English
Related papers

Related papers: A New Methodology for Generalizing Unweighted Netw…

200 papers

Today, there exist many centrality measures for assessing the importance of nodes in a network as a function of their position and the underlying topology. One class of such measures builds on eigenvector centrality, where the importance of…

Social and Information Networks · Computer Science 2020-02-28 James B Glattfelder

In network analysis, a measure of node centrality provides a scale indicating how central a node is within a network. The coreness is a popular notion of centrality that accounts for the maximal smallest degree of a subgraph containing a…

Statistics Theory · Mathematics 2024-06-14 Eddie Aamari , Ery Arias-Castro , Clément Berenfeld

Weight norm $\|w\|$ and margin $\gamma$ participate in learning theory via the normalized margin $\gamma/\|w\|$. Since standard neural net optimizers do not control normalized margin, it is hard to test whether this quantity causally…

Machine Learning · Computer Science 2022-09-21 Alexander R. Farhang , Jeremy Bernstein , Kushal Tirumala , Yang Liu , Yisong Yue

Complex networks have gained more attention from the last few years. The size of real-world complex networks, such as online social networks, WWW network, collaboration networks, is increasing exponentially with time. It is not feasible to…

Social and Information Networks · Computer Science 2019-10-08 Akrati Saxena , Vaibhav Malik , S. R. S. Iyengar

While much of network design focuses mostly on cost (number or weight of edges), node degrees have also played an important role. They have traditionally either appeared as an objective, to minimize the maximum degree (e.g., the Minimum…

Data Structures and Algorithms · Computer Science 2023-02-23 Michael Dinitz , Guy Kortsarz , Shi Li

There are several metrics (Modularity, Mutual Information, Conductance, etc.) to evaluate the strength of graph clustering in large graphs. These metrics have great significance to measure the effectiveness and they are often used to find…

Social and Information Networks · Computer Science 2016-10-12 Md. Khaledur Rahman

Communities of vertices within a giant network such as the World-Wide Web are likely to be vastly smaller than the network itself. However, Fortunato and Barth\'{e}lemy have proved that modularity maximization algorithms for community…

Physics and Society · Physics 2013-05-29 Jonathan W. Berry , Bruce Hendrickson , Randall A. LaViolette , Cynthia A. Phillips

Despite the celebrated popularity of Graph Neural Networks (GNNs) across numerous applications, the ability of GNNs to generalize remains less explored. In this work, we propose to study the generalization of GNNs through a novel…

Machine Learning · Computer Science 2024-04-17 Shouheng Li , Dongwoo Kim , Qing Wang

The local structure of unweighted networks can be characterized by the number of times a subgraph appears in the network. The clustering coefficient, reflecting the local configuration of triangles, can be seen as a special case of this…

Statistical Mechanics · Physics 2009-11-10 J. -P. Onnela , J. Saramäki , J. Kertész , K. Kaski

A community within a network is a group of vertices densely connected to each other but less connected to the vertices outside. The problem of detecting communities in large networks plays a key role in a wide range of research areas, e.g.…

Social and Information Networks · Computer Science 2013-03-08 Pasquale De Meo , Emilio Ferrara , Giacomo Fiumara , Alessandro Provetti

We show that modularity, a quantity introduced in the study of networked systems, can be generalized and used in the clustering problem as an indicator for the quality of the solution. The introduction of this measure arises very naturally…

Statistical Mechanics · Physics 2009-11-11 L. Angelini , D. Marinazzo , M. Pellicoro , S. Stramaglia

Edge-weighted graphs play an important role in the theory of Robinsonian matrices and similarity theory, particularly via the concept of level graphs, that is, graphs obtained from an edge-weighted graph by removing all sufficiently light…

Existing generalization measures that aim to capture a model's simplicity based on parameter counts or norms fail to explain generalization in overparameterized deep neural networks. In this paper, we introduce a new, theoretically…

Machine Learning · Computer Science 2021-03-11 Lorenz Kuhn , Clare Lyle , Aidan N. Gomez , Jonas Rothfuss , Yarin Gal

Modularity is a popular metric for quantifying the degree of community structure within a network. The distribution of the largest eigenvalue of a network's edge weight or adjacency matrix is well studied and is frequently used as a…

Methodology · Statistics 2020-07-15 Rong Ma , Ian Barnett

This paper studies the novel concept of weight correlation in deep neural networks and discusses its impact on the networks' generalisation ability. For fully-connected layers, the weight correlation is defined as the average cosine…

Machine Learning · Computer Science 2020-10-20 Gaojie Jin , Xinping Yi , Liang Zhang , Lijun Zhang , Sven Schewe , Xiaowei Huang

The roles of different nodes within a network are often understood through centrality analysis, which aims to quantify the capacity of a node to influence, or be influenced by, other nodes via its connection topology. Many different…

Social and Information Networks · Computer Science 2020-07-01 Stuart Oldham , Ben Fulcher , Linden Parkes , Aurina Arnatkeviciute , Chao Suo , Alex Fornito

Regularization is a set of techniques that are used to improve the generalization ability of deep neural networks. In this paper, we introduce weight compander (WC), a novel effective method to improve generalization by reparameterizing…

Machine Learning · Computer Science 2023-06-30 Rinor Cakaj , Jens Mehnert , Bin Yang

Learning distributed representations for nodes in graphs is a crucial primitive in network analysis with a wide spectrum of applications. Linear graph embedding methods learn such representations by optimizing the likelihood of both…

Machine Learning · Computer Science 2018-10-16 Yihan Gao , Chao Zhang , Jian Peng , Aditya Parameswaran

The coexistence of sparsity and clustering (non-vanishing average fraction of triangles per node) is one of the few structural features that, irrespective of finer details, are ubiquitously observed across large real-world networks. This…

Probability · Mathematics 2026-03-17 Alessio Catanzaro , Remco van der Hofstad , Diego Garlaschelli

We present a new metric of link cohesion for measuring the strength of edges in complex, highly connected graphs. Link cohesion accounts for local small hop connections and associated node degrees and can be used to support edge scoring and…

Social and Information Networks · Computer Science 2020-03-09 Cetin Savkli , Catherine Schwartz , Amanda Galante , Jonathan Cohen