Consensus Control for Decentralized Deep Learning

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Over the past years, image generation and manipulation have achieved remarkable progress due to the rapid development of generative AI based on deep learning. Recent studies have devoted significant efforts to address the problem of face image manipulation ...

This paper proposes a novel approach to improve the performance of distributed nonlinear control systems while preserving stability by leveraging Deep Neural Networks (DNNs). We build upon the Neural System Level Synthesis (Neur-SLS) framework and introduc ...

The convergence speed of machine learning models trained with Federated Learning is significantly affected by non-independent and identically distributed (non-IID) data partitions, even more so in a fully decentralized setting without a central server. In ...

Generative artificial intelligence (AI) has made unprecedented advances in vision language models over the past two years. These advances are largely due to diffusion-based generative models, which are very stable and simple to train. These diffusion model ...

Machine learning is currently shifting from a centralized paradigm to decentralized ones where machine learning models are trained collaboratively. In fully decentralized learning algorithms, data remains where it was produced, models are trained locally a ...

Signalized intersections are a fundamental part of urban networks. Their understanding is crucial to identify congestion patterns, queues, delays, and safety issues in local and network level. In this work, we analyze multimodal vehicle trajectories and pr ...

Decentralized storage networks offer services with intriguing possibilities to reduce inequalities in an extremely centralized market. Fair distribution of rewards, however, is still a persistent problem in the current generation of decentralized applicati ...

Marmoset monkeys encode vital information in their calls and serve as a surrogate model for neuro-biologists to understand the evolutionary origins of human vocal communication. Traditionally analyzed with signal processing-based features, recent approache ...

In the domains of machine learning, data science and signal processing, graph or network data, is becoming increasingly popular. It represents a large portion of the data in computer, transportation systems, energy networks, social, biological, and other s ...

State-of-the-art (SOTA) face recognition systems generally use deep convolutional neural networks (CNNs) to extract deep features, called embeddings, from face images. The face embeddings are stored in the system's database and are used for recognition of ...

For our fifth anniversary, we reconnected with authors of recent Comments and Perspectives in Nature Machine Intelligence and asked them how the topic they wrote about developed. We also wanted to know what other topics in AI they found exciting, surprisin ...

Monitoring surface cracks in infrastructure is crucial for structural health monitoring. Automatic visual inspection offers an effective solution, especially in hard-to-reach areas. Machine learning approaches have proven their effectiveness but typically ...

As distribution shifts are inescapable in realistic clinical scenarios due to inconsistencies in imaging protocols, scanner vendors, and across different centers, well-trained deep models incur a domain generalization problem in unseen environments. Despit ...

Machine learning models have been shown to leak sensitive information about their training datasets. Models are increasingly deployed on devices, raising concerns that white-box access to the model parameters increases the attack surface compared to black- ...

Supplementary datasets accompanying the manuscript "ARBRE: Computational resource to predict pathways towards industrially important aromatic compounds" published in the Metabolic Engineering Journal (https://doi.org/10.1016/j.ymben.2022.03.013). In line w ...

Consensus Control for Decentralized Deep Learning

Chat with Graph Search

Towards the Detection of AI-Synthesized Human Face Images

Optimal distributed control with stability guarantees by training a network of neural closed-loop maps

D-Cliques: Compensating for Data Heterogeneity with Topology in Decentralized Federated Learning

MCMC: Bridging Rendering, Optimization and Generative AI

Frugal Decentralized Learning

An automatized signal timing detection at signalized intersections with detailed vehicle trajectory data

Altruism, reciprocity, and tokens to reward forwarding data: Is that fair?

On the Utility of Speech and Audio Foundation Models for Marmoset Call Analysis

Quantization for Distributed Processing and Learning of Structured Data

Face Reconstruction Fromdeep Facial Embeddings Using A Convolutional Neural Network

Anniversary AI reflections

From classification to segmentation with explainable AI: A study on crack detection and growth monitoring

OptTTA: Learnable Test-Time Augmentation for Source-Free Medical Image Segmentation Under Domain Shift

Investigating the Effect of Misalignment on Membership Privacy in the White-box Setting

Supplementary datasets for "ARBRE: Computational resource to predict pathways towards industrially important aromatic compounds"