Robust Graph Dictionary Learning

Authors: Weijie Liu, Jiahao Xie, Chao Zhang, Makoto Yamada, Nenggan Zheng, Hui Qian

ICLR 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results demonstrate that our algorithm achieves good performance on both simulated and real-world datasets. This section provides empirical evidence that RGDL performs well in the unsupervised graph clustering task on both synthetic and real-world datasets
Researcher Affiliation Collaboration Weijie Liu,1,2 Jiahao Xie,2 Chao Zhang,2,8,9 Makoto Yamada,3,4,5 Nenggan Zheng,1,2,6,8 Hui Qian2,7,8 1 Qiushi Academy for Advanced Studies, Zhejiang University 2 College of Computer Science and Technology, Zhejiang University 3 Okinawa Institute of Science and Technology 4 Kyoto University 5 RIKEN AIP 6 Zhejiang Lab 7 State Key Lab of CAD&CG, Zhejiang University 8 Alibaba-Zhejiang University Joint Research Institute of Frontier Technologies 9 Advanced Technology Institute, Zhejiang University
Pseudocode Yes Algorithm 1 Projected Gradient Descent for RGWD. Algorithm 2 Robust Graph Dictionary Learning (RGDL)
Open Source Code Yes Code available at https://github.com/cxxszz/rgdl.
Open Datasets Yes We first test RGDL in the graph clustering task on datasets simulated according to the well-studied Stochastic Block Model (SBM) (Holland et al., 1983; Wang and Wong, 1987). We consider widely utilized benchmark datasets including MUTAG (Debnath et al., 1991), BZR (Sutherland et al., 2003), and Peking 1 (Pan et al., 2016). We further use RGDL to cluster real-world graphs. RGDL is thus compared against GDL (Vincent-Cuaz et al., 2021), GWF (Xu, 2020), and other state-of-the-art graph classification methods including WGDL (Zhang et al., 2021) and GNTK (Du et al., 2019) on the benchmark datasets MUTAG (Debnath et al., 1991), IMDB-B, and IMDB-M (Yanardag and Vishwanathan, 2015).
Dataset Splits Yes We perform a 10-fold nested cross validation (using 9 folds for training, 1 for testing, and reporting the average accuracy of this experiment repeated 10 times) by keeping same folds across methods.
Hardware Specification No The paper does not specify any particular hardware components (e.g., GPU models, CPU types, or memory) used for running the experiments.
Software Dependencies No The paper mentions software components like 'kmeans algorithm' and '3-NN as the classifier' but does not provide specific version numbers for any software dependencies or libraries used in the experiments.
Experiment Setup Yes The heat kernel matrix is employed for the PRM. The number of atoms M is set as M = β(# classes) where β is chosen from {2, 3, 4, 5}. RGDL is run with different values of ϵ. Specifically, ϵ is chosen from {U, 10−1U, 10−2U, 10−3U} where U = maxk∈JKK Ck. We further conduct sensitivity analysis of λ by varying the value in {0, 10−5, 10−4, 10−3, 10−2, 10−1}. RGDL, GDL, and GWF use 3-NN as the classifier due to its simplicity.