Papers with Code 아카이브
Transfer Learning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 4
- 평가표
- 6
- 보존된 평가 기록
- 10
Transfer Learning is a machine learning technique where a model trained on one task is re-purposed and fine-tuned for a related, but different task. The idea behind transfer learning is to leverage the knowledge learned from a pre-trained model to solve a new, but related problem. This can be useful in situations where there is limited data available to train a new model from scratch, or when the new task is similar enough to the original task that the pre-trained model can be adapted to the new problem with only minor modifications.
<span style="color:grey; opacity: 0.6">( Image credit: Subodh Malgonde )</span>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/neuron1682/cross-lingual-phenotype-prediction
공식 코드https://github.com/neutralpronoun/general-gcl
공식 코드Topology Only Pre-Training: Towards Generalised Multi-Domain Graph Models
https://github.com/news-vt/makassar-ml
공식 코드A Transformer Framework for Data Fusion and Multi-Task Learning in Smart Cities
https://github.com/ngailapdi/CLRec
공식 코드The Surprising Positive Knowledge Transfer in Continual 3D Object Shape Reconstruction
https://github.com/nghuyong/MTL-SLAM
공식 코드Multi-task Learning for Low-resource Second Language Acquisition Modeling
https://github.com/ngminhtri0394/c2p2
공식 코드https://github.com/ngoc-nguyen-0/LOKT_neurips2023
공식 코드https://github.com/nguyentthong/CrossSummOptimalTransport
공식 코드https://github.com/nguyentthong/Paper-VLP
공식 코드https://github.com/nguyentthong/READ
공식 코드https://github.com/nhiratani/transfer_retention_model
공식 코드Disentangling and Mitigating the Impact of Task Similarity for Continual Learning
https://github.com/niiceMing/CMTA
공식 코드Contrastive Modules with Temporal Attention for Multi-Task Reinforcement Learning
https://github.com/nik-dim/pamal
공식 코드Pareto Manifold Learning: Tackling multiple tasks via ensembles of single-task models
https://github.com/nik-dim/tall_masks
공식 코드Localizing Task Information for Improved Model Merging and Compression
https://github.com/nikitacs16/xlift_dst
공식 코드Cross-lingual Intermediate Fine-tuning improves Dialogue State Tracking
https://github.com/nilakshdas/skelevision
공식 코드SkeleVision: Towards Adversarial Resiliency of Person Tracking with Multi-Task Learning
https://github.com/niloofaryousefi/ECML2015
공식 코드Multi-Task Learning with Group-Specific Feature Space Sharing
https://github.com/nineabyss/zerog
공식 코드ZeroG: Investigating Cross-dataset Zero-shot Transferability in Graphs
https://github.com/ninglab/TransferAct
공식 코드Improving Compound Activity Classification via Deep Transfer and Representation Learning
https://github.com/ningyu1991/DefectDetection
공식 코드https://github.com/ningyuxu/structural_concepts_correspondence
공식 코드https://github.com/nishchalprasad/mesc
공식 코드https://github.com/niuchuangnn/m3fm
공식 코드Specialty-Oriented Generalist Medical AI for Chest CT Screening
https://github.com/nju-websoft/lkge
공식 코드Lifelong Embedding Learning and Transfer for Growing Knowledge Graphs
https://github.com/nju-websoft/mukge
공식 코드https://github.com/nju-websoft/sckd
공식 코드Serial Contrastive Knowledge Distillation for Continual Few-shot Relation Extraction
https://github.com/njuhugn/CoNet
공식 코드CoNet: Collaborative Cross Networks for Cross-Domain Recommendation
https://github.com/njunlp/id-ockr
공식 코드Large Language Models are Limited in Out-of-Context Knowledge Reasoning
https://github.com/nkusyl/evit
공식 코드EViT: An Eagle Vision Transformer with Bi-Fovea Self-Attention
https://github.com/nlee0212/crehate
공식 코드https://github.com/nlp-waseda/expr-exper-emo
공식 코드Building a Dialogue Corpus Annotated with Expressed and Experienced Emotions
https://github.com/nlp2ct/consisttl
공식 코드ConsistTL: Modeling Consistency in Transfer Learning for Low-Resource Neural Machine Translation
https://github.com/nlp2ct/unite
공식 코드https://github.com/nlpfreshman0/more
공식 코드MoRE: A Mixture of Low-Rank Experts for Adaptive Multi-Task Learning
https://github.com/nmi-lab/snn_maml
공식 코드Emulating Brain-like Rapid Learning in Neuromorphic Edge Computing
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.