Inductive Anomaly Detection on Attributed Networks

Authors: Kaize Ding, Jundong Li, Nitin Agarwal, Huan Liu

IJCAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on various attributed networks demonstrate the efficacy of the proposed approach.
Researcher Affiliation Academia Kaize Ding1 , Jundong Li2,3 , Nitin Agarwal4 and Huan Liu1 1Computer Science and Engineering, Arizona State University, USA 2Electrical and Computer Engineering, University of Virginia, USA 3Computer Science & School of Data Science, University of Virginia, USA 4Information Science, University of Arkansas Little Rock, USA kaize.ding@asu.edu, jundong@virginia.edu, nxagarwal@ualr.edu, huan.liu@asu.edu
Pseudocode Yes Algorithm 1: The training process of AEGIS
Open Source Code No The paper does not provide any explicit statements about releasing source code or links to a code repository for the described methodology.
Open Datasets Yes In the experiments, we employ three public real-world attributed network datasets (Blog Catalog [Wang et al., 2010], Flickr [Tang and Liu, 2009], and ACM [Tang et al., 2008]) for performance comparison.
Dataset Splits Yes we sample another 40% data to construct the newly observed attributed (sub)network G for testing and the remaining 10% data is for the validation purpose.
Hardware Specification No The paper does not specify any hardware details such as CPU/GPU models, memory, or cloud computing instances used for experiments.
Software Dependencies No The paper mentions software components like ELU, ReLU, and Adam optimizer but does not provide specific version numbers for any programming languages, libraries, or frameworks (e.g., Python, PyTorch, TensorFlow).
Experiment Setup Yes We set the learning rate of the reconstruction loss to 0.005. The training epoch of GDN-AE is 200, while the training epoch of Ano-GAN is 50. We set the parameter K to 3 (Blog Caltalog), 2 (Flickr), 3 (ACM). In addition, the number of samples P is set to 0.05 n for each dataset.