Papers › RAN-GNNs: breaking the capacity limits of graph neural networks

RAN-GNNs: breaking the capacity limits of graph neural networks

29 Mar 2021arXiv:2103.15565archive 2025-07-28

Diego Valsesia, Giulia Fracastoro, Enrico Magli

Graph neural networks have become a staple in problems addressing learning and analysis of data defined over graphs. However, several results suggest an inherent difficulty in extracting better performance by increasing the number of layers. Recent works attribute this to a phenomenon peculiar to the extraction of node features in graph-based tasks, i.e., the need to consider multiple neighborhood sizes at the same time and adaptively tune them. In this paper, we investigate the recently proposed randomly wired architectures in the context of graph neural networks. Instead of building deeper networks by stacking many layers, we prove that employing a randomly-wired architecture can be a more effective way to increase the capacity of the network and obtain richer representations. We show that such architectures behave like an ensemble of paths, which are able to merge contributions from receptive fields of varied size. Moreover, these receptive fields can also be modulated to be wider or narrower through the trainable weights over the paths. We also provide extensive experimental evidence of the superior performance of randomly wired architectures over multiple tasks and four graph convolution definitions, using recent benchmarking frameworks that addresses the reliability of previous testing methodologies.

PaperPDF

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

AttributeBenchmarking

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Graph Property Prediction ogbg-molpcba RandomGIN-vn+FLAG Ext. data No #22 of 36 Archive leaderboard report
Graph Property Prediction ogbg-molpcba RandomGIN-vn+FLAG Number of params 5572026 #22 of 36 Archive leaderboard report
Graph Property Prediction ogbg-molpcba RandomGIN-vn+FLAG Test AP 0.2881 ± 0.0028 #22 of 36 Archive leaderboard report
Graph Property Prediction ogbg-molpcba RandomGIN-vn+FLAG Validation AP 0.3035 ± 0.0047 #22 of 36 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Convolution

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections