Papers with Code 아카이브

Meta-Learning

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

하위 태스크: 3
평가표: 4
보존된 평가 기록: 13

Meta-learning is a methodology considered with "learning to learn" machine learning algorithms.

<span style="color:grey; opacity: 0.6">( Image credit: Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks )</span>

코드

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

https://github.com/tomsherborne/xgr

공식 코드

Meta-Learning a Cross-lingual Manifold for Semantic Parsing

https://github.com/tomte812/chef

공식 코드

Cross-Domain Few-Shot Learning by Representation Fusion

https://github.com/tonysy/PyAction

공식 코드

Learning Implicit Temporal Alignment for Few-shot Video Classification

https://github.com/tonyzhaozh/few-shot-learning

공식 코드

Calibrate Before Use: Improving Few-Shot Performance of Language Models

https://github.com/tonyzhaozh/meld

공식 코드

MELD: Meta-Reinforcement Learning from Images via Latent State Models

https://github.com/towardsautonomy/meta_reg_by_enforcing_mutual_exclusiveness

공식 코드

Meta-Regularization by Enforcing Mutual-Exclusiveness

https://github.com/tqzhong/cg4mctg

공식 코드

Benchmarking and Improving Compositional Generalization of Multi-aspect Controllable Text Generation

https://github.com/transmuteai/metadock

공식 코드

Dynamic Kernel Selection for Improved Generalization and Memory Efficiency in Meta-learning

https://github.com/tricktreat/promptner

공식 코드

PromptNER: Prompt Locating and Typing for Named Entity Recognition

https://github.com/tristandeleu/pytorch-meta

공식 코드

Torchmeta: A Meta-Learning library for PyTorch

https://github.com/tristandeleu/synergies-disentanglement-sparsity

공식 코드

Synergies between Disentanglement and Sparsity: Generalization and Identifiability in Multi-Task Learning

https://github.com/tsinghua-fib-lab/gpd

공식 코드

Spatio-Temporal Few-Shot Learning via Diffusive Neural Network Generation

https://github.com/tsinghuac3i/llm4biohypogen

공식 코드

Large Language Models as Biomedical Hypothesis Generators: A Comprehensive Evaluation

https://github.com/tuantuange/dhm-uht

공식 코드

Unsupervised Meta-Learning via Dynamic Head and Heterogeneous Task Construction for Few-Shot Classification

https://github.com/tung-nd/tnp-pytorch

공식 코드

Transformer Neural Processes: Uncertainty-Aware Meta Learning Via Sequence Modeling

https://github.com/tunib-ai/parallelformers

공식 코드

Few-Shot Bot: Prompt-Based Learning for Dialogue Systems

https://github.com/twelfth-star/LinkGPT

공식 코드

LinkGPT: Teaching Large Language Models To Predict Missing Links

https://github.com/txsun1997/black-box-tuning

공식 코드

BBTv2: Towards a Gradient-Free Future with Large Language Models

https://github.com/tyhuang0428/CLIP2Point

공식 코드

CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-training

https://github.com/tylersco/adapted_deep_embeddings

공식 코드

Adapted Deep Embeddings: A Synthesis of Methods for $k$-Shot Inductive Transfer Learning

https://github.com/tyliu22/Meta-learning-PAC-Bayes-bound-with-data-depedent-prior

공식 코드

PAC-Bayes Bounds for Meta-learning with Data-Dependent Prior

https://github.com/typilus/typilus

공식 코드

Typilus: Neural Type Hints

https://github.com/ubc-nlp/sparrow

공식 코드

The Skipped Beat: A Study of Sociopragmatic Understanding in LLMs for 64 Languages

https://github.com/uber-common/differentiable-plasticity

공식 코드

Differentiable plasticity: training plastic neural networks with backpropagation

https://github.com/uber-research/Evolvability-ES

공식 코드

Evolvability ES: Scalable and Direct Optimization of Evolvability

https://github.com/uber-research/learning-to-reweight-examples

공식 코드

Learning to Reweight Examples for Robust Deep Learning

https://github.com/uber/ludwig

공식 코드

Ludwig: a type-based declarative deep learning toolbox

https://github.com/ubiquitouslearning/fes

공식 코드

Federated Few-Shot Learning for Mobile NLP

https://github.com/ucbdrive/few-shot-object-detection

공식 코드

Frustratingly Simple Few-Shot Object Detection

https://github.com/ucbdrive/tafe-net

공식 코드

TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learning

https://github.com/uci-cbcl/RP-Net

공식 코드

Recurrent Mask Refinement for Few-Shot Medical Image Segmentation

https://github.com/ucinlp/null-prompts

공식 코드

Cutting Down on Prompts and Parameters: Simple Few-Shot Learning with Language Models

https://github.com/uclanlp/paraamr

공식 코드

ParaAMR: A Large-Scale Syntactically Diverse Paraphrase Dataset by AMR Back-Translation

https://github.com/udelaqui/foundation_models_for_polyp_detection_segmentation

공식 코드

AI-Assisted Colonoscopy: Polyp Detection and Segmentation using Foundation Models

https://github.com/uic-liu-lab/cpt

공식 코드

Continual Training of Language Models for Few-Shot Learning

https://github.com/uitml/nohub

공식 코드

Hubs and Hyperspheres: Reducing Hubness and Improving Transductive Few-shot Learning with Hyperspherical Embeddings

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