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/brjathu/RPSnet
공식 코드An Adaptive Random Path Selection Approach for Incremental Learning
https://github.com/brozosc/graph-neural-networks-for-surfactant-multi-property-prediction
공식 코드Graph Neural Networks for Surfactant Multi-Property Prediction
https://github.com/brucewsy/ad-kd
공식 코드AD-KD: Attribution-Driven Knowledge Distillation for Language Model Compression
https://github.com/bruceyo/V-PETL
공식 코드Towards a Unified View on Visual Parameter-Efficient Transfer Learning
https://github.com/brunoclr/molgen_opt
공식 코드Molecule Generation and Optimization for Efficient Fragrance Creation
https://github.com/brunotruthalliance/resflow
공식 코드https://github.com/bryanzhou008/advancing-commonsense-reasoning
공식 코드Advancing Transformer's Capabilities in Commonsense Reasoning
https://github.com/btjhjeon/IMM_tensorflow
공식 코드Overcoming Catastrophic Forgetting by Incremental Moment Matching
https://github.com/budnikm/aml
공식 코드https://github.com/budzianowski/multiwoz
공식 코드Know Thy Strengths: Comprehensive Dialogue State Tracking Diagnostics
https://github.com/bumble666/hypermoe_early_version
공식 코드HyperMoE: Towards Better Mixture of Experts via Transferring Among Experts
https://github.com/bumble666/pha
공식 코드Prototype-based HyperAdapter for Sample-Efficient Multi-task Tuning
https://github.com/bundlerecommender/bundlemage
공식 코드Accurate Bundle Matching and Generation via Multitask Learning with Partially Shared Parameters
https://github.com/bupt-ai-cz/proml
공식 코드Semi-supervised Domain Adaptation via Prototype-based Multi-level Learning
https://github.com/bupt-ai-cz/restnet
공식 코드RestNet: Boosting Cross-Domain Few-Shot Segmentation with Residual Transformation Network
https://github.com/burakekim/MTL_homoscedastic_SRB
공식 코드A Multi-Task Deep Learning Framework for Building Footprint Segmentation
https://github.com/byaman14/ZS-SSL
공식 코드https://github.com/byeongjun-park/DTR
공식 코드https://github.com/byeongjun-park/Switch-DiT
공식 코드Switch Diffusion Transformer: Synergizing Denoising Tasks with Sparse Mixture-of-Experts
https://github.com/bytedance/TWIST
공식 코드Self-Supervised Learning by Estimating Twin Class Distributions
https://github.com/bytefuse/representation-manifold-quality-metric
공식 코드Manifold Characteristics That Predict Downstream Task Performance
https://github.com/c16mftang/biological-ssl
공식 코드Biologically Plausible Training Mechanisms for Self-Supervised Learning in Deep Networks
https://github.com/c3imaging/child_tts_fastpitch
공식 코드Improved Child Text-to-Speech Synthesis through Fastpitch-based Transfer Learning
https://github.com/caesarea38/doclangid
공식 코드DocLangID: Improving Few-Shot Training to Identify the Language of Historical Documents
https://github.com/caidog1129/milp_multitask
공식 코드Multi-task Representation Learning for Mixed Integer Linear Programming
https://github.com/caizexin/tf_multispeakerTTS_fc
공식 코드From Speaker Verification to Multispeaker Speech Synthesis, Deep Transfer with Feedback Constraint
https://github.com/cake-lab/datafree-model-extraction
공식 코드https://github.com/calclavia/story-generation
공식 코드Improving Neural Story Generation by Targeted Common Sense Grounding
https://github.com/calubkk/raat
공식 코드Enhancing Noise Robustness of Retrieval-Augmented Language Models with Adaptive Adversarial Training
https://github.com/calvinchengyx/cross-lan-mft-measure
공식 코드https://github.com/cambridge-mlg/LITE
공식 코드https://github.com/cambridge-mlg/cnaps
공식 코드Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processes
https://github.com/cambridge-mlg/fit
공식 코드https://github.com/cambridgeltl/ECNMT
공식 코드Emergent Communication Pretraining for Few-Shot Machine Translation
https://github.com/cambridgeltl/composable-sft
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.