From b5722a56b43d1449eaaaad1b6b18005e332fc4d8 Mon Sep 17 00:00:00 2001 From: meng-ustc Date: Wed, 25 Nov 2020 21:06:15 +0800 Subject: [PATCH] add README.md --- examples/benchmarks/GATs/README.md | 5 +++++ 1 file changed, 5 insertions(+) create mode 100644 examples/benchmarks/GATs/README.md diff --git a/examples/benchmarks/GATs/README.md b/examples/benchmarks/GATs/README.md new file mode 100644 index 000000000..a69e7d433 --- /dev/null +++ b/examples/benchmarks/GATs/README.md @@ -0,0 +1,5 @@ +#GATs +* Graph Attention Networks(GATs) leverage masked self-attentional layers on graph-structured data. The nodes in stacked layers have different weights and they are able to attend over their +neighborhoods’ features, without requiring any kind of costly matrix operation (such as inversion) or depending on knowing the graph structure upfront. +* This code used in Qlib is implemented with PyTorch by ourselves. +* Paper: Graph Attention Networks https://arxiv.org/pdf/1710.10903.pdf \ No newline at end of file