A typed tensor language formalizes federated computations via virtual global tensor semantics and proves shared-state factorization for one-round and iterative programs, plus a differentiable fragment for gradient descent.
hub
Flower: A Friendly Federated Learning Research Framework
39 Pith papers cite this work, alongside 107 external citations. Polarity classification is still indexing.
39
Pith papers citing it
107
external citations · Pith
abstract
Federated Learning (FL) has emerged as a promising technique for edge devices to collaboratively learn a shared prediction model, while keeping their training data on the device, thereby decoupling the ability to do machine learning from the need to store the data in the cloud. However, FL is difficult to implement realistically, both in terms of scale and systems heterogeneity. Although there are a number of research frameworks available to simulate FL algorithms, they do not support the study of scalable FL workloads on heterogeneous edge devices. In this paper, we present Flower -- a comprehensive FL framework that distinguishes itself from existing platforms by offering new facilities to execute large-scale FL experiments and consider richly heterogeneous FL device scenarios. Our experiments show Flower can perform FL experiments up to 15M in client size using only a pair of high-end GPUs. Researchers can then seamlessly migrate experiments to real devices to examine other parts of the design space. We believe Flower provides the community with a critical new tool for FL study and development.
hub tools
citation-role summary
background 2
method 1
citation-polarity summary
representative citing papers
The FedSurg challenge benchmarks federated learning on appendectomy videos and finds only 26% F1 on unseen centers even with centralized data, plus extra penalties from decentralization, with spatiotemporal models performing best.
FeDa4Fair is a new library and benchmark for creating federated datasets with heterogeneous client-level biases to standardize evaluation of fairness methods in federated learning.
Real 5G testbed experiments show consistent stragglers in 70% of federated learning trials due to communication delays, challenging common wireless FL assumptions.
FeLiX reduces wall-clock time-to-target accuracy in federated learning by up to 2.37x using lightweight availability tiers, fresh-utility client selection, and informativeness-aware aggregation without requiring oracular knowledge of client availability.
Inertia-weighted FedAvg plus RoCoF-augmented ChebyKAN controllers achieve 75% generalization on unseen IEEE-39 faults and beat centralized PFL on two of three stabilized cases at full decentralization.
BlockTrain partitions models into block-local diffusion objectives that train near end-to-end WikiText quality with one-block worker memory, real WAN transport, and one-sweep distributed serving.
FLKit is a new toolkit with four lifecycle stages, eleven role-specific entry points, a glossary, FL Story template, and tool directory to support federated learning projects in health and life sciences.
FSC uses unsupervised clustering for pseudo-label episodes and a three-stage federated pipeline to achieve 71.6% accuracy in 2-way 2-shot in-context diagnosis of respiratory and cardiac audio conditions.
Fed-FBD decomposes ResNet into independently tracked functional blocks with color variants to deliver block-level isolation, chance-level membership inference, and sub-second surgical unlearning in federated learning on medical and CIFAR datasets.
New cycle-consistent optimization, task vector theory, singular vector decompositions, adaptive routing, and efficient evolutionary search provide foundations for merging neural network weights across tasks.
Harmonization works better than personalization for appearance-based domain shifts in federated medical imaging while personalization is superior for structural shifts, with both performing similarly when shifts are small.
AW-PSP dynamically weights node sampling by real-time availability predictions and failure correlations to improve robustness, label coverage, and fairness in federated learning under correlated device failures.
CroSatFL cuts ground station communications by over 100x and transmission energy by 6x in satellite federated learning compared to baselines, while keeping competitive accuracy.
FedRouter clusters adapters locally per task samples and globally across clients to create task-centric personalized models, improving generalization and reducing task interference in federated fine-tuning.
Federated learning trains private local randomised predictors whose aggregation yields a global predictor with nonvacuous PAC-Bayesian generalisation bounds and near-centralized accuracy.
GEN-Guard detects generalization failures in federated surgical AI via client-blocked evaluation and corrects them via disagreement-aware distillation, yielding reported gains on in-federation, unseen-institution, and worst-case performance.
DFL-AA removes link-quality distortion in expectation from gossip aggregation in asynchronous decentralized federated learning by combining online IPW for selection bias correction with AoI weighting for staleness mitigation.
pFedCKKS derives CKKS parameter constraints for PFL under 128-bit security reducing choices to inner and outer ciphertext primes and evaluates precision-cost trade-offs on FEMNIST, CelebA and Sentiment140.
QSplitFL is a DQN framework that selects split points in split federated learning from hardware metrics with a decayed loss-drop reward and committee voting, reporting faster convergence and higher accuracy than baselines on image classification tasks.
FPLIER performs federated PLIER training via secure aggregation that is algebraically equivalent to centralized training, with membership-inference risk shown to decrease as the rank of the expression matrix increases.
M²FedAQI is a lightweight multimodal federated framework that fuses visual and tabular data via feature modulation for improved AQI prediction and regression on heterogeneous edge devices.
FedSSG generates and shares synthetic samples within a federated setup to reduce class imbalance and domain shift problems in medical image classification.
Fed-FSTQ uses Fisher-guided token quantization to cut uplink traffic 46-fold and improve straggler-limited time-to-accuracy by 52% versus Fed-LoRA in non-IID multilingual and medical QA tasks.
citing papers explorer
-
A Typed Tensor Language for Federated Learning
A typed tensor language formalizes federated computations via virtual global tensor semantics and proves shared-state factorization for one-round and iterative programs, plus a differentiable fragment for gradient descent.
-
Federated Learning for Surgical Vision in Appendicitis Classification: Results of the FedSurg EndoVis 2024 Challenge
The FedSurg challenge benchmarks federated learning on appendectomy videos and finds only 26% F1 on unseen centers even with centralized data, plus extra penalties from decentralization, with spatiotemporal models performing best.
-
FeDa4Fair: Client-Level Federated Datasets for Fairness Evaluation
FeDa4Fair is a new library and benchmark for creating federated datasets with heterogeneous client-level biases to standardize evaluation of fairness methods in federated learning.
-
Beyond Assumptions: Measuring Federated Learning over Real 5G Networks
Real 5G testbed experiments show consistent stragglers in 70% of federated learning trials due to communication delays, challenging common wireless FL assumptions.
-
Robust Federated Learning Under Real-World Client Churn
FeLiX reduces wall-clock time-to-target accuracy in federated learning by up to 2.37x using lightweight availability tiers, fresh-utility client selection, and informativeness-aware aggregation without requiring oracular knowledge of client availability.
-
Inertia-Informed Federated Learning Control Framework for Distributed Smart Grid Resilience
Inertia-weighted FedAvg plus RoCoF-augmented ChebyKAN controllers achieve 75% generalization on unseen IEEE-39 faults and beat centralized PFL on two of three stabilized cases at full decentralization.
-
Decentralised AI Training and Inference with BlockTrain
BlockTrain partitions models into block-local diffusion objectives that train near end-to-end WikiText quality with one-block worker memory, real WAN transport, and one-sweep distributed serving.
-
Development and Design of FLKit: A Structured Onboarding Toolkit for Federated Learning in Health and Life Sciences
FLKit is a new toolkit with four lifecycle stages, eleven role-specific entry points, a glossary, FL Story template, and tool directory to support federated learning projects in health and life sciences.
-
Unlocking In-Context Learning in Audio-Language Models from Decentralized Medical Audio
FSC uses unsupervised clustering for pseudo-label episodes and a three-stage federated pipeline to achieve 71.6% accuracy in 2-way 2-shot in-context diagnosis of respiratory and cardiac audio conditions.
-
Fed-FBD: Federated Functional Block Diversification for Isolation, Privacy, and Surgical Unlearning
Fed-FBD decomposes ResNet into independently tracked functional blocks with color variants to deliver block-level isolation, chance-level membership inference, and sub-second surgical unlearning in federated learning on medical and CIFAR datasets.
-
Model Merging: Foundations and Algorithms
New cycle-consistent optimization, task vector theory, singular vector decompositions, adaptive routing, and efficient evolutionary search provide foundations for merging neural network weights across tasks.
-
When To Adapt? Adapting the Model or Data in Federated Medical Imaging
Harmonization works better than personalization for appearance-based domain shifts in federated medical imaging while personalization is superior for structural shifts, with both performing similarly when shifts are small.
-
Robust Synchronisation for Federated Learning in The Face of Correlated Device Failure
AW-PSP dynamically weights node sampling by real-time availability predictions and failure correlations to improve robustness, label coverage, and fairness in federated learning under correlated device failures.
-
CroSatFL: Energy-Efficient Federated Learning with Cross-Aggregation for Satellite Edge Computing
CroSatFL cuts ground station communications by over 100x and transmission energy by 6x in satellite federated learning compared to baselines, while keeping competitive accuracy.
-
Task-Centric Personalized Federated Fine-Tuning of Language Models
FedRouter clusters adapters locally per task samples and globally across clients to create task-centric personalized models, improving generalization and reducing task interference in federated fine-tuning.
-
Federated Learning with Nonvacuous Generalisation Bounds
Federated learning trains private local randomised predictors whose aggregation yields a global predictor with nonvacuous PAC-Bayesian generalisation bounds and near-centralized accuracy.
-
GEN-Guard: Correcting Generalization Failures for Deployable Federated Surgical AI
GEN-Guard detects generalization failures in federated surgical AI via client-blocked evaluation and corrects them via disagreement-aware distillation, yielding reported gains on in-federation, unseen-institution, and worst-case performance.
-
Asynchronous Decentralized Federated Learning over Lossy Wireless Links via Reception- and Age-Aware Aggregation
DFL-AA removes link-quality distortion in expectation from gossip aggregation in asynchronous decentralized federated learning by combining online IPW for selection bias correction with AoI weighting for staleness mitigation.
-
Exploring CKKS Parameter Trade-offs for Privacy-Preserving Personalized Federated Learning
pFedCKKS derives CKKS parameter constraints for PFL under 128-bit security reducing choices to inner and outer ciphertext primes and evaluates precision-cost trade-offs on FEMNIST, CelebA and Sentiment140.
-
QSplitFL: Capability Aware Deep Q-Learning for Optimal Split Point Selection in Split Federated Learning
QSplitFL is a DQN framework that selects split points in split federated learning from hardware metrics with a decayed loss-drop reward and committee voting, reporting faster convergence and higher accuracy than baselines on image classification tasks.
-
FPLIER: Federated Pathway-Level Information Extractor
FPLIER performs federated PLIER training via secure aggregation that is algebraically equivalent to centralized training, with membership-inference risk shown to decrease as the rank of the expression matrix increases.
-
M$^2$FedAQI: Multimodal Federated Learning for Air Quality Prediction on Heterogeneous Edge Devices
M²FedAQI is a lightweight multimodal federated framework that fuses visual and tabular data via feature modulation for improved AQI prediction and regression on heterogeneous edge devices.
-
Federated Medical Image Classification under Class and Domain Imbalance exploiting Synthetic Sample Generation
FedSSG generates and shares synthetic samples within a federated setup to reduce class imbalance and domain shift problems in medical image classification.
-
FED-FSTQ: Fisher-Guided Token Quantization for Communication-Efficient Federated Fine-Tuning of LLMs on Edge Devices
Fed-FSTQ uses Fisher-guided token quantization to cut uplink traffic 46-fold and improve straggler-limited time-to-accuracy by 52% versus Fed-LoRA in non-IID multilingual and medical QA tasks.
-
OpenCLAW-Nexus: A Self-Reinforcing Trust Framework for Byzantine-Resilient Decentralized Federated Learning
OpenCLAW-Nexus uses a single discounted Beta-reputation model to unify reputation-based node selection, Rep-FedAvg aggregation, and reputation-aware BFT consensus, achieving Byzantine resilience in decentralized FL with 72.6% accuracy on non-IID CIFAR-10 under 20% attacks.
-
Cooperate to Compete: Strategic Data Generation and Incentivization Framework for Coopetitive Cross-Silo Federated Learning
CoCoGen+ models each federated learning round as a weighted potential game with strategic synthetic data generation and payoff redistribution incentives, showing improved efficiency over baselines under non-IID data and competition.
-
Evaluating Differential Privacy Against Membership Inference in Federated Learning: Insights from the NIST Genomics Red Team Challenge
Stacking seven black-box estimators into a meta-classifier reveals persistent membership leakage in differentially private federated learning models at epsilon=200 on NIST genomics data, outperforming single-signal baselines.
-
AI4EOSC: a Federated Cloud Platform for Artificial Intelligence in Scientific Research
AI4EOSC combines federated cloud scheduling, serverless inference, FAIR metadata, and provenance into one open platform for European research AI.
-
FedRef: Bayesian Fine-Tuning using a Reference Model to Mitigate Catastrophic Forgetting for Heterogeneous Federated Learning
FedRef uses a temporally aggregated reference model and MAP regularization for server-side fine-tuning to reduce forgetting and drift in non-IID federated learning, showing better accuracy and lower client compute on image tasks.
-
Federated Survival Analysis in Healthcare: A Multi-Model Evaluation on Cross-Institutional Heterogeneous Breast Cancer Data
Federated training of Cox, DeepSurv, and Random Survival Forest models on cross-institutional breast cancer data outperforms local training and approaches centralized performance, with RSF showing the best overall balance.
-
FedMTFI: Feature Importance Based Optimized Multi Teacher Knowledge Distillation in Heterogeneous Federated Learning Environment
FedMTFI clusters heterogeneous clients, trains cluster prototypes, and applies multi-teacher distillation with SHAP to improve accuracy over standard FL in non-IID settings.
-
GuidaPA: Privacy-Preserving Chatbot for Public Administration via Federated Learning
Federated QLoRA fine-tuning on distributed PA manuals from SIGESON and SIDFORS yields ROUGE-1/2/L of 61.10/55.77/59.44 and BLEU-4 of 45.02, close to centralized training.
-
Embedding-Based Federated Learning with Runtime Governance for Iron Deficiency Prediction
An embedding-based federated learning system with a frozen haematology foundation model and personalised aggregation (FedMAP) improves iron deficiency prediction across two non-IID clinical sites over local-only training.
-
Understanding Communication Backends in Cross-Silo Federated Learning
Benchmarks of MPI, gRPC, and PyTorch RPC in cross-silo FL plus a new gRPC+S3 hybrid backend deliver up to 3.8x speedup for large-model transmission under realistic network conditions.
-
Automating aggregation strategy selection in federated learning
A framework automates federated learning aggregation strategy selection via LLM inference in single-trial mode and genetic search in multi-trial mode, improving robustness under non-IID data.
-
Federated Learning for ICD Classification with Lightweight Models and Pretrained Embeddings
Lightweight federated learning with frozen embeddings and MLP heads reaches competitive micro and macro F1 scores for ICD-9 and ICD-10 coding on MIMIC-IV, nearly matching centralized training.
-
DeTrigger: A Gradient-Centric Approach to Backdoor Attack Mitigation in Federated Learning
DeTrigger detects and mitigates backdoor attacks in federated learning via gradient analysis and temperature scaling, claiming up to 251x faster detection and 98.9% attack reduction on four datasets with minimal accuracy loss.
-
Semi-asynchronous Federated Learning in Flower: Framework Extension and Performance Assessment
Extends Flower framework with FedSaSync semi-asynchronous strategy, claiming reduced idle time versus synchronous baselines in heterogeneous settings.
-
A Comparative Study of Federated Learning Aggregation Strategies under Homogeneous and Heterogeneous Data Distributions
Federated aggregation strategies show distinct performance trade-offs in accuracy, loss, and efficiency depending on whether client data distributions are homogeneous or heterogeneous.