paper-with-me

Papers

Ego-GNNs: Exploiting Ego Structures in Graph Neural Networks

2021-07-22 · Dylan Sandfelder, Priyesh Vijayan, William L. Hamilton

Graph neural networks (GNNs) have achieved remarkable success as a framework for deep learning on graph-structured data. However, GNNs are fundamentally limited by their tree-structured inductive bias: the WL-subtree kernel formulation bounds the representational capacity of GNNs, and polynomial-time GNNs are provably incapable of recognizing triangles in a graph. In this work, we propose to augment the GNN message-passing operations with information defined on ego graphs (i.e., the induced subgraph surrounding each node). We term these approaches Ego-GNNs and show that Ego-GNNs are provably more powerful than standard message-passing GNNs. In particular, we show that Ego-GNNs are capable of recognizing closed triangles, which is essential given the prominence of transitivity in real-world graphs. We also motivate our approach from the perspective of graph signal processing as a form of multiplex graph convolution. Experimental results on node classification using synthetic and real data highlight the achievable performance gains using this approach.

📄 PDF Abstract BibTeX arXiv:2107.10957

Code (0)

등록된 구현이 없습니다.

Tasks

Inductive BiasNode Classification

Similar Papers 제목 키워드 기반

Graph Neural Ordinary Differential Equations

2019-11-18 · Michael Poli, Stefano Massaroli, Junyoung Park, Atsushi Yamashita 외

We introduce the framework of continuous--depth graph neural networks (GNNs). Graph neural ordinary differential equations (GDEs) are formalized as the counterpart to GNNs where the input-output relationship is determine…

Learning with Multigraph Convolutional Filters

2022-10-28 · Landon Butler, Alejandro Parada-Mayorga, Alejandro Ribeiro

In this paper, we introduce a convolutional architecture to perform learning when information is supported on multigraphs. Exploiting algebraic signal processing (ASP), we propose a convolutional signal processing model …

Continuous-Depth Neural Models for Dynamic Graph Prediction

2021-06-22 · Michael Poli, Stefano Massaroli, Clayton M. Rabideau, Junyoung Park 외

We introduce the framework of continuous-depth graph neural networks (GNNs). Neural graph differential equations (Neural GDEs) are formalized as the counterpart to GNNs where the input-output relationship is determined b…

Prediction

Collaborative Graph Neural Networks for Attributed Network Embedding

2023-07-22 · Qiaoyu Tan, Xin Zhang, Xiao Huang, Hao Chen 외

Graph neural networks (GNNs) have shown prominent performance on attributed network embedding. However, existing efforts mainly focus on exploiting network structures, while the exploitation of node attributes is rather …

AttributeNetwork Embedding

Adapting to Heterophilic Graph Data with Structure-Guided Neighbor Discovery

2025-06-10 · Victor M. Tenorio, Madeline Navarro, Samuel Rey, Santiago Segarra 외

Graph Neural Networks (GNNs) often struggle with heterophilic data, where connected nodes may have dissimilar labels, as they typically assume homophily and rely on local message passing. To address this, we propose crea…