相关论文: Dynamic Topology Optimization for Non-IID Data in …

Decentralized Federated Learning has emerged as an alternative to centralized architectures due to its faster training, privacy preservation, and reduced communication overhead. In decentralized communication, the server aggregation phase…

From learning assistance to companionship, social robots promise to enhance many aspects of daily life. However, social robots have not seen widespread adoption, in part because (1) they do not adapt their behavior to new users, and (2)…

Most decentralized optimization algorithms are handcrafted. While endowed with strong theoretical guarantees, these algorithms generally target a broad class of problems, thereby not being adaptive or customized to specific problem…

Deep learning (DL) has been increasingly applied in medical imaging, however, it requires large amounts of data, which raises many challenges related to data privacy, storage, and transfer. Federated learning (FL) is a training paradigm…

Decentralized deep learning requires dealing with non-iid data across clients, which may also change over time due to temporal shifts. While non-iid data has been extensively studied in distributed settings, temporal shifts have received no…

The convergence speed of machine learning models trained with Federated Learning is significantly affected by heterogeneous data partitions, even more so in a fully decentralized setting without a central server. In this paper, we show that…

Federated learning (FL) emerges as a promising approach to empower vehicular networks, composed by intelligent connected vehicles equipped with advanced sensing, computing, and communication capabilities. While previous studies have…

Federated learning (FL) faces critical challenges, particularly in heterogeneous environments where non-independent and identically distributed data across clients can lead to unfair and inefficient model performance. In this work, we…

The principal benefit of unsupervised representation learning is that a pre-trained model can be fine-tuned where data or labels are scarce. Existing approaches for graph representation learning are domain specific, maintaining consistent…

Decentralized SGD can run with low communication costs, but its sparse communication characteristics deteriorate the convergence rate, especially when the number of nodes is large. In decentralized learning settings, communication is…

We present HyperMorph, a learning-based strategy for deformable image registration that removes the need to tune important registration hyperparameters during training. Classical registration methods solve an optimization problem to find a…

Decentralized optimization has emerged as a critical paradigm for distributed learning, enabling scalable training while preserving data privacy through peer-to-peer collaboration. However, existing methods often suffer from communication…

In traditional topology optimization, the computing time required to iteratively update the material distribution within a design domain strongly depends on the complexity or size of the problem, limiting its application in real engineering…

We design a low complexity decentralized learning algorithm to train a recently proposed large neural network in distributed processing nodes (workers). We assume the communication network between the workers is synchronized and can be…

As the complexity of our neural network models grow, so too do the data and computation requirements for successful training. One proposed solution to this problem is training on a distributed network of computational devices, thus…

In decentralized optimization, several nodes connected by a network collaboratively minimize some objective function. For minimization of Lipschitz functions lower bounds are known along with optimal algorithms. We study a specific class of…

We consider the problem of decentralized optimization in networks with communication delays. To accommodate delays, we need decentralized optimization algorithms that work on directed graphs. Existing approaches require nodes to know their…

Edge robotics involves frequent exchanges of large-volume multi-modal data. Existing methods ignore the interdependency between robotic functionalities and communication conditions, leading to excessive communication overhead. This paper…

We propose an efficient framework that integrates distance-aware multi-hop message passing with dynamic topology refinement. Unlike standard GNNs that rely on shallow, fixed-hop aggregation, DRTR leverages both static preprocessing and…

While traditional Deep Learning (DL) optimization methods treat all training samples equally, Distributionally Robust Optimization (DRO) adaptively assigns importance weights to different samples. However, a significant gap exists between…