This is the official code repository for the paper GCondenser: Benchmarking Graph Condensation. GCondenser is a graph condensation (GC) toolkit, designed for the graph condensation field 🚀. It benchmarks existing GC methods, accelerates the development of your own GC methods, and can be…
The main features of superallen13/gcondenser are: Graph Neural Networks.
Open-source alternatives to superallen13/gcondenser include: labmlai/annotated_deep_learning_paper_implementations — This project is a collection of deep learning research papers translated into annotated code. It serves as a resource… amanda-zheng/sfgc — This is the Pytorch implementation of NeurIPS-23 work: "Structure-free Graph Condensation (SFGC): From Large-scale… amazon-research/doscond — [KDD 2022] The implementation for "Condensing Graphs via One-Step Gradient Matching" on graph classification is shown… benedekrozemberczki/appnp — A PyTorch implementation of "Predict then Propagate: Graph Neural Networks meet Personalized PageRank" (ICLR 2019). benedekrozemberczki/attentionwalk — A PyTorch Implementation of "Watch Your Step: Learning Node Embeddings via Graph Attention" (NeurIPS 2018). a4bio/proteininvbench — One can use the Colab to evaluate our latest models.
This project is a collection of deep learning research papers translated into annotated code. It serves as a resource for reproducing academic research, providing implementations of transformers, diffusion models, and reinforcement learning architectures. The library distinguishes itself by using a side-by-side annotation format that combines executable Python code with descriptive markdown notes. This approach provides a structured way to explain the logic of neural network papers alongside their PyTorch-based implementations. The codebase covers several major capability areas, including ge
This is the Pytorch implementation of NeurIPS-23 work: "Structure-free Graph Condensation (SFGC): From Large-scale Graphs to Condensed Graph-free Data".
KDD 2022 The implementation for "Condensing Graphs via One-Step Gradient Matching" on graph classification is shown below. For node classification, please refer to link.
One can use the Colab to evaluate our latest models.