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/mly-nlp/LJP-MSJudge
공식 코드Legal Judgment Prediction with Multi-Stage CaseRepresentation Learning in the Real Court Setting
https://github.com/mlzxy/visual-kinetic-chain
공식 코드Scaling Manipulation Learning with Visual Kinematic Chain Prediction
https://github.com/mmatena/model_merging
공식 코드https://github.com/mmcdermott/comprehensive_MTL_EHR
공식 코드https://github.com/mmorafah/takfl
공식 코드Towards Diverse Device Heterogeneous Federated Learning via Task Arithmetic Knowledge Integration
https://github.com/mobarakol/AP-MTL
공식 코드https://github.com/mobarakol/ST-MTL
공식 코드https://github.com/moghadas76/gintrip
공식 코드https://github.com/mohammadmahdinoori/nowruz-at-semeval-2022-task-7
공식 코드Nowruz at SemEval-2022 Task 7: Tackling Cloze Tests with Transformers and Ordinal Regression
https://github.com/mohsenbayati/cv-impute
공식 코드On Low-rank Trace Regression under General Sampling Distribution
https://github.com/mooncake199809/ufvl-net
공식 코드OFVL-MS: Once for Visual Localization across Multiple Indoor Scenes
https://github.com/moranli-aca/LearnableGroups-Hand
공식 코드https://github.com/mortezaro/mtl-disfluency-detection
공식 코드Re-framing Incremental Deep Language Models for Dialogue Processing with Multi-task Learning
https://github.com/moukamisama/recon
공식 코드Recon: Reducing Conflicting Gradients from the Root for Multi-Task Learning
https://github.com/mrchor/FDN
공식 코드https://github.com/mrchor/HiNet
공식 코드HiNet: Novel Multi-Scenario & Multi-Task Learning with Hierarchical Information Extraction
https://github.com/mrqa/MRQA-Shared-Task-2019
공식 코드MRQA 2019 Shared Task: Evaluating Generalization in Reading Comprehension
https://github.com/ms-dot-k/Lip-to-Speech-Synthesis-in-the-Wild
공식 코드Lip-to-Speech Synthesis in the Wild with Multi-task Learning
https://github.com/msa-lmc/s4d
공식 코드https://github.com/msadat3/scihtc
공식 코드Hierarchical Multi-Label Classification of Scientific Documents
https://github.com/mtcrawshaw/meta
공식 코드SLAW: Scaled Loss Approximate Weighting for Efficient Multi-Task Learning
https://github.com/muhaochen/bilingual_dictionaries
공식 코드https://github.com/mungomeng/deepmts
공식 코드https://github.com/mungomeng/survival-adamss
공식 코드https://github.com/mungomeng/survival-deepmss
공식 코드https://github.com/mungomeng/survival-deepmts
공식 코드https://github.com/nPIML-team/nPIML
공식 코드Noise-aware Physics-informed Machine Learning for Robust PDE Discovery
https://github.com/nailperry-zd/paddleseg-trianglenet
공식 코드TriangleNet: Edge Prior Augmented Network for Semantic Segmentation through Cross-Task Consistency
https://github.com/namisan/mt-dnn
공식 코드https://github.com/namtuanly/MTL-TabNet
공식 코드An End-to-End Multi-Task Learning Model for Image-based Table Recognition
https://github.com/naver-ai/dawin
공식 코드DaWin: Training-free Dynamic Weight Interpolation for Robust Adaptation
https://github.com/naver-ai/egtr
공식 코드EGTR: Extracting Graph from Transformer for Scene Graph Generation
https://github.com/naver-ai/negmerge
공식 코드NegMerge: Consensual Weight Negation for Strong Machine Unlearning
https://github.com/ncbi-nlp/bluebert
공식 코드An Empirical Study of Multi-Task Learning on BERT for Biomedical Text Mining
https://github.com/ncbi/aioner
공식 코드AIONER: All-in-one scheme-based biomedical named entity recognition using deep learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.