A Degeneracy Framework for Scalable Graph Autoencoders
Authors: Guillaume Salha, Romain Hennequin, Viet Anh Tran, Michalis Vazirgiannis
IJCAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We evaluate and discuss our method on several variants of existing graph AE and VAE, providing the first application of these models to large graphs with up to millions of nodes and edges. We achieve empirically competitive results w.r.t. several popular scalable node embedding methods, which emphasizes the relevance of pursuing further research towards more scalable graph AE and VAE. In Section 4, we empirically evaluate our framework. |
| Researcher Affiliation | Collaboration | Guillaume Salha1,2 , Romain Hennequin1 , Viet Anh Tran1 and Michalis Vazirgiannis2 1Deezer Research & Development, Paris, France 2 Ecole Polytechnique, Palaiseau, France |
| Pseudocode | Yes | Algorithm 1 k-core Decomposition; Algorithm 2 Propagation of Latent Representations |
| Open Source Code | No | The paper mentions "supplementary material" (https://arxiv.org/abs/1902.08813), which points to the paper itself, but does not explicitly state that the source code for their methodology is provided or available at a specific repository. |
| Open Datasets | Yes | We provide experiments on the three medium-size graphs used in [Kipf and Welling, 2016b]: Cora (n = 2, 708 and m = 5, 429), Citeseer (n = 3, 327 and m = 4, 732) and Pubmed (n = 19, 717 and m = 44, 338), and on two large graphs from Stanford s SNAP project: the Google web graph (n = 875, 713 and m = 4, 322, 051) and the US Patent citation networks (n = 2, 745, 762 and m = 13, 965, 410). |
| Dataset Splits | Yes | We create validation and test sets from removed edges and from the same number of randomly sampled pairs of unconnected nodes... Validation and test sets gather 5% and 10% of edges (respectively 2% and 3%), for medium-size (resp. large-size) graphs. The incomplete train adjacency matrix is used when running Algorithm 2. Validation set is only used for model tuning. |
| Hardware Specification | Yes | We used Python and especially the Tensorflow library, training models on a NVIDIA GTX 1080 GPU and running other operations on a double Intel Xeon Gold 6134 CPU. |
| Software Dependencies | No | The paper mentions "Python" and "Tensorflow library" but does not specify their version numbers for reproducibility. |
| Experiment Setup | Yes | All models are trained on 200 epochs to return 16-dim embeddings (32-dim for Patent) to reproduce [Kipf and Welling, 2016b] s results. For each model, hyperparameters were tuned on AUC scores using validation set (see Annex 2 for details). |