for Active Annotation in Aerial Object Detection

https://github.com/zwt233/Grain

공식 코드

Grain: Improving Data Efficiency of Graph Neural Networks via Diversified Influence Maximization

https://github.com/zwt233/igp

공식 코드

Information Gain Propagation: a new way to Graph Active Learning with Soft Labels

https://github.com/zwt233/rim

공식 코드

RIM: Reliable Influence-based Active Learning on Graphs

https://github.com/zzsfornlp/zmsp

공식 코드

A Survey of Active Learning for Natural Language Processing

https://gitlab.com/akhilsnair/workflow_sisso

공식 코드

Materials-Discovery Workflows Guided by Symbolic Regression: Identifying Acid-Stable Oxides for Electrocatalysis

https://gitlab.com/asolovykh/mlip-i-pi-tutorial

공식 코드

Path-integral molecular dynamics with actively-trained and universal machine learning force fields

https://gitlab.com/gortizji/product_graphs

공식 코드

Sampling and Reconstruction of Signals on Product Graphs

https://gitlab.com/haghdam/deep_active_learning

공식 코드

Active Learning for Deep Detection Neural Networks

https://gitlab.com/hylleraasplatform/hyal

공식 코드

Learning atomic forces from uncertainty-calibrated adversarial attacks

https://gitlab.com/serralba/concept_drift

공식 코드

Efficient Concept Drift Handling for Batch Android Malware Detection Models

https://gitlab.com/zaverkin_v/gmnn

공식 코드

Fast and Sample-Efficient Interatomic Neural Network Potentials for Molecules and Materials Based on Gaussian Moments

https://gitlab.is.tue.mpg.de/mbuissonfenet/active_learning_gp

공식 코드

Actively Learning Gaussian Process Dynamics

https://worksheets.codalab.org/worksheets/0x39ba5559790b4099a7ff75f916ce19a4

공식 코드

On the Importance of Adaptive Data Collection for Extremely Imbalanced Pairwise Tasks

https://worksheets.codalab.org/worksheets/0x8ef22fd3cd384029bf1d1cae5b268f2d

공식 코드

On the Relationship between Data Efficiency and Error for Uncertainty Sampling

https://worksheets.codalab.org/worksheets/0x978bd1ba6b284678994c067f9c9bdb78

공식 코드

Derivative free optimization via repeated classification

https://worksheets.codalab.org/worksheets/0xf8dfe5bcc1dc408fb54b3cc15a5abce8

공식 코드

Uncertainty Sampling is Preconditioned Stochastic Gradient Descent on Zero-One Loss

https://github.com/BBloggsbott/k-armed-bandits

A Tutorial on Thompson Sampling

https://github.com/BlackHC/batchbald_redux

BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning

https://github.com/BlackHC/ddu_dirty_mnist

Deep Deterministic Uncertainty: A Simple Baseline

https://github.com/CFEL-CMI/Active-Learning-of-PES

libact: Pool-based Active Learning in Python

https://github.com/CompRhys/roost

Active learning based generative design for the discovery of wide bandgap materials

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