Publications associées à Extrapolating Paths with Graph Neural Networks

The power of adaptivity in source identification with time queries on the path

Patrick Thiran, Gergely Odor, Victor Cyril L Lecomte

We study the problem of identifying the source of a stochastic diffusion process spreading on a graph based on the arrival times of the diffusion at a few queried nodes. In a graph

G=(V,E)

, an unknown source node

v^* \in V

is drawn uniformly at random, ...

2022

Efficient Text-based Reinforcement Learning by Jointly Leveraging State and Commonsense Graph Representations

Mrinmaya Sachan, Mattia Atzeni

Text-based games (TBGs) have emerged as useful benchmarks for evaluating progress at the intersection of grounded language understanding and reinforcement learning (RL). Recent work has proposed the use of external knowledge to improve the efficiency of RL ...

ASSOC COMPUTATIONAL LINGUISTICS-ACL2021

iPool--Information-Based Pooling in Hierarchical Graph Neural Networks

Pascal Frossard, Chenglin Li, Xing Gao

With the advent of data science, the analysis of network or graph data has become a very timely research problem. A variety of recent works have been proposed to generalize neural networks to graphs, either from a spectral graph theory or a spatial perspec ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2021

On Representation Learning for Scientific News Articles Using Heterogeneous Knowledge Graphs

Karl Aberer, Angeliki Romanou, Panagiotis Smeros

In the era of misinformation and information inflation, the credibility assessment of the produced news is of the essence. However, fact-checking can be challenging considering the limited references presented in the news. This challenge can be transcended ...

ASSOC COMPUTING MACHINERY2021

NICEpath: Finding metabolic pathways in large networks through atom-conserving substrate-product pairs

Vassily Hatzimanikatis, Jasmin Maria Hafner

Motivation: Finding biosynthetic pathways is essential for metabolic engineering of organisms to produce chemicals, biodegradation prediction of pollutants and drugs, and for the elucidation of bioproduction pathways of secondary metabolites. A key step in ...

OXFORD UNIV PRESS2021

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

Graph Signal Processing: Foundations and Emerging Directions [From the Guest Editors]

Dimitri Nestor Alice Van De Ville, Negar Kiyavash

The articles in this special section focus on graph signal processing. Generically, the networks that sustain our societies can be understood as complex systems formed by multiple nodes, where global network behavior arises from local interactions between ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2020

Community-Aware Graph Signal Processing: Modularity Defines New Ways of Processing Graph Signals

Dimitri Nestor Alice Van De Ville, Thomas William Arthur Bolton, Raphaël Pierre Liégeois

The emerging field of graph signal processing (GSP) allows one to transpose classical signal processing operations (e.g., filtering) to signals on graphs. The GSP framework is generally built upon the graph Laplacian, which plays a crucial role in studying ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2020

Scale-dependent measure of network centrality from diffusion dynamics

Alexis Arnaudon

Classic measures of graph centrality capture distinct aspects of node importance, from the local (e.g., degree) to the global (e.g., closeness). Here we exploit the connection between diffusion and geometry to introduce a multiscale centrality measure. A n ...

AMER PHYSICAL SOC2020

Dynamic pattern recognition in large-scale graphs with applications to social networks

Volodymyr Miz

A graph is a versatile data structure facilitating representation of interactions among objects in various complex systems. Very often these objects have attributes whose measurements change over time, reflecting the dynamics of the system. This general da ...

EPFL2020

Extrapolating Paths with Graph Neural Networks

Graph Chatbot

Chattez avec Graph Search

The power of adaptivity in source identification with time queries on the path

Efficient Text-based Reinforcement Learning by Jointly Leveraging State and Commonsense Graph Representations

iPool--Information-Based Pooling in Hierarchical Graph Neural Networks

On Representation Learning for Scientific News Articles Using Heterogeneous Knowledge Graphs

NICEpath: Finding metabolic pathways in large networks through atom-conserving substrate-product pairs

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

Graph Signal Processing: Foundations and Emerging Directions [From the Guest Editors]

Community-Aware Graph Signal Processing: Modularity Defines New Ways of Processing Graph Signals

Scale-dependent measure of network centrality from diffusion dynamics

Dynamic pattern recognition in large-scale graphs with applications to social networks

On Representation Learning for Scientific News Articles Using Heterogeneous Knowledge Graphs

NICEpath: Finding metabolic pathways in large networks through atom-conserving substrate-product pairs

Scale-dependent measure of network centrality from diffusion dynamics

The power of adaptivity in source identification with time queries on the path

Efficient Text-based Reinforcement Learning by Jointly Leveraging State and Commonsense Graph Representations

Community-Aware Graph Signal Processing: Modularity Defines New Ways of Processing Graph Signals

iPool--Information-Based Pooling in Hierarchical Graph Neural Networks

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

Graph Signal Processing: Foundations and Emerging Directions [From the Guest Editors]

Dynamic pattern recognition in large-scale graphs with applications to social networks