Mean-field theory of graph neural networks in graph partitioning

Authors: Tatsuro Kawamoto, Masashi Tsubaki, Tomoyuki Obuchi

NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental A theoretical performance analysis of the graph neural network (GNN) is presented. ... This demonstrates a good agreement with numerical experiments.
Researcher Affiliation Academia Tatsuro Kawamoto, Masashi Tsubaki Artificial Intelligence Research Center, National Institute of Advanced Industrial Science and Technology, 2-3-26 Aomi, Koto-ku, Tokyo, Japan {kawamoto.tatsuro, tsubaki.masashi}@aist.go.jp Tomoyuki Obuchi Department of Mathematical and Computing Science, Tokyo Institute of Technology, 2-12-1 Ookayama Meguro-ku Tokyo, Japan obuchi@c.titech.ac.jp
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code No The paper mentions implementing the GNN using Chainer but does not provide any statement or link indicating that their specific implementation code is open-source or publicly available.
Open Datasets No The paper uses data generated from the Stochastic Block Model (SBM) rather than a pre-existing, publicly available dataset with concrete access information.
Dataset Splits Yes For the validation (development) set, 100 graph instances of the same SBMs are provided.
Hardware Specification No The paper does not provide specific hardware details (e.g., CPU/GPU models, memory, or cloud instance types) used for running the experiments.
Software Dependencies Yes We implemented the GNN using Chainer (version 3.2.0) [36].
Experiment Setup Yes We set the dimension of the feature space to D = 100 and the number of layers to T = 100, and each result represents the average over 30 samples. ... We also employ residual networks (Res Nets) [38] and batch normalization (BN) [39].