paper-with-me

홈 › Papers

The Logic of Graph Neural Networks

2021-04-29 · Martin Grohe

Graph neural networks (GNNs) are deep learning architectures for machine learning problems on graphs. It has recently been shown that the expressiveness of GNNs can be characterised precisely by the combinatorial Weisfeiler-Leman algorithms and by finite variable counting logics. The correspondence has even led to new, higher-order GNNs corresponding to the WL algorithm in higher dimensions. The purpose of this paper is to explain these descriptive characterisations of GNNs.

📄 PDF Abstract BibTeX arXiv:2104.14624

Code (0)

등록된 구현이 없습니다.

Tasks

BIG-bench Machine LearningDescriptive

Similar Papers 제목 키워드 기반

A Study of Morphological Filtering Using Graph and Hypergraphs

2015-07-25 · Keerthana S. Prakash, R. P. Prakash, V. P. Binu

Mathematical morphology (MM) helps to describe and analyze shapes using set theory. MM can be effectively applied to binary images which are treated as sets. Basic morphological operators defined can be used as an effect…

Graphery: Interactive Tutorials for Biological Network Algorithms

2021-02-06 · Heyuan Zeng, Jinbiao Zhang, Gabriel A. Preising, Tobias Rubel 외

Networks provide a meaningful way to represent and analyze complex biological information, but the methodological details of network-based tools are often described for a technical audience. Graphery is a hands-on tutori…

Navigate

Topological Spatial Graph Coarsening

2025-12-30 · Anna Calissano, Etienne Lasalle arxiv

Spatial graphs are particular graphs for which the nodes are localized in space (e.g., public transport network, molecules, branching biological structures). In this work, we consider the problem of spatial graph reducti…

Point Clouds

Topological Mapping for Manhattan-like Repetitive Environments

2020-02-16 · Sai Shubodh Puligilla, Satyajit Tourani, Tushar Vaidya, Udit Singh Parihar 외

We showcase a topological mapping framework for a challenging indoor warehouse setting. At the most abstract level, the warehouse is represented as a Topological Graph where the nodes of the graph represent a particular …

Logiformer: A Two-Branch Graph Transformer Network for Interpretable Logical Reasoning

2022-05-02 · Fangzhi Xu, Jun Liu, Qika Lin, Yudai Pan 외

Machine reading comprehension has aroused wide concerns, since it explores the potential of model for text understanding. To further equip the machine with the reasoning capability, the challenging task of logical reason…

Logical ReasoningMachine Reading ComprehensionReading ComprehensionVocal Bursts Valence Prediction