Papers with Code 아카이브

Multi-Task Learning

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

하위 태스크: 2
평가표: 8
보존된 평가 기록: 16

Multi-task learning aims to learn multiple different tasks simultaneously while maximizing performance on one or all of the tasks.

<span style="color:grey; opacity: 0.6">( Image credit: Cross-stitch Networks for Multi-task Learning )</span>

코드

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

https://github.com/qianc62/MGTC

공식 코드

An Approach for Process Model Extraction By Multi-Grained Text Classification

https://github.com/qingyu-qc/bioner_gerbera

공식 코드

Augmenting Biomedical Named Entity Recognition with General-domain Resources

https://github.com/qiyu3816/MTFNN-CO

공식 코드

A Multi-Head Ensemble Multi-Task Learning Approach for Dynamical Computation Offloading

https://github.com/qzhb/srl

공식 코드

Self-Regulated Learning for Egocentric Video Activity Anticipation

https://github.com/rabeehk/hyperformer

공식 코드

Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks

https://github.com/rachel-1/qa_plausibility

공식 코드

Determining Question-Answer Plausibility in Crowdsourced Datasets Using Multi-Task Learning

https://github.com/rachneet/cross-task-figurative-explanations

공식 코드

Effective Cross-Task Transfer Learning for Explainable Natural Language Inference with T5

https://github.com/rail-berkeley/BridgeData-V2

공식 코드

BridgeData V2: A Dataset for Robot Learning at Scale

https://github.com/rajdeep345/mtlts

공식 코드

MTLTS: A Multi-Task Framework To Obtain Trustworthy Summaries From Crisis-Related Microblogs

https://github.com/ramakanth-pasunuru/CAS-MAS

공식 코드

Continual and Multi-Task Architecture Search

https://github.com/raquelaoki/m3e2

공식 코드

Multi-treatment Effect Estimation from Biomedical Data

https://github.com/raumannsr/ENHANCE

공식 코드

ENHANCE (ENriching Health data by ANnotations of Crowd and Experts): A case study for skin lesion classification

https://github.com/raumannsr/hints_crowd

공식 코드

Multi-task Ensembles with Crowdsourced Features Improve Skin Lesion Diagnosis

https://github.com/ravikiranrao/mtclar-fsl

공식 코드

Efficient Labelling of Affective Video Datasets via Few-Shot & Multi-Task Contrastive Learning

https://github.com/renzhenwang/label-hierarchy-transition

공식 코드

Label Hierarchy Transition: Delving into Class Hierarchies to Enhance Deep Classifiers

https://github.com/retkowsky/florence-2

공식 코드

Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks

https://github.com/rgwt123/DialogueMT

공식 코드

Autocorrect in the Process of Translation -- Multi-task Learning Improves Dialogue Machine Translation

https://github.com/rickgroen/cov-weighting

공식 코드

Multi-Loss Weighting with Coefficient of Variations

https://github.com/ricupa/layer-optimized-multi-task-model

공식 코드

Giving each task what it needs -- leveraging structured sparsity for tailored multi-task learning

https://github.com/ricupa/less-is-more-towards-parsimonious-multi-task-models-using-structured-sparsity

공식 코드

Less is More -- Towards parsimonious multi-task models using structured sparsity

https://github.com/ricupa/mtml-learn-how-to-adapt-to-unseen-tasks

공식 코드

Multi-Task Meta Learning: learn how to adapt to unseen tasks

https://github.com/ritikajha/Attribute-prediction-in-masked-facial-images-with-deep-multitask-learning

공식 코드

MaskMTL: Attribute prediction in masked facial images with deep multitask learning

https://github.com/rlworkgroup/metaworld

공식 코드

Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning

https://github.com/rohitash-chandra/CMTL_dynamictimeseries

공식 코드

Co-evolutionary multi-task learning for dynamic time series prediction

https://github.com/rolsheng/mm-vufm4ds

공식 코드

Delving into Multi-modal Multi-task Foundation Models for Road Scene Understanding: From Learning Paradigm Perspectives

https://github.com/rotmanguy/mtal

공식 코드

Multi-task Active Learning for Pre-trained Transformer-based Models

https://github.com/royabel/top-down-networks

공식 코드

Biologically-Motivated Learning Model for Instructed Visual Processing

https://github.com/royalskye/routing-mvmoe

공식 코드

MVMoE: Multi-Task Vehicle Routing Solver with Mixture-of-Experts

https://github.com/rperi/trustworthy-asv-fairness

공식 코드

To train or not to train adversarially: A study of bias mitigation strategies for speaker recognition

https://github.com/rrahmati/roboinstruct-2

공식 코드

Vision-Based Multi-Task Manipulation for Inexpensive Robots Using End-To-End Learning from Demonstration

https://github.com/rucaibox/mpo

공식 코드

Parameter-Efficient Mixture-of-Experts Architecture for Pre-trained Language Models

https://github.com/rucaibox/mpoe

공식 코드

Parameter-Efficient Mixture-of-Experts Architecture for Pre-trained Language Models

https://github.com/ruchtem/moo-mtl

공식 코드

Multi-task problems are not multi-objective

https://github.com/ruidan/IMN-E2E-ABSA

공식 코드

An Interactive Multi-Task Learning Network for End-to-End Aspect-Based Sentiment Analysis

https://github.com/ruili33/sec

공식 코드

Are Human-generated Demonstrations Necessary for In-context Learning?

https://github.com/s-huu/pmtl

공식 코드

Private Multi-Task Learning: Formulation and Applications to Federated Learning

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