Federated Learning
Free-Rider and Conflict Aware Collaboration Formation for Cross-Silo Federated Learning
·2733 words·13 mins·
loading
·
loading
AI Generated
Machine Learning
Federated Learning
🏢 Beijing University of Posts and Telecommunications
FedEgoists: A novel FL collaboration formation strategy mitigating free-riders & conflicts in cross-silo business settings, ensuring optimal coalition formation for improved model performance.
FOOGD: Federated Collaboration for Both Out-of-distribution Generalization and Detection
·3370 words·16 mins·
loading
·
loading
Machine Learning
Federated Learning
🏢 Zhejiang University
FOOGD: A novel federated learning framework that simultaneously tackles out-of-distribution generalization and detection by estimating probability density for reliable global distribution guidance.
Fine-Tuning Personalization in Federated Learning to Mitigate Adversarial Clients
·1780 words·9 mins·
loading
·
loading
Machine Learning
Federated Learning
🏢 EPFL
Fine-tune personalization in federated learning to beat adversarial clients; collaboration level depends on data heterogeneity and adversary fraction.
FIARSE: Model-Heterogeneous Federated Learning via Importance-Aware Submodel Extraction
·2079 words·10 mins·
loading
·
loading
Machine Learning
Federated Learning
🏢 Purdue University
FIARSE dynamically optimizes submodels in federated learning based on parameter importance, improving efficiency and global model accuracy.
Ferrari: Federated Feature Unlearning via Optimizing Feature Sensitivity
·2722 words·13 mins·
loading
·
loading
Machine Learning
Federated Learning
🏢 Universiti Malaya
Ferrari, a novel federated feature unlearning framework, minimizes feature sensitivity via Lipschitz continuity, enabling effective and privacy-preserving data removal without full client participatio…
FedSSP: Federated Graph Learning with Spectral Knowledge and Personalized Preference
·1387 words·7 mins·
loading
·
loading
Machine Learning
Federated Learning
🏢 Wuhan University
FedSSP tackles personalized federated graph learning challenges by sharing generic spectral knowledge and incorporating personalized preferences, achieving superior performance in cross-domain scenari…
FedNE: Surrogate-Assisted Federated Neighbor Embedding for Dimensionality Reduction
·2620 words·13 mins·
loading
·
loading
Machine Learning
Federated Learning
🏢 Ohio State University
FEDNE: a novel approach enabling collaborative dimensionality reduction of distributed data in federated learning without data sharing, achieved via surrogate loss functions and data augmentation.
FedLPA: One-shot Federated Learning with Layer-Wise Posterior Aggregation
·3141 words·15 mins·
loading
·
loading
Machine Learning
Federated Learning
🏢 Tsinghua University
FedLPA: One-shot federated learning with layer-wise posterior aggregation improves model accuracy in non-IID data by efficiently aggregating layer-wise posteriors of local models using a novel approac…
FedGTST: Boosting Global Transferability of Federated Models via Statistics Tuning
·1875 words·9 mins·
loading
·
loading
Machine Learning
Federated Learning
🏢 University of Illinois Urbana-Champaign
FedGTST significantly improves federated transfer learning by tuning cross-client statistics, achieving superior global transferability with minimal communication overhead.
FedGMKD: An Efficient Prototype Federated Learning Framework through Knowledge Distillation and Discrepancy-Aware Aggregation
·2196 words·11 mins·
loading
·
loading
AI Generated
Machine Learning
Federated Learning
🏢 Aberystwyth University
FedGMKD: A novel federated learning framework uses knowledge distillation and discrepancy-aware aggregation for efficient, privacy-preserving personalized learning in heterogeneous data settings.
FedGMark: Certifiably Robust Watermarking for Federated Graph Learning
·2525 words·12 mins·
loading
·
loading
Machine Learning
Federated Learning
🏢 Department of Computer Science, Illinois Institute of Technology
FedGMark: the first certified robust watermarking method for protecting Federated Graph Learning models against theft and unauthorized copying.
Federated Transformer: Multi-Party Vertical Federated Learning on Practical Fuzzily Linked Data
·3432 words·17 mins·
loading
·
loading
AI Generated
Machine Learning
Federated Learning
🏢 National University of Singapore
Federated Transformer (FeT) revolutionizes multi-party fuzzy vertical federated learning by encoding fuzzy identifiers and using a transformer architecture, achieving up to 46% accuracy improvement an…
Federated Online Prediction from Experts with Differential Privacy: Separations and Regret Speed-ups
·1475 words·7 mins·
loading
·
loading
Machine Learning
Federated Learning
🏢 Pennsylvania State University
This paper presents novel algorithms achieving speed-ups in differentially private federated online prediction from experts, addressing both stochastic and oblivious adversaries, with rigorous theoret…
Federated Model Heterogeneous Matryoshka Representation Learning
·2030 words·10 mins·
loading
·
loading
AI Generated
Machine Learning
Federated Learning
🏢 College of Computer Science, TMCC, SysNet, DISSec, GTIISC, Nankai University
FedMRL: a novel federated learning approach achieves high accuracy with low communication cost by enabling clients with heterogeneous models to collaboratively train using shared auxiliary models and …
Federated Learning under Periodic Client Participation and Heterogeneous Data: A New Communication-Efficient Algorithm and Analysis
·1715 words·9 mins·
loading
·
loading
Machine Learning
Federated Learning
🏢 George Mason University
Amplified SCAFFOLD: A new algorithm for federated learning significantly reduces communication rounds under periodic client participation and heterogeneous data, achieving linear speedup and resilienc…
Federated Learning over Connected Modes
·1775 words·9 mins·
loading
·
loading
Machine Learning
Federated Learning
🏢 TU Berlin
Federated Learning over Connected Modes (FLOCO) accelerates global training and improves local accuracy in heterogeneous data settings by leveraging mode connectivity for collaborative model personali…
Federated Graph Learning for Cross-Domain Recommendation
·2607 words·13 mins·
loading
·
loading
AI Generated
Machine Learning
Federated Learning
🏢 Xiamen University
FedGCDR, a novel federated graph learning framework, tackles cross-domain recommendation challenges by securely leveraging positive knowledge from multiple sources while mitigating negative transfer a…
Federated Behavioural Planes: Explaining the Evolution of Client Behaviour in Federated Learning
·2909 words·14 mins·
loading
·
loading
Machine Learning
Federated Learning
🏢 Università Della Svizzera Italiana
Federated Behavioural Planes visualize client behavior in federated learning, enabling robust aggregation and enhanced security against malicious clients.
FedAvP: Augment Local Data via Shared Policy in Federated Learning
·3211 words·16 mins·
loading
·
loading
Machine Learning
Federated Learning
🏢 Seoul National University
FedAvP enhances federated learning’s privacy by sharing only augmentation policies, improving performance in diverse settings.
FACT or Fiction: Can Truthful Mechanisms Eliminate Federated Free Riding?
·1605 words·8 mins·
loading
·
loading
Machine Learning
Federated Learning
🏢 University of Maryland
FACT, a novel federated learning mechanism, eliminates free-riding and incentivizes truthful agent behavior by introducing a penalty system and a competitive environment, boosting model performance si…