• Corpus ID: 234599864

FedCV: A Federated Learning Framework for Diverse Computer Vision Tasks

  title={FedCV: A Federated Learning Framework for Diverse Computer Vision Tasks},
  author={Chaoyang He and Alay Shah and Zhenheng Tang and Dian Fan and Adarshan Naiynar Sivashunmugam and Keerti Bhogaraju and Mita Shimpi and Li Shen and Xiaowen Chu and Mahdi Soltanolkotabi and Salman Avestimehr},
Federated Learning (FL) is a distributed learning paradigm that can learn a global or personalized model from decentralized datasets on edge devices. However, in the computer vision domain, model performance in FL is far behind centralized training due to the lack of exploration in diverse tasks with a unified FL framework. FL has rarely been demonstrated effectively in advanced computer vision tasks such as object detection and image segmentation. To bridge the gap and facilitate the… 

FLAIR: Federated Learning Annotated Image Repository

This work introduces FLAIR, a challenging large-scale annotated image dataset for multi-label classification suitable for federated learning and implements multiple baselines in different learning setups for different tasks on this dataset.

FedAudio: A Federated Learning Benchmark for Audio Tasks

A unique contribution of FedAudio is the introduction of data noises and label errors to the datasets to emulate challenges when deploying FL systems in real-world settings.

FLAME: Federated Learning Across Multi-device Environments

This paper proposes FLAME, a user-centered FL training approach to counter statistical and system heterogeneity in MDEs, and bring consistency in inference performance across devices.

FedFA: Federated Learning with Feature Anchors to Align Feature and Classifier for Heterogeneous Data

A simple yet effective framework named FedFA with F eature A nchors (FedFA) to align the feature mappings and calibrate classifier across clients during local training, which allows client models updating in a shared feature space with consistent classi fiers.

From distributed machine learning to federated learning: a survey

This paper proposes a functional architecture of federated learning systems and a taxonomy of related techniques and presents four widely used federated systems based on the functional architecture.

Differentially Private CutMix for Split Learning with Vision Transformer

This work proposes DP-CutMixSL, a differentially private (DP) SL framework by developing DP patch-level randomized CutMix (DP- cutMix) , a novel privacy-preserving inter-client interpolation scheme that replaces randomly selected patches in smashed data.

GossipFL: A Decentralized Federated Learning Framework With Sparsified and Adaptive Communication

This work designs a novel sparsification algorithm to enable that each client only needs to communicate with one peer with a highly sparsified model, and proposes a new and novel gossip matrix generation algorithm that can better utilize the bandwidth resources while preserving the convergence property.

Deep Neural Network Fusion via Graph Matching with Applications to Model Ensemble and Federated Learning

This work proposes an efficient graduated assignment-based model fusion method, dubbed GAMF, which iteratively updates the matchings in a consistency-maintaining manner, and applies GAMF to tackle the compact model ensemble task and federated learning task on MNIST, CIFAR-10, CifAR-100, and Tiny-Imagenet.

A Review on Machine Learning Styles in Computer Vision—Techniques and Future Directions

This paper presents literature analysis of how different machine learning styles evolved in the field of Artificial Intelligence (AI) for computer vision to help researchers working with learning styles as it gives a deep insight into future directions.

N-FedAvg: Novel Federated Average Algorithm Based on FedAvg

The N-FedAvg algorithm is proposed, which selects clients in sequence before each epoch, reducing the randomness when selecting clients, so that all clients' data can have the opportunity to participate in federated learning, and prevent local data of some clients from participating in the federation with a low probability.



FedVision: An Online Visual Object Detection Platform Powered by Federated Learning

FedVision - a machine learning engineering platform to support the development of federated learning powered computer vision applications has been deployed through a collaboration between WeBank and Extreme Vision to help customers develop computer vision-based safety monitoring solutions in smart city applications.

Federated Visual Classification with Real-World Data Distribution

Two new large-scale datasets for species and landmark classification are introduced, with realistic per-user data splits that simulate real-world edge learning scenarios, and two new algorithms are developed that intelligently resample and reweight over the client pool, bringing large improvements in accuracy and stability in training.

Federated Object Detection: Optimizing Object Detection Model with Federated Learning

Kullback-Leibler divergence(KLD) is used to measure the weights divergence between different model trained with non-IID data, and a useful scheme to improve FedAvg based Abnormal Weights Supression is proposed, reducing the influence of the weight divergence caused by non- IID and unbalanced data.

FedNAS: Federated Deep Learning via Neural Architecture Search

This work proposes a Federated NAS (FedNAS) algorithm to help scattered workers collaboratively searching for a better architecture with higher accuracy and shows that the architecture searched by FedNAS can outperform the manually predefined architecture.

FedML: A Research Library and Benchmark for Federated Machine Learning

FedML is introduced, an open research library and benchmark that facilitates the development of new federated learning algorithms and fair performance comparisons and can provide an efficient and reproducible means of developing and evaluating algorithms for the Federated learning research community.

FedGraphNN: A Federated Learning System and Benchmark for Graph Neural Networks

FedGraphNN is an open research federated learning system and the benchmark to facilitate GNN-based FL research, built on a unified formulation of federated GNNs and supports commonly used datasets, GNN models, FL algorithms, and flexible APIs.

Federated Learning with Matched Averaging

This work proposes Federated matched averaging (FedMA) algorithm designed for federated learning of modern neural network architectures e.g. convolutional neural networks (CNNs) and LSTMs and indicates that FedMA outperforms popular state-of-the-art federatedLearning algorithms on deep CNN and L STM architectures trained on real world datasets, while improving the communication efficiency.

SSFL: Tackling Label Deficiency in Federated Learning via Personalized Self-Supervision

A series of algorithms that broaden existing supervised personalization algorithms into the setting of self-supervised learning including perFedAvg, Ditto, and local fine-tuning, among others are proposed and a novel personalized federated selfsupervisedLearning algorithm, Per-SSFL, is proposed which balances personalization and consensus by carefully regulating the distance between the local and global representations of data.

Agnostic Federated Learning

This work proposes a new framework of agnostic federated learning, where the centralized model is optimized for any target distribution formed by a mixture of the client distributions, and shows that this framework naturally yields a notion of fairness.

Federated Learning with Only Positive Labels

This work proposes a generic framework for training with only positive labels, namely Federated Averaging with Spreadout (FedAwS), where the server imposes a geometric regularizer after each round to encourage classes to be spreadout in the embedding space.