Related papers: Basis Matters: Better Communication-Efficient Seco…
Federated learning (FL) is a popular machine learning technique that enables multiple users to collaboratively train a model while maintaining the user data privacy. A significant challenge in FL is the communication bottleneck in the…
Communication compression is a common technique in distributed optimization that can alleviate communication overhead by transmitting compressed gradients and model parameters. However, compression can introduce information distortion,…
Quantization is a common approach to mitigate the communication cost of federated learning (FL). In practice, the quantized local parameters are further encoded via an entropy coding technique, such as Huffman coding, for efficient data…
Federated learning (FL) is a distributed machine learning approach that enables multiple local clients and a central server to collaboratively train a model while keeping the data on their own devices. First-order methods, particularly…
In this paper, a new communication-efficient federated learning (FL) framework is proposed, inspired by vector quantized compressed sensing. The basic strategy of the proposed framework is to compress the local model update at each device…
This paper investigates the feasibility of federated representation learning under the constraints of communication cost and privacy protection. Existing works either conduct annotation-guided local training which requires frequent…
Although Federated Learning has been widely studied in recent years, there are still high overhead expenses in each communication round for large-scale models such as Vision Transformer. To lower the communication complexity, we propose a…
Optimization plays a key role in machine learning. Recently, stochastic second-order methods have attracted much attention due to their low computational cost in each iteration. However, these algorithms might perform poorly especially if…
In distributed optimization and learning, several machines alternate between local computations in parallel and communication with a distant server. Communication is usually slow and costly and forms the main bottleneck. This is…
Batch normalization (BN) is a popular and ubiquitous method in deep learning that has been shown to decrease training time and improve generalization performance of neural networks. Despite its success, BN is not theoretically well…
Semantic communication has emerged as a pillar for the next generation of communication systems due to its capabilities in alleviating data redundancy. Most semantic communication systems are built upon advanced deep learning models whose…
To address the communication bottleneck problem in distributed optimization within a master-worker framework, we propose LocalNewton, a distributed second-order algorithm with local averaging. In LocalNewton, the worker machines update…
We propose basic and natural assumptions under which iterative optimization methods with compressed iterates can be analyzed. This problem is motivated by the practice of federated learning, where a large model stored in the cloud is…
Federated learning is a distributed machine learning approach in which clients train models locally with their own data and upload them to a server so that their trained results are shared between them without uploading raw data to the…
Communication efficiency is a widely recognised research problem in Federated Learning (FL), with recent work focused on developing techniques for efficient compression, distribution and aggregation of model parameters between clients and…
Federated Learning (FL) has been widely concerned for it enables decentralized learning while ensuring data privacy. However, most existing methods unrealistically assume that the classes encountered by local clients are fixed over time.…
Modern deep learning models are often trained in parallel over a collection of distributed machines to reduce training time. In such settings, communication of model updates among machines becomes a significant performance bottleneck and…
We consider federated learning (FL), where the training data is distributed across a large number of clients. The standard optimization method in this setting is Federated Averaging (FedAvg), which performs multiple local first-order…
We propose a communication efficient quasi-Newton method for large-scale multi-agent convex composite optimization. We assume the setting of a network of agents that cooperatively solve a global minimization problem with strongly convex…
Lossy gradient compression, with either unbiased or biased compressors, has become a key tool to avoid the communication bottleneck in centrally coordinated distributed training of machine learning models. We analyze the performance of two…