Related papers: Federated Sinkhorn
Consider the setting where each vertex of a graph has a function, and communications can only occur between vertices connected by an edge. We wish to minimize the sum of these functions. For the case when each function is the sum of a…
Federated learning has been spotlighted as a way to train neural networks using distributed data with no need for individual nodes to share data. Unfortunately, it has also been shown that adversaries may be able to extract local data…
Graph Neural Networks (GNNs) are the first choice methods for graph machine learning problems thanks to their ability to learn state-of-the-art level representations from graph-structured data. However, centralizing a massive amount of…
Graph foundation models have demonstrated remarkable adaptability across diverse downstream tasks through large-scale pretraining on graphs. However, existing implementations of the backbone model, graph transformers, are typically limited…
Quantum teleportation is a primitive foundational protocol for exchanging quantum information in a quantum network as well as infrastructural operational strategy in the measurement-based quantum computation. Designing an efficient scheme…
Quantum communication implementations require efficient and reliable quantum channels. Optical fibers have proven to be an ideal candidate for distributing quantum states. Thus, today's efforts address overcoming issues towards high data…
We study asynchronous federated learning mechanisms with nodes having potentially different computational speeds. In such an environment, each node is allowed to work on models with potential delays and contribute to updates to the central…
We consider a distributed computing system in which a master node coordinates $N$ workers to evaluate a function over $n$ input files, where this function accepts general decomposition. In particular, we focus on the general case where the…
We introduce a new and increasingly relevant setting for distributed optimization in machine learning, where the data defining the optimization are distributed (unevenly) over an extremely large number of \nodes, but the goal remains to…
We consider practical data characteristics underlying federated learning, where unbalanced and non-i.i.d. data from clients have a block-cyclic structure: each cycle contains several blocks, and each client's training data follow…
We present a quantum repeater protocol for distributing entanglement over long distances, where a dedicated communication stage enables trial rates not limited by the travel time between repeater nodes. To accomplish this, each node…
Federated learning allows distributed devices to collectively train a model without sharing or disclosing the local dataset with a central server. The global model is optimized by training and averaging the model parameters of all local…
Entropy regularized optimal transport and its multi-marginal generalization have attracted increasing attention in various applications, in particular due to efficient Sinkhorn-like algorithms for computing optimal transport plans. However,…
Synchronous federated learning scales poorly due to the straggler effect. Asynchronous algorithms increase the update throughput by processing updates upon arrival, but they introduce two fundamental challenges: gradient staleness, which…
Federated learning has attracted significant attention as a privacy-preserving framework for training personalised models on multi-source heterogeneous data. However, most existing approaches are unable to handle scenarios where subgroup…
We propose and analyze a modified damped Newton algorithm to solve the semi-discrete optimal transport with storage fees. We prove global linear convergence for a wide range of storage fee functions, the main assumption being that each…
It is well understood that client-master communication can be a primary bottleneck in Federated Learning. In this work, we address this issue with a novel client subsampling scheme, where we restrict the number of clients allowed to…
As a promising solution to achieve efficient learning among isolated data owners and solve data privacy issues, federated learning is receiving wide attention. Using the edge server as an intermediary can effectively collect sensor data,…
Large-scale neuromorphic architectures consist of computing tiles that communicate spikes using a shared interconnect. The communication patterns in such systems are inherently sparse, asynchronous, and localized due to the spiking nature…
In part I of this paper, a distributed and a centralized architecture for an optimal radio resource allocation aware of the traffic delay-tolerance nature, user subscription type, and application usage variations were developed. In the…