Communication efficiency is crucial for federated learning (FL). Conducting local training steps in clients to reduce the communication frequency between clients and the server is a common method to address this issue. However, it leads to the client drift problem due to non-i.i.d. data distributions in different clients which severely deteriorates the performance. In this work, we propose a new method to improve the training performance in cross-silo FL via maintaining double momentum buffers. One momentum buffer tracks the server model updating direction, and the other tracks the local model updating direction. Moreover, we introduce a novel momentum fusion technique to coordinate the server and local momentum buffers. We also provide the first theoretical convergence analysis involving both the server and local standard momentum SGD. Extensive deep FL experimental results show a better training performance than FedAvg and existing standard momentum SGD variants.

Cross-silo federated learning (FL) has attracted much attention in medical imaging analysis with deep learning in recent years as it can resolve the critical issues of insufficient data, data privacy, and training efficiency. However, there can be a generalization gap between the model trained from FL and the one from centralized training. This important issue comes from the non-iid data distribution of the local data in the participating clients and is well-known as client drift. In this work, we propose a novel training frame-work FedSM to avoid the client drift issue and successfully close the generalization gap compared with the centralized training for medical image segmentation tasks for the first time. We also propose a novel personalized FL objective formulation and a new method SoftPull to solve it in our proposed framework FedSM. We conduct rigorous theoretical analysis to guarantee its convergence for optimizing the non-convex smooth objective function. Real-world medical image segmentation experiments using deep FL validate the motivations and effectiveness of our proposed method.

The communication bottleneck has been a critical problem in large-scale distributed deep learning. In this work, we study distributed SGD with random block-wise sparsification as the gradient compressor, which is ring-allreduce compatible and highly computation-efficient but leads to inferior performance. To tackle this important issue, we improve the communication-efficient distributed SGD from a novel aspect, that is, the trade-off between the variance and second moment of the gradient. With this motivation, we propose a new detached error feedback (DEF) algorithm, which shows better convergence bound than error feedback for non-convex problems. We also propose DEF-A to accelerate the generalization of DEF at the early stages of the training, which shows better generalization bounds than DEF. Furthermore, we establish the connection between communication-efficient distributed SGD and SGD with iterate averaging (SGD-IA) for the first time. Extensive deep learning experiments show significant empirical improvement of the proposed methods under various settings. Our reproducible codes and scripts for all experiments in this work will be made publicly available.

The privacy-preserving federated learning for vertically partitioned (VP) data has shown promising results as the solution of the emerging multiparty joint modeling application, in which the data holders (such as government branches, private finance, and e-business companies) collaborate throughout the learning process rather than relying on a trusted third party to hold data. However, most of the existing federated learning algorithms for VP data are limited to synchronous computation. To improve the efficiency when the unbalanced computation/communication resources are common among the parties in the federated learning system, it is essential to develop asynchronous training algorithms for VP data while keeping the data privacy. In this article, we propose an asynchronous federated stochastic gradient descent (AFSGD-VP) algorithm and its two variance reduction variants, including stochastic variance reduced gradient (SVRG) and SAGA on the VP data. Moreover, we provide the convergence analyses of AFSGD-VP and its SVRG and SAGA variants under the condition of strong convexity and without any restrictions of staleness. We also discuss their model privacy, data privacy, computational complexities, and communication costs. To the best of our knowledge, AFSGD-VP and its SVRG and SAGA variants are the first asynchronous federated learning algorithms for VP data with theoretical guarantees. Extensive experimental results on a variety of VP datasets not only verify the theoretical results of AFSGD-VP and its SVRG and SAGA variants but also show that our algorithms have much higher efficiency than the corresponding synchronous algorithms.

Federated Learning (FL) has attracted increasing attention in recent years. A leading training algorithm in FL is local SGD, which updates the model parameter on each worker and averages model parameters across different workers only once in a while. Although it has fewer communication rounds than the classical parallel SGD, local SGD still has large communication overhead in each communication round for large machine learning models, such as deep neural networks. To address this issue, we propose a new communication-efficient distributed SGD method, which can significantly reduce the communication cost by the error-compensated double compression mechanism. Under the non-convex setting, our theoretical results show that our approach has better communication complexity than existing methods and enjoys the same linear speedup regarding the number of workers as the full-precision local SGD. Moreover, we propose a communication-efficient distributed SGD with momentum, which also has better communication complexity than existing methods and enjoys a linear speedup with respect to the number of workers. At last, extensive experiments are conducted to verify the performance of our proposed two methods. Moreover, we propose a communication-efficient distributed SGD with momentum to accelerate the convergence, which also has better communication complexity than existing methods and enjoys a linear speedup with respect to the number of workers. At last, extensive experiments are conducted to verify the performance of our proposed methods.

Although the distributed machine learning methods can speed up the training of large deep neural networks, the communication cost has become the non-negligible bottleneck to constrain the performance. To address this challenge, the gradient compression based communication-efficient distributed learning methods were designed to reduce the communication cost, and more recently the local error feedback was incorporated to compensate for the corresponding performance loss. However, in this paper, we will show that a new "gradient mismatch" problem is raised by the local error feedback in centralized distributed training and can lead to degraded performance compared with full-precision training. To solve this critical problem, we propose two novel techniques, 1) step ahead and 2) error averaging, with rigorous theoretical analysis. Both our theoretical and empirical results show that our new methods can handle the "gradient mismatch" problem. The experimental results show that we can even train faster with common gradient compression schemes than both the full-precision training and local error feedback regarding the training epochs and without performance loss.

Training the deep convolutional neural network for computer vision problems is slow and inefficient, especially when it is large and distributed across multiple devices. The inefficiency is caused by the backpropagation algorithm's forward locking, backward locking, and update locking problems. Existing solutions for acceleration either can only handle one locking problem or lead to severe accuracy loss or memory inefficiency. Moreover, none of them consider the straggler problem among devices. In this paper, we propose Layer-wise Staleness and a novel efficient training algorithm, Diversely Stale Parameters (DSP), to address these challenges. We also analyze the convergence of DSP with two popular gradient-based methods and prove that both of them are guaranteed to converge to critical points for non-convex problems. Finally, extensive experimental results on training deep learning models demonstrate that our proposed DSP algorithm can achieve significant training speedup with stronger robustness than compared methods.

Making an optimal decision to avoid obstacles while heading to the goal is one of the fundamental challenges for mobile robots equipped with limited computational resources. In this paper, we present a deep imitation learning algorithm that develops a computationally efficient obstacle avoidance policy based on egocentric local occupancy maps. The trained model embedded with a variant of the value iteration networks is able to provide near-optimal continuous action commands through fast feed-forward inferences and generalize well to unseen planning-based scenarios. To improve the policy robustness, we augment the training data set with artificially generated maps, which effectively alleviates the shortage of catastrophic samples in normal demonstrations. Extensive experiments on a Segway robot show the effectiveness of the proposed approach in terms of solution optimality, robustness as well as computation time.

As an effective solution to the approximate nearest neighbors (ANN) search problem, learning to hash (L2H) is able to learn similarity-preserving hash functions tailored for a given dataset. However, existing L2H research mainly focuses on improving query performance by learning good hash functions, while Hamming ranking (HR) is used as the default querying method. We show by analysis and experiments that Hamming distance, the similarity indicator used in HR, is too coarse-grained and thus limits the performance of query processing. We propose a new fine-grained similarity indicator, quantization distance (QD), which provides more information about the similarity between a query and the items in a bucket. We then develop two efficient querying methods based on QD, which achieve significantly better query performance than HR. Our methods are general and can work with various L2H algorithms. Our experiments demonstrate that a simple and elegant querying method can produce performance gain equivalent to advanced and complicated learning algorithms.