Publications related to Social network

Quasi-Global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data

Martin Jaggi, Sebastian Urban Stich, Tao Lin, Sai Praneeth Reddy Karimireddy

Decentralized training of deep learning models is a key element for enabling data privacy and on-device learning over networks. In realistic learning scenarios, the presence of heterogeneity across different clients' local datasets poses an optimization ch ...

JMLR-JOURNAL MACHINE LEARNING RESEARCH2021

Facilitators First: Building a Tool With Facilitators to Foster a More Collaborative Makerspace Community Through Movement Traces

Bertrand Roland Schneider, Léonore Valentine Guillain

Research indicates that makerspaces equip students with the practical skills needed to build their own projects and thrive in the twenty-first-century workforce. While the appeal of makerspaces lies in their spirit of tinkering and community-driven ethos, ...

ASSOC COMPUTING MACHINERY2021

The Metabolic Regimes at the Scale of an Entire Stream Network Unveiled Through Sensor Data and Machine Learning

Tom Ian Battin, Enrico Bertuzzo, Pier Luigi Segatto

Streams and rivers form dense networks that drain the terrestrial landscape and are relevant for biodiversity dynamics, ecosystem functioning, and transport and transformation of carbon. Yet, resolving in both space and time gross primary production (GPP), ...

2021

Social Learning Under Inferential Attacks

Ali H. Sayed, Stefan Vlaski, Virginia Bordignon, Konstantinos Ntemos

A common assumption in the social learning literature is that agents exchange information in an unselfish manner. In this work, we consider the scenario where a subset of agents aims at driving the network beliefs to the wrong hypothesis. The adversaries a ...

IEEE2021

Is planning still political? The politicization of high-speed rail in Spain (1986–2016)

Ander Audikana Arriola

Post-political debate has stimulated a vigorous research agenda about the role of politics in regional and urban planning. It warns of a depoliticization process leading to the emergence of a consensual social order and the retreat of the properly politica ...

2021

The structural connectome and motor recovery after stroke: predicting natural recovery

Jean-Philippe Thiran, Friedhelm Christoph Hummel, Gabriel Girard, Takuya Morishita, Elena Beanato, Maximilian Jonas Wessel, Chang-Hyun Park, Philipp Johannes Koch, Philip Egger, Giorgia Giulia Evangelista

Stroke patients vary considerably in terms of outcomes: some patients present ‘natural’ recovery proportional to their initial impairment (fitters), while others do not (non-fitters). Thus, a key challenge in stroke rehabilitation is to identify individual ...

2021

Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances

Wulfram Gerstner, Clément Hongler, Johanni Michael Brea, Francesco Spadaro, Berfin Simsek, Arthur Jacot

We study how permutation symmetries in overparameterized multi-layer neural networks generate `symmetry-induced' critical points. Assuming a network with

L

layers of minimal widths

r_1^*, \ldots, r_{L-1}^*

reaches a zero-loss minimum at $ r_1^*! \c ...

2021

Turning crowds into communities: The collectives of online citizen science

Jérôme Baudry

Over the past two decades, a number of digital platforms have been developed with the aim of engaging citizens in scientific research projects. The success of these platforms depends in no small part on their ability to attract and retain participants, tur ...

2021

The physics of higher-order interactions in complex systems

Enrico Amico, Benedetta Franceschiello

Network representations of complex systems are limited to pairwise interactions, but real-world systems often involve higher-order interactions. This Perspective looks at the new physics emerging from attempts to characterize these interactions. Complex ne ...

NATURE PORTFOLIO2021

Characterization and prediction of clinical pathways of vulnerability to psychosis through graph signal processing

Dimitri Nestor Alice Van De Ville, Maude Schneider, Daniela Maria Zöller, Anjali Bagunu Tarun

Causal interactions between specific psychiatric symptoms could contribute to the heterogenous clinical trajectories observed in early psychopathology. Current diagnostic approaches merge clinical manifestations that co-occur across subjects and could sign ...

eLIFE SCIENCES PUBL LTD2021

Social network

Graph Chatbot

Chat with Graph Search

Quasi-Global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data

Facilitators First: Building a Tool With Facilitators to Foster a More Collaborative Makerspace Community Through Movement Traces

The Metabolic Regimes at the Scale of an Entire Stream Network Unveiled Through Sensor Data and Machine Learning

Social Learning Under Inferential Attacks

Is planning still political? The politicization of high-speed rail in Spain (1986–2016)

The structural connectome and motor recovery after stroke: predicting natural recovery

Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances

Turning crowds into communities: The collectives of online citizen science

The physics of higher-order interactions in complex systems

Characterization and prediction of clinical pathways of vulnerability to psychosis through graph signal processing

Facilitators First: Building a Tool With Facilitators to Foster a More Collaborative Makerspace Community Through Movement Traces

Quasi-Global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data

The Metabolic Regimes at the Scale of an Entire Stream Network Unveiled Through Sensor Data and Machine Learning

Is planning still political? The politicization of high-speed rail in Spain (1986–2016)

Social Learning Under Inferential Attacks

Characterization and prediction of clinical pathways of vulnerability to psychosis through graph signal processing

Turning crowds into communities: The collectives of online citizen science

The structural connectome and motor recovery after stroke: predicting natural recovery

Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances

The physics of higher-order interactions in complex systems