pytorch_geometric
PyTorch üzerine kurulu Graph Neural Network kütüphanesidir (PyG). Yayımlanmış makalelerden grafik ve düzensiz yapılar üzerinde derin öğrenme yöntemleri, mini-batch yükleyiciler, çoklu GPU ve torch.compile desteği, çok sayıda kıyaslama veri seti ve dönüşümler sunar. MIT lisanslıdır.
pyg-team · MLOps & AI Infrastructure
Common commercial products in this category: Weights & Biases, Amazon SageMaker, Databricks
- 10-20 satır kodla bir GNN modeli eğitmeye başlayabilirsin
- Çok sayıda küçük grafı veya tek dev grafı mini-batch yükleyicilerle işleyebilirsin
- Milyonlarca düğümlü grafikler için ölçeklenebilir GNN'ler kullanabilirsin
- • Website is unreachable (checked: 2026-10-31)
- • High number of open issues (1,384)
- ↑ PositiveGitHub Issue
Link Prediction on Heterogeneous Graphs with Heterogeneous Graph Learning
“### 🚀 The feature, motivation and pitch I am working with heterogeneous knowledge graphs and am trying to do link prediction on them. The specific issue I am facing is that I cannot find any working implementation that would allow me to do link prediction on a graph with…”
- • NeutralGitHub Issue
Issue reproducing the results of the original ecc implementation. Pooling layer and conv layer are giving different resu
“As I mentioned in #319 I have problems to reproduce the [ecc implemenation]( using pytorch_geometric. I found some differences between the results obtained, first one is that the results of both convolution operations using the same weights have different results. Moreover, the…”
Verified against README · Oct 30, 2026 · source