paper-with-me

홈 › Papers

On the expressive power of message-passing neural networks as global feature map transformers

2022-03-17 · Floris Geerts, Jasper Steegmans, Jan Van den Bussche

We investigate the power of message-passing neural networks (MPNNs) in their capacity to transform the numerical features stored in the nodes of their input graphs. Our focus is on global expressive power, uniformly over all input graphs, or over graphs of bounded degree with features from a bounded domain. Accordingly, we introduce the notion of a global feature map transformer (GFMT). As a yardstick for expressiveness, we use a basic language for GFMTs, which we call MPLang. Every MPNN can be expressed in MPLang, and our results clarify to which extent the converse inclusion holds. We consider exact versus approximate expressiveness; the use of arbitrary activation functions; and the case where only the ReLU activation function is allowed.

📄 PDF Abstract BibTeX arXiv:2203.09555

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

MPNN There are at least eight notable examples of models from the literature that can be described using the Message Passing Neural Networks (MPNN) framework. For simplicity we…

Similar Papers 제목 키워드 기반

Expressive Power of Temporal Message Passing

2024-08-19 · Przemysław Andrzej Wałęga, Michael Rawson

Graph neural networks (GNNs) have recently been adapted to temporal settings, often employing temporal versions of the message-passing mechanism known from GNNs. We divide temporal message passing mechanisms from literat…

How Powerful are K-hop Message Passing Graph Neural Networks

2022-05-26 · Jiarui Feng, Yixin Chen, Fuhai Li, Anindya Sarkar 외

The most popular design paradigm for Graph Neural Networks (GNNs) is 1-hop message passing -- aggregating information from 1-hop neighbors repeatedly. However, the expressive power of 1-hop message passing is bounded by …

Improving the Expressiveness of $K$-hop Message-Passing GNNs by Injecting Contextualized Substructure Information

2024-06-27 · Tianjun Yao, Yiongxu Wang, Kun Zhang, Shangsong Liang

Graph neural networks (GNNs) have become the \textit{de facto} standard for representational learning in graphs, and have achieved state-of-the-art performance in many graph-related tasks; however, it has been shown that…

On the Expressive Power of Sparse Geometric MPNNs

2024-07-02 · Yonatan Sverdlov, Nadav Dym

Motivated by applications in chemistry and other sciences, we study the expressive power of message-passing neural networks for geometric graphs, whose node features correspond to 3-dimensional positions. Recent work has…

Identity-aware Graph Neural Networks

2021-01-25 · Jiaxuan You, Jonathan Gomes-Selman, Rex Ying, Jure Leskovec

Message passing Graph Neural Networks (GNNs) provide a powerful modeling framework for relational data. However, the expressive power of existing GNNs is upper-bounded by the 1-Weisfeiler-Lehman (1-WL) graph isomorphism …

Graph ClassificationGraph Property PredictionLink PredictionNode Clustering+1