search

VITA-Group / Deep_GCN_Benchmarking

[TPAMI 2022] "Bag of Tricks for Training Deeper Graph Neural Networks A Comprehensive Benchmark Study" by Tianlong Chen*, Kaixiong Zhou*, Keyu Duan, Wenqing Zheng, Peihao Wang, Xia Hu, Zhangyang Wang
MIT License
125 stars 20 forks source link

the use of self.cached in models/GCN.py #2

Open Bolairex opened 3 years ago

Bolairex commented 3 years ago

Could you please explain the use of self.cached in models/GCN.py? If the setting is transductive and the self.cached is set to 'False' manually, will that influence the performance (e.g. ACC) of the algorithm?

ScottHoang commented 2 years ago

the self.cached prevented the model from recomputing the normalized graph over and over and just memorizing it since the graph is the same in inductive. Without cached, each run might take longer, but I doubt the ACC will suffer.