Related papers: ACE-Sync: An Adaptive Cloud-Edge Synchronization F…
We present EDGE, a general-purpose, misconception-aware adaptive learning framework composed of four stages: Evaluate (ability and state estimation), Diagnose (posterior infer-ence of misconceptions), Generate (counterfactual item…
Federated learning (FL) is one of the popular distributed machine learning (ML) solutions but incurs significant communication and computation costs at edge devices. Federated split learning (FSL) can train sub-models in parallel and reduce…
Distributed learning algorithms, such as the ones employed in Federated Learning (FL), require communication compression to reduce the cost of client uploads. The compression methods used in practice are often biased, making error feedback…
To reduce the long training time of large deep neural network (DNN) models, distributed synchronous stochastic gradient descent (S-SGD) is commonly used on a cluster of workers. However, the speedup brought by multiple workers is limited by…
Stochastic Gradient Descent (SGD) is the key learning algorithm for many machine learning tasks. Because of its computational costs, there is a growing interest in accelerating SGD on HPC resources like GPU clusters. However, the…
With recent research advances, deep learning models have become an attractive choice for acoustic echo cancellation (AEC) in real-time teleconferencing applications. Since acoustic echo is one of the major sources of poor audio quality, a…
Network consensus optimization has received increasing attention in recent years and has found important applications in many scientific and engineering fields. To solve network consensus optimization problems, one of the most well-known…
Coding images for machines with minimal bitrate and strong analysis performance is key to effective edge-cloud systems. Several approaches deploy an image codec and perform analysis on the reconstructed image. Other methods compress…
The emerging field semantic communication is driving the research of end-to-end data transmission. By utilizing the powerful representation ability of deep learning models, learned data transmission schemes have exhibited superior…
Split learning is a promising privacy-preserving distributed learning scheme that has low computation requirement at the edge device but has the disadvantage of high communication overhead between edge device and server. To reduce the…
Optimizing distributed learning systems is an art of balancing between computation and communication. There have been two lines of research that try to deal with slower networks: {\em communication compression} for low bandwidth networks,…
Federated learning effectively addresses issues such as data privacy by collaborating across participating devices to train global models. However, factors such as network topology and device computing power can affect its training or…
Edge intelligence enables AI inference at the network edge, co-located with or near the radio access network, rather than in centralized clouds or on mobile devices. It targets low-latency, resource-constrained applications with large data…
Communication overhead is the key challenge for distributed training. Gradient compression is a widely used approach to reduce communication traffic. When combining with parallel communication mechanism method like pipeline, gradient…
Dataset Condensation aims to condense a large dataset into a smaller one while maintaining its ability to train a well-performing model, thus reducing the storage cost and training effort in deep learning applications. However, conventional…
In this paper, we consider solving the distributed optimization problem over a multi-agent network under the communication restricted setting. We study a compressed decentralized stochastic gradient method, termed ``compressed exact…
Combining gradient compression methods (e.g., CountSketch, quantization) and adaptive optimizers (e.g., Adam, AMSGrad) is a desirable goal in federated learning (FL), with potential benefits on both fewer communication rounds and less…
Federated learning obtains a central model on the server by aggregating models trained locally on clients. As a result, federated learning does not require clients to upload their data to the server, thereby preserving the data privacy of…
Medical images acquired from standardized protocols show consistent macroscopic or microscopic anatomical structures, and these structures consist of composable/decomposable organs and tissues, but existing self-supervised learning (SSL)…
The ubiquitous use of IoT and machine learning applications is creating large amounts of data that require accurate and real-time processing. Although edge-based smart data processing can be enabled by deploying pretrained models, the…