From 7e3d13bbed69a5cbafd79ee21ead7464807b9282 Mon Sep 17 00:00:00 2001 From: Hiwot Kassa Date: Thu, 24 Oct 2024 08:03:08 -0700 Subject: [PATCH] added param count inside benchmark --- graph_neural_network/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/graph_neural_network/README.md b/graph_neural_network/README.md index efb354725..f1b24072a 100644 --- a/graph_neural_network/README.md +++ b/graph_neural_network/README.md @@ -1,5 +1,5 @@ # 1. Problem -This benchmark represents a multi-class node classification task in a heterogenous graph using the [IGB Heterogeneous Dataset](https://github.com/IllinoisGraphBenchmark/IGB-Datasets) named IGBH-Full. The task is carried out using a [GAT](https://arxiv.org/abs/1710.10903) model based on the [Relational Graph Attention Networks](https://arxiv.org/abs/1904.05811) paper. +This benchmark represents a multi-class node classification task in a heterogenous graph using the [IGB Heterogeneous Dataset](https://github.com/IllinoisGraphBenchmark/IGB-Datasets) named IGBH-Full. The task is carried out using a [GAT](https://arxiv.org/abs/1710.10903) model with 25M parameters, based on the [Relational Graph Attention Networks](https://arxiv.org/abs/1904.05811) paper. The reference implementation is based on [graphlearn-for-pytorch (GLT)](https://github.com/alibaba/graphlearn-for-pytorch).