-
## Motivation
PyG currently requires users to store graphs (and associated node + edge features) in `Data` and `HeteroData` objects, which are accepted by loaders to run forward/backward passes on …
-
Recently, I run the example provided with the following command:
```
dglke_train
```
By default, it will use FB15k knowledge graph. However, it seems to construct a graph.HeteroGraph which is not …
-
`compile_forward_sampling_function` tries to reuse any variables that are in the trace as inputs. It uses some logic based on variable name, shared inputs, volatile inputs, ... and so on:
https://g…
-
## 🚀 Feature
Currently, in `sample_neigbours` we only support a single fanout value (see [link](https://github.com/dmlc/dgl/blob/86c81b4e927d94ed2dba76fc04e2088c6931e6b5/python/dgl/sampling/neighb…
-
We are trying to migrate from pure alloy helm chart to grafana-k8s-monitoring. We've been using custom alloy config including some logic around seeding metrics required for [Grafana Service Graphs](ht…
-
Hello! Our static bug checker has found a performance issue in tensorboard-master/tensorboard/plugins/graph/graphs_demo.py: Python type argument [`step`](https://github.com/xjdlb/my-awesome-tensorlf…
-
Would like to have a page (in documentation and/or readme, but leaning towards just documentation) that basically explains each module at an extremely high level and why it might be useful. Could have…
-
### 🐛 Describe the bug
```
import torch
model = torch.nn.EmbeddingBag(num_embeddings=49157, embedding_dim=32, mode="sum")
a = torch.tensor([[39906]]).long()
example_args = (a,)
model_eval = mo…
-
Instead of sampling data in timeline graphs by arbitrary value that may change queries at different times, we should display at some fixed times, so that for a given pixel-time, it will always be the …
-
## PyMC4 developer taskboard
Efforts in implementing pymc4 are not single person, so we need a place to sync our progress on this. This issue should be the place where we communicate, update status o…