Publication

Nature vs. Nurture: Feature vs. Structure for Graph Neural Networks

Related publications (163)

Graph Chatbot

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.

k-Quasi-Planar Graphs

A topological graph is k-quasi-planar if it does not contain k pairwise crossing edges. A topological graph is simple if every pair of its edges intersect at most once (either at a vertex or at their intersection). In 1996, Pach, Shahrokhi. and Szegedy [16 ...

Springer-Verlag Berlin2012

Beyond Graphs: A New Synthesis

Dario Floreano, Claudio Mattiussi, Daniel Marbach, Peter Dürr

Artiﬁcial neural networks, electronic circuits, and gene networks are some examples of systems that can be modeled as networks, that is, as collections of interconnected nodes. In this paper we introduce the concept of terminal graph (t-graph for short), w ...

2011

Wavelet Frames On Graphs Defined By Fmri Functional Connectivity

Dimitri Nestor Alice Van De Ville, Nora Leonardi

Multiscale representations such as the wavelet transform are useful for many signal processing tasks. Graphs are flexible models to represent complex networks and a spectral graph wavelet transform (SGWT) has recently been developed as a generalization of ...

Ieee Service Center, 445 Hoes Lane, Po Box 1331, Piscataway, Nj 08855-1331 Usa2011

Algebraic Algorithms for Vector Network Coding

Christina Fragouli, Javad Ebrahimi Boroojeni

We develop new algebraic algorithms for scalar and vector network coding. In vector network coding, the source multicasts information by transmitting vectors of length L, while intermediate nodes process and combine their incoming packets by multiplying th ...

Institute of Electrical and Electronics Engineers2011

Parallelizing Machine Learning- Functionally: A Framework and Abstractions for Parallel Graph Processing

Philipp Haller

Implementing machine learning algorithms for large data, such as the Web graph and social networks, is challenging. Even though much research has focused on making sequential algorithms more scalable, their running times continue to be prohibitively long. ...

2011

Graphs that Admit Right Angle Crossing Drawings

Radoslav Fulek, Balázs Keszegh, Filip Moric

We consider right angle crossing (RAC) drawings of graphs in which the edges are represented by polygonal arcs and any two edges can cross only at a right angle. We show that if a graph with n vertices admits a RAC drawing with at most 1 bend or 2 bends pe ...

2010

Leveraging User-Generated Content for Information Discovery on the Web

Adriana Budura

The large-scale adoption of the Web 2.0 paradigm has revolutionized the way we interact with the Web today. End-users, so far mainly passive consumers of information are now becoming active information producers, creating, uploading, and commenting on all ...

EPFL2010

Algebraic techniques for deterministic networks

Christina Fragouli, Javad Ebrahimi Boroojeni

We here summarize some recent advances in the study of linear deterministic networks, recently proposed as approximations for wireless channels. This work started by extending the algebraic framework developed for multicasting over graphs in [1] to include ...

2010

A separator theorem for string graphs and its applications

János Pach

A string graph is the intersection graph of a collection of continuous arcs in the plane. We show that any string graph with in edges can be separated into two parts of roughly equal size by the removal of O(m(3/4)root log m) vertices. This result is then ...

Cambridge University Press2010

A Magnetic Procedure for the Stability Number

Dominique de Werra

A magnet is a pair u, v of adjacent vertices such that the proper neighbours of u are completely linked to the proper neighbours of v. It has been shown that one can reduce the graph by removing the two vertices u, v of a magnet and introducing a new verte ...

2009