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.

In this work, we carry out the first, in-depth, privacy analysis of Decentralized Learning-a collaborative machine learning framework aimed at addressing the main limitations of federated learning. We introduce a suite of novel attacks for both passive and ...

Artificial Neural Networks (ANN) are habitually trained via the back-propagation (BP) algorithm. This approach has been extremely successful: Current models like GPT-3 have O(10 11 ) parameters, are trained on O(10 11 ) words and produce awe-inspiring resu ...

Machine learning models (e.g., neural networks) achieve high accuracy in wind power forecasting, but they are usually regarded as black boxes that lack interpretability. To address this issue, the paper proposes a glass-box model that combines high accurac ...

When arranged in a crossbar configuration, resistive memory devices can be used to execute Matrix-Vector Multiplications (MVMs), the most dominant operation of many Machine Learning (ML) algorithms, in constant time complexity. Nonetheless, when performing ...

Decentralized learning (DL) has gained prominence for its potential benefits in terms of scalability, privacy, and fault tolerance. It consists of many nodes that coordinate without a central server and exchange millions of parameters in the inherently ite ...

Decentralized learning (DL) is an emerging approach that enables nodes to collaboratively train a machine learning model without sharing raw data. In many application domains, such as healthcare, this approach faces challenges due to the high level of hete ...

The recent advance of large language models (LLMs) demonstrates that these large-scale foundation models achieve remarkable capabilities across a wide range of language tasks and domains. The success of the statistical learning approach challenges our unde ...

Deep learning has shown remarkable potential for industrial applications, particularly in predictive maintenance and condition monitoring. A key challenge in this domain is prognostics, specifically predicting the Remaining Useful Life (RUL) of assets - a ...

Natural language processing and other artificial intelligence fields have witnessed impressive progress over the past decade. Although some of this progress is due to algorithmic advances in deep learning, the majority has arguably been enabled by scaling ...

Current machine learning models for vision are often highly specialized and limited to a single modality and task. In contrast, recent large language models exhibit a wide range of capabilities, hinting at a possibility for similarly versatile models in co ...

We introduce BLAP, a model capable of generating high-quality captions for music. BLAP leverages a fine-tuned CLAP audio encoder and a pre-trained Flan-T5 large language model. To achieve effective cross-modal alignment between music and language, BLAP uti ...

Most recent test-time adaptation methods focus on only classification tasks, use specialized network architectures, destroy model calibration or rely on lightweight information from the source domain. To tackle these issues, this paper proposes a novel Tes ...

In control system networks, reconfiguration of the controller when agents are leaving or joining the network is still an open challenge, in particular when operation constraints that depend on each agent's behavior must be met. Drawing our motivation from ...

Foundation models have become a powerful tool in single-cell transcriptomics, enabling broad generalization across tasks such as cell type annotation, data integration, and drug response prediction. Yet, most current models are trained predominantly on hea ...

We are used to defining network neutrality as absence of traffic differentiation, like policing or shaping. These mechanisms, however, are often not what determines end-users’ quality of experience (QoE). Most content today is accessed through edge caches, ...

This work investigates the benefits of a two-layer adaptive signal control framework combining multi-region perimeter control (PC) with distributed Max Pressure (MP) control in selected network intersections. Motivated by MP’s questionable performance in o ...

Decentralized signal control of congested traffic networks based on the Max-Pressure (MP) controller is theoretically proven to maximize throughput, stabilize the system and balance queues for single intersections under specific conditions. However, its pe ...

Machine learning has transformed many fields and has recently found applications in chemistry and materials science. The small datasets commonly found in chemistry sparked the development of sophisticated machine learning approaches that incorporate chemic ...

Recent developments in network neuroscience have highlighted the importance of developing techniques for analysing and modelling brain networks. A particularly powerful approach for studying complex neural systems is to formulate generative models that use ...

Human voluntary movement stems from the coordinated activations in space and time of many musculoskeletal segments. However, the current methodological approaches to study human movement are still limited to the evaluation of the synergies among a few body ...

Consensus Control for Decentralized Deep Learning

Chat with Graph Search

On the (In)security of Peer-to-Peer Decentralized Machine Learning

Artificial Neural Network Training on an Optical Processor via Direct Feedback Alignment

Explainable modeling for wind power forecasting: A Glass-Box model with high accuracy

LIONHEART: A Layer-based Mapping Framework for Heterogeneous Systems with Analog In-Memory Computing Tiles

Decentralized learning made easy with DecentralizePy

Fair Decentralized Learning

Monotonicity Reasoning in the Age of Neural Foundation Models

Overcoming Distribution Shifts and Imbalance Challenges in Representation Learning for Deep Regression Models

Text Representation Learning for Low Cost Natural Language Understanding

4M: Massively Multimodal Masked Modeling

Bootstrapping Language-Audio Pre-training for Music Captioning

TeSLA: Test-Time Self-Learning With Automatic Adversarial Augmentation

Model Predictive Control for Multi-Agent Systems under Limited Communication and Time-Varying Network Topology

Abstract IA02: Cancer-specific foundation models: Friend or foe in healthcare AI?

Caching and Neutrality

Two-layer adaptive signal control framework for large-scale networks combining efficient Max-Pressure and Perimeter Control

Critical node selection method for efficient Max-Pressure traffic signal control in large-scale congested networks

Leveraging large language models for predictive chemistry

Investigating cognitive ability using action-based models of structural brain networks

The kinectome: A comprehensive kinematic map of human motion in health and disease