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/boschresearch/transfersafesequentiallearning

공식 코드

Global Safe Sequential Learning via Efficient Knowledge Transfer

https://github.com/bstienen/active-learning

공식 코드

Constraining the Parameters of High-Dimensional Models with Active Learning

https://github.com/bucherb/adversarial-curiosity

공식 코드

An Adversarial Objective for Scalable Exploration

https://github.com/c-liangyu/csval

공식 코드

Making Your First Choice: To Address Cold Start Problem in Vision Active Learning

https://github.com/c-w-d/meaeq

공식 코드

MeaeQ: Mount Model Extraction Attacks with Efficient Queries

https://github.com/ca-tt-ac/key-patch-proposer

공식 코드

Key Patch Proposer: Key Patches Contain Rich Information

https://github.com/caelan/pddlstream

공식 코드

Learning compositional models of robot skills for task and motion planning

https://github.com/callanwu/star

공식 코드

STAR: Constraint LoRA with Dynamic Active Learning for Data-Efficient Fine-Tuning of Large Language Models

https://github.com/cambridge-mlg/cnaps

공식 코드

Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processes

https://github.com/cambridge-mlg/expressiveness-approx-bnns

공식 코드

On the Expressiveness of Approximate Inference in Bayesian Neural Networks

https://github.com/castel44/al_delay

공식 코드

Stream-based Active Learning with Verification Latency in Non-stationary Environments

https://github.com/cenyou/transfersafesequentiallearning

공식 코드

Global Safe Sequential Learning via Efficient Knowledge Transfer

https://github.com/chapman20j/sar_bal

공식 코드

Novel Batch Active Learning Approach and Its Application to Synthetic Aperture Radar Datasets

https://github.com/chauhanjatin10/GraphsFewShot

공식 코드

Few-Shot Learning on Graphs via Super-Classes based on Graph Spectral Measures

https://github.com/chen700564/supercd

공식 코드

Few-shot Named Entity Recognition via Superposition Concept Discrimination

https://github.com/chenchenzong/bual

공식 코드

Bidirectional Uncertainty-Based Active Learning for Open Set Annotation

https://github.com/chenchenzong/eaoa

공식 코드

Rethinking Epistemic and Aleatoric Uncertainty for Active Open-Set Annotation: An Energy-Based Approach

https://github.com/chengaf/DALAUP

공식 코드

Deep Active Learning for Anchor User Prediction

https://github.com/chenhongyiyang/ppal

공식 코드

Plug and Play Active Learning for Object Detection

https://github.com/chojw/maximum-classifier-discrepancy-for-active-learning

공식 코드

MCDAL: Maximum Classifier Discrepancy for Active Learning

https://github.com/chreul/mptv

공식 코드

Improving OCR Accuracy on Early Printed Books by combining Pretraining, Voting, and Active Learning

https://github.com/chris-lange/sdm_active_sampling

공식 코드

Active Learning-Based Species Range Estimation

https://github.com/chrisantuseze/active-self-pretraining

공식 코드

A3: Active Adversarial Alignment for Source-Free Domain Adaptation

https://github.com/chritoth/active-bayesian-causal-inference

공식 코드

Active Bayesian Causal Inference

https://github.com/chschroeder/self-training-for-sample-efficient-active-learning

공식 코드

Self-Training for Sample-Efficient Active Learning for Text Classification with Pre-Trained Language Models

https://github.com/chufengt/APIS

공식 코드

Active Pointly-Supervised Instance Segmentation

https://github.com/chungimungi/Generation-of-Colors-using-BiLSTMs

공식 코드

Generation Of Colors using Bidirectional Long Short Term Memory Networks

https://github.com/chungimungi/color-prediction

공식 코드

Generation Of Colors using Bidirectional Long Short Term Memory Networks

https://github.com/cjshui/WAAL

공식 코드

Deep Active Learning: Unified and Principled Method for Query and Training

https://github.com/clinicalml/active_learn_to_defer

공식 코드

Sample Efficient Learning of Predictors that Complement Humans

https://github.com/codedecde/smal

공식 코드

On Efficiently Acquiring Annotations for Multilingual Models

https://github.com/coleygroup/molpal

공식 코드

Accelerating high-throughput virtual screening through molecular pool-based active learning

https://github.com/cosmic-cortex/modAL

공식 코드

modAL: A modular active learning framework for Python

https://github.com/crispchris/IALE

공식 코드

IALE: Imitating Active Learner Ensembles

https://github.com/cuent/ogb-kdd21

공식 코드

On Graph Neural Network Ensembles for Large-Scale Molecular Property Prediction

https://github.com/curai/curai-research

공식 코드

Adding more data does not always help: A study in medical conversation summarization with PEGASUS

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