English
Related papers

Related papers: Gravity Effects on Information Filtering and Netwo…

200 papers

Weight sharing, equivariance, and local filters, as in convolutional neural networks, are believed to contribute to the sample efficiency of neural networks. However, it is not clear how each one of these design choices contributes to the…

Machine Learning · Computer Science 2025-01-27 Arash Behboodi , Gabriele Cesa

A method of `network filtering' has been proposed recently to detect the effects of certain external perturbations on the interacting members in a network. However, with large networks, the goal of detection seems a priori difficult to…

Methodology · Statistics 2010-01-28 Shu Yang , Eric D. Kolaczyk

In this paper, we show how informativity and identifiability for networks of dynamical systems can be investigated using Gr\"obner bases. We provide a sufficient condition for informativity in terms of positive definiteness of the spectrum…

Systems and Control · Electrical Eng. & Systems 2026-02-27 Anders Hansson , João Victor Galvão da Mata , Martin S. Andersen

Empirical networks of weighted dyadic relations often contain noisy edges that alter the global characteristics of the network and obfuscate the most important structures therein. Graph pruning is the process of identifying the most…

Physics and Society · Physics 2016-01-20 Navid Dianati

Link weight is crucial in weighted complex networks. It provides additional dimension for describing and adjusting the properties of networks. The topological role of weight is studied by the effects of random redistribution of link weights…

Statistical Mechanics · Physics 2007-05-23 Menghui Li , Ying Fan , Dahui Wang , Na Liu , Daqing Li , Jinshan Wu , Zengru Di

We present a minimal model for the quantum evolution of matter under the influence of classical gravity in the Newtonian limit. Based on a continuous measurement-feedback channel that acts simultaneously on all constituent masses of a given…

Quantum Physics · Physics 2018-12-10 Kiran E. Khosla , Stefan Nimmrichter

Theoretical work on sequential choice and large-scale experiments in online ranking and voting systems has demonstrated that social influence can have a drastic impact on social and technological systems. Yet, the effect of social influence…

Social and Information Networks · Computer Science 2025-02-28 Marina Kontalexi , Alexandros Gelastopoulos , Pantelis P. Analytis

We proposed a gravitation theory based on an analogy with electrodynamics on the basis of a vector field. For the first time, to calculate the basic gravitational effects in the framework of a vector theory of gravity, we use a Lagrangian…

General Relativity and Quantum Cosmology · Physics 2011-04-20 V. N. Borodikhin

Strong gravitational lensing by galaxies provides us with a unique opportunity to understand the nature of gravity on galactic and extra-galactic scales. In this paper, we propose a new multimessenger approach using data from both…

Cosmology and Nongalactic Astrophysics · Physics 2020-07-08 Tao Yang , Bin Hu , Rong-Gen Cai , Bin Wang

Real data collected from different applications that have additional topological structures and connection information are amenable to be represented as a weighted graph. Considering the node labeling problem, Graph Neural Networks (GNNs)…

Social and Information Networks · Computer Science 2020-02-06 Xiaoxiao Li , Joao Saude

Graph neural networks (GNNs) have proven to be an effective tool for enhancing the performance of recommender systems. However, these systems often suffer from popularity bias, leading to an unfair advantage for frequently interacted items,…

Information Retrieval · Computer Science 2026-04-29 Nemat Gholinejad , Mostafa Haghir Chehreghani

A particle filtering approach is suggested for the training of multi-layer neural networks without utilizing gradients calculation. The network weights are considered to be the components of the estimated state-vector of a noise driven…

Optimization and Control · Mathematics 2020-10-13 Isaac Yaesh , Natan Grinfeld

With improvements in data resolution and quality, researchers can now represent complex systems as signed, weighted, and directed networks. In this article, we introduce a framework for measuring net and indirect effects without simplifying…

Physics and Society · Physics 2025-10-10 Carlos Gómez-Ambrosi , Violeta Calleja-Solanas

Large pre-trained models, or foundation models, have shown impressive performance when adapted to a variety of downstream tasks, often out-performing specialized models. Hypernetworks, neural networks that generate some or all of the…

Machine Learning · Computer Science 2025-03-04 Jeffrey Gu , Serena Yeung-Levy

Complex networks grow subject to structural constraints which affect their measurable properties. Assessing the effect that such constraints impose on their observables is thus a crucial aspect to be taken into account in their analysis. To…

Physics and Society · Physics 2014-07-31 Oleguer Sagarra , Francesc Font-Clos , Conrad J. Pérez-Vicente , Albert Díaz-Guilera

Filters of convolutional networks used in computer vision are often visualized as image patches that maximize the response of the filter. We use the same approach to interpret weight matrices in simple architectures for natural language…

Computation and Language · Computer Science 2019-07-11 Jindřich Libovický

Gravitation governs the expansion and fate of the universe, and the growth of large scale structure within it, but has not been tested in detail on these cosmic scales. The observed acceleration of the expansion may provide signs of…

Cosmology and Nongalactic Astrophysics · Physics 2011-11-29 Eric V. Linder

Gravitational lensing in metric theories of gravity is discussed. I introduce a generalized approximate metric element, inclusive of both post-post-Newtonian (ppN) contributions and gravito-magnetic field. Following Fermat's principle and…

Astrophysics · Physics 2009-11-07 M. Sereno

Whatever information a deep neural network has gleaned from training data is encoded in its weights. How this information affects the response of the network to future data remains largely an open question. Indeed, even defining and…

Machine Learning · Computer Science 2020-06-23 Alessandro Achille , Giovanni Paolini , Stefano Soatto

We present the data-driven reconstruction of gravitational theories and Dark Energy models on cosmological scales. We showcase the power of present cosmological probes at constraining these models and quantify the knowledge of their…

Cosmology and Nongalactic Astrophysics · Physics 2020-04-22 Marco Raveri