Papers with Code 아카이브
Federated Learning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 5
- 평가표
- 12
- 보존된 평가 기록
- 61
Federated Learning is a machine learning approach that allows multiple devices or entities to collaboratively train a shared model without exchanging their data with each other. Instead of sending data to a central server for training, the model is trained locally on each device, and only the model updates are sent to the central server, where they are aggregated to improve the shared model.
This approach allows for privacy-preserving machine learning, as each device keeps its data locally and only shares the information needed to improve the model.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/dos-group/fedzero
공식 코드FedZero: Leveraging Renewable Excess Energy in Federated Learning
https://github.com/dphuongn/FLoRA
공식 코드FLoRA: Enhancing Vision-Language Models with Parameter-Efficient Federated Learning
https://github.com/dphuongn/FedDLP
공식 코드https://github.com/dphuongn/FedKEM
공식 코드Enhancing Heterogeneous Federated Learning with Knowledge Extraction and Multi-Model Fusion
https://github.com/dr-bell/data-centric-federated-learning
공식 코드Enhancing Efficiency in Multidevice Federated Learning through Data Selection
https://github.com/dskhanirfan/fets2022
공식 코드Regularized Weight Aggregation in Networked Federated Learning for Glioblastoma Segmentation
https://github.com/dtczhl/fedtuning
공식 코드FedTune: Automatic Tuning of Federated Learning Hyper-Parameters from System Perspective
https://github.com/dual-grp/fedu_fmtl
공식 코드A New Look and Convergence Rate of Federated Multi-Task Learning with Laplacian Regularization
https://github.com/duanyiyao/urvfl
공식 코드URVFL: Undetectable Data Reconstruction Attack on Vertical Federated Learning
https://github.com/dunzeng/fedaware
공식 코드On the Power of Adaptive Weighted Aggregation in Heterogeneous Federated Learning and Beyond
https://github.com/dystopians/secdood
공식 코드Secure On-Device Video OOD Detection Without Backpropagation
https://github.com/dzp2095/fcu
공식 코드Enable the Right to be Forgotten with Federated Client Unlearning in Medical Imaging
https://github.com/dzp2095/fedlsm
공식 코드Scale Federated Learning for Label Set Mismatch in Medical Image Classification
https://github.com/dzungvpham/raifle
공식 코드https://github.com/ebagdasa/backdoor_federated_learning
공식 코드https://github.com/ebagdasa/federated_adaptation
공식 코드https://github.com/ebagdasa/mithridates
공식 코드Mithridates: Auditing and Boosting Backdoor Resistance of Machine Learning Pipelines
https://github.com/ebtisaamcs/rkd
공식 코드Robust Knowledge Distillation in Federated Learning: Counteracting Backdoor Attacks
https://github.com/eceisik/ARFED
공식 코드ARFED: Attack-Resistant Federated averaging based on outlier elimination
https://github.com/eceisik/FeTS_Challenge_METU_FL_Team
공식 코드https://github.com/edouardoyallon/acco
공식 코드ACCO: Accumulate While You Communicate for Communication-Overlapped Sharded LLM Training
https://github.com/edvinli/federated-learning-mixture
공식 코드https://github.com/eechn/End-to-End-Verifiable-Decentralized-Federated-Learning
공식 코드https://github.com/eejiarong/gas
공식 코드GAS: Generative Activation-Aided Asynchronous Split Federated Learning
https://github.com/ehsanlatif/ppfl
공식 코드Privacy-Preserved Automated Scoring using Federated Learning for Educational Research
https://github.com/ehsannowroozi/federatedlearning_poison_lf_fp
공식 코드https://github.com/eis-lab/hypemefed
공식 코드Effective Heterogeneous Federated Learning via Efficient Hypernetwork-based Weight Generation
https://github.com/eleanor-w/kci_for_fl
공식 코드The More is not the Merrier: Investigating the Effect of Client Size on Federated Learning
https://github.com/eliaguerra/federated_comparison_cttc
공식 코드The Cost of Training Machine Learning Models over Distributed Data Sources
https://github.com/ellenxtan/ifedtree
공식 코드https://github.com/ellisalicante/ma-fl-mia
공식 코드https://github.com/elmahdichayti/linspeedupcode
공식 코드https://github.com/elmahdichayti/optauxinf
공식 코드https://github.com/elucidator8918/Fed-ML-Chem
공식 코드https://github.com/elucidator8918/QFL-MLNCP-NeurIPS
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.