Robust Heterophilic Graph Learning against Label Noise for Anomaly Detection
Authors: Junhang Wu, Ruimin Hu, Dengshi Li, Zijun Huang, Lingfei Ren, Yilong Zang
IJCAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments on realworld datasets demonstrate the effectiveness of our method. |
| Researcher Affiliation | Academia | Junhang Wu1,2 , Ruimin Hu 1,3, , Dengshi Li4,1 , Zijun Huang1,2 , Lingfei Ren1,2 , Yilong Zang1,2 1 National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University 2 Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University 3 School of Cyber Science and Engineering, Wuhan University 4 School of Artificial Intelligence, Jianghan University {wjh920925, huangzijun, renlingfei, zangyl}@whu.edu.cn, hurm1964@gmail.com, reallds@jhun.edu.cn |
| Pseudocode | No | The paper describes the proposed model and its components in detail but does not include a formally labeled pseudocode or algorithm block. |
| Open Source Code | Yes | The source code of our model is available1. 1https://github.com/Shzuwu/NRGL |
| Open Datasets | Yes | Two widely used datasets are utilized to evaluate NRGL, and their statistics are shown in Table 2. Elliptic [Weber et al., 2019]: It is a Bitcoin transaction network where transactions and flows are the nodes and edges. The task is to predict illegal nodes (transactions). Yelp [Rayana and Akoglu, 2015]: It collects the reviews of hotels or restaurants on the Yelp platform, and the reviews are seen as nodes to be connected if they are posted by the same user. The task is to detect fake nodes (reviews). |
| Dataset Splits | Yes | Following [Chai et al., 2022], we adopt the same dataset division. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used for experiments, such as CPU or GPU models, memory, or other computational resources. |
| Software Dependencies | No | The paper does not list specific software dependencies with version numbers (e.g., PyTorch 1.9, Python 3.8). |
| Experiment Setup | Yes | We deploy the batch size of 512 for both Elliptic and Yelp, the initial learning rate of 0.01, and the high-pass filter strength controller coefficient α of 0.1. |