Federated Visual Classification with Real-World Data Distribution

By Tzu-Ming Harry Hsu, Hang Qi, Matthew Brown. 2020

248 citations recorded by the source corpus.

Federated Learning enables visual models to be trained on-device, bringing advantages for user privacy (data need never leave the device), but challenges in terms of data diversity and quality. Whilst typical models in the datacenter are trained using data that are independent and identically distributed (IID), data at source are typically far from IID. Furthermore, differing quantities of data are typically available at each device (imbalance). In this work, we characterize the effect these real-world data distributions have on distributed learning, using as a benchmark the standard Federated Averaging (FedAvg) algorithm. To do so, we introduce two new large-scale datasets for species and landmark classification, with realistic per-user data splits that simulate real-world edge learning scenarios. We also develop two new algorithms (FedVC, FedIR) that intelligently resample and reweight over the client pool, bringing large improvements in accuracy and stability in training. The datasets are made available online.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging, Federated & Distributed Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Radiology, Nuclear Medicine and Imaging

In Federated & Distributed Learning

Citations in the corpus

Ensemble Distillation for Robust Model Fusion in Federated Learning (2020, background): “, 2016) and its recent adaptations (Mohri et al., 2019; Li et al., 2020; Hsu et al., 2019; Karimireddy et al., 2019; Hsu et al., 2020; Reddi et al., 2020), are all based on directly averaging of the participating client’s parameters and can hence only be applied if all client’s models have the same ”
FedML: A Research Library and Benchmark for Federated Machine Learning (2020, background): “Promising application domains include, but are not limited to, computer vision [77, 78], natural language processing [79, 80, 81, 82, 83], ﬁnance [74, 35, 84], transportation [85, 86, 87, 88, 89, 90, 91, 92, 93, 94], digital health [95, 96, 97, 98, 99, 100, 101], recommendation [102, 103, 104, 105,…”
Effective Federated Adaptive Gradient Methods with Non-IID Decentralized Data (2020, unknown): “…performance of FL algorithms on visual classification tasks and show that FedAvg performs worse with increasing nonIIDness than FedMomentum, which can consistently improve the test accuracy (Hsu et al. (2019, 2020)) and theoretically converge to a first-order stationary point (Huo et al. (2020)).”
No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data (2021, methodology): “For FedAvgM, the server momentum is set to be 0.1.”
FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Space (2021, background): “Federated learning [15, 20, 36, 56] provides a promising privacy-preserving solution for multi-site data collaboration, which develops a global model from decentralized datasets by aggregating the parameters of each local client while keeping data locally.”
Federated Learning on Non-IID Data: A Survey (2021, background): “• Although two real image dataset are introduced in [91, 54], a universal homogeneous and heterogeneous benchmark dataset still lacks for FL.”
Model-Contrastive Federated Learning (2021, methodology): “Moreover, it has been applied in many applications such as medical imaging [21, 23], object detection [32], and landmark classification [15].”