-
Although #106 has been solved by fusion #108, the slowness of the unfused implementation (`apply_edges` + `aggregate_neighbors`) was not clearly understood. Realistic GNN models would contain mixed ca…
-
How can I work around the issue in InlineStrings https://github.com/JuliaStrings/InlineStrings.jl/issues/21 ?
I don't make any sense of the suggested fix.
For example:
```
julia> using Flux
ju…
-
We came across an instance where the batching function was used for a generator instead of a vector. Do you think that GraphNeuralNetworks would also be able to overload the batching function for gene…
-
#107 breaks Zygote autodiff. `Zygote.gradient()` returns `nothing` for the fused kernel, while returns correct gradient for the unfused one. This bug further breaks GNN training, with hard-to-understa…
-
When repeatedly performing inference operations, the GPU memory gets filled up quite fast. This causes the GPU to have to perform garbage collection. In my implementation, this accounted for 50% of GP…
-
I test the code of
https://carlolucibello.github.io/GraphNeuralNetworks.jl/stable/
I got an error:
![image](https://user-images.githubusercontent.com/12711073/147380538-070cc893-0c30-479c-9609…
zsz00 updated
2 years ago
-
This is a feature request: it'd be nice to have extend the functionality of `Flux.outputsize` to `GNNChain`s. I imagine this could be applied to either a `WithGraph` or a `GNNGraph` and Tuple of `inpu…
-
I'm a bit confused about using multiple node feature arrays per graph. Using multiple node feature arrays allows keeping apart different features of the node (i.e. x and y values) however when trying …
-
With the well-known graph-matrix duality (see [GraphBLAS intro](https://www.sciencedirect.com/science/article/pii/S1877050915011618), Fig. 1), simple graph message passing kernels are equivalent to sp…
-
第五章的数据有2708个样本,但是训练集验证集 测试集 数据分布分别是140:500:1000,数据划分存在问题。
正确的数据集划分应该把
“train_index = np.arange(y.shape[0]) 数据集大小有问题
val_index = np.arange(y.shape[0], y.shape[0] + 500)”
修改为
“x_shape=1208
trai…