Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userAccelerating Federated Learning with a Global Biased Optimiser
236
0
0.0
(
0
)
Added by
Jed Mills
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Federated Learning (FL) is a recent development in the field of machine learning that collaboratively trains models without the training data leaving client devices, to preserve data privacy. In realistic FL settings, the training set is distributed over clients in a highly non-Independent and Identically Distributed (non-IID) fashion, which has been shown extensively to harm FL convergence speed and final model performance. To address this challenge, we propose a novel, generalised approach for incorporating adaptive optimisation techniques into FL with the Federated Global Biased Optimiser (FedGBO) algorithm. FedGBO accelerates FL by employing a set of global biased optimiser values during the client-training phase, which helps to reduce `client-drift from non-IID data, whilst also benefiting from adaptive optimisation. We show that the FedGBO update with a generic optimiser can be reformulated as centralised training using biased gradients and optimiser updates, and apply this theoretical framework to prove the convergence of FedGBO using momentum-Stochastic Gradient Descent (SGDm). We also conduct extensive experiments using 4 realistic FL benchmark datasets (CIFAR100, Sent140, FEMNIST, Shakespeare) and 3 popular adaptive optimisers (RMSProp, SGDm, Adam) to compare the performance of state-of-the-art adaptive-FL algorithms. The results demonstrate that FedGBO has highly competitive performance whilst achieving lower communication and computation costs, and provide practical insights into the trade-offs associated with the different adaptive-FL algorithms and optimisers for real-world FL deployments.
rate research
Read More
Communication overhead hinders the scalability of large-scale distributed training. Gossip SGD, where each node averages only with its neighbors, is more communication-efficient than the prevalent parallel SGD. However, its convergence rate is reversely proportional to quantity $1-beta$ which measures the network connectivity. On large and sparse networks where $1-beta to 0$, Gossip SGD requires more iterations to converge, which offsets against its communication benefit. This paper introduces Gossip-PGA, which adds Periodic Global Averaging into Gossip SGD. Its transient stage, i.e., the iterations required to reach asymptotic linear speedup stage, improves from $Omega(beta^4 n^3/(1-beta)^4)$ to $Omega(beta^4 n^3 H^4)$ for non-convex problems. The influence of network topology in Gossip-PGA can be controlled by the averaging period $H$. Its transient-stage complexity is also superior to Local SGD which has order $Omega(n^3 H^4)$. Empirical results of large-scale training on image classification (ResNet50) and language modeling (BERT) validate our theoretical findings.
Personalization methods in federated learning aim to balance the benefits of federated and local training for data availability, communication cost, and robustness to client heterogeneity. Approaches that require clients to communicate all model parameters can be undesirable due to privacy and communication constraints. Other approaches require always-available or stateful clients, impractical in large-scale cross-device settings. We introduce Federated Reconstruction, the first model-agnostic framework for partially local federated learning suitable for training and inference at scale. We motivate the framework via a connection to model-agnostic meta learning, empirically demonstrate its performance over existing approaches for collaborative filtering and next word prediction, and release an open-source library for evaluating approaches in this setting. We also describe the successful deployment of this approach at scale for federated collaborative filtering in a mobile keyboard application.
Graph neural networks (GNN) have been successful in many fields, and derived various researches and applications in real industries. However, in some privacy sensitive scenarios (like finance, healthcare), training a GNN model centrally faces challenges due to the distributed data silos. Federated learning (FL) is a an emerging technique that can collaboratively train a shared model while keeping the data decentralized, which is a rational solution for distributed GNN training. We term it as federated graph learning (FGL). Although FGL has received increasing attention recently, the definition and challenges of FGL is still up in the air. In this position paper, we present a categorization to clarify it. Considering how graph data are distributed among clients, we propose four types of FGL: inter-graph FL, intra-graph FL and graph-structured FL, where intra-graph is further divided into horizontal and vertical FGL. For each type of FGL, we make a detailed discussion about the formulation and applications, and propose some potential challenges.
The popular federated edge learning (FEEL) framework allows privacy-preserving collaborative model training via frequent learning-updates exchange between edge devices and server. Due to the constrained bandwidth, only a subset of devices can upload their updates at each communication round. This has led to an active research area in FEEL studying the optimal device scheduling policy for minimizing communication time. However, owing to the difficulty in quantifying the exact communication time, prior work in this area can only tackle the problem partially by considering either the communication rounds or per-round latency, while the total communication time is determined by both metrics. To close this gap, we make the first attempt in this paper to formulate and solve the communication time minimization problem. We first derive a tight bound to approximate the communication time through cross-disciplinary effort involving both learning theory for convergence analysis and communication theory for per-round latency analysis. Building on the analytical result, an optimized probabilistic scheduling policy is derived in closed-form by solving the approximate communication time minimization problem. It is found that the optimized policy gradually turns its priority from suppressing the remaining communication rounds to reducing per-round latency as the training process evolves. The effectiveness of the proposed scheme is demonstrated via a use case on collaborative 3D objective detection in autonomous driving.
Federated Learning (FL) has shown great potential as a privacy-preserving solution to learning from decentralized data that are only accessible to end devices (i.e., clients). In many scenarios however, a large proportion of the clients are probably in possession of low-quality data that are biased, noisy or even irrelevant. As a result, they could significantly slow down the convergence of the global model we aim to build and also compromise its quality. In light of this, we propose FedProf, a novel algorithm for optimizing FL under such circumstances without breaching data privacy. The key of our approach is a data representation profiling and matching scheme that uses the global model to dynamically profile data representations and allows for low-cost, lightweight representation matching. Based on the scheme we adaptively score each client and adjust its participation probability so as to mitigate the impact of low-value clients on the training process. We have conducted extensive experiments on public datasets using various FL settings. The results show that FedProf effectively reduces the number of communication rounds and overall time (up to 4.5x speedup) for the global model to converge and provides accuracy gain.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
