Dual Encoder Contrastive Learning with Augmented Views for Graph Anomaly Detection

Authors: Nannan Wu, Hongdou Dong, Wenjun Wang, Yiming Zhao

IJCAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experimental results demonstrate that DECLARE outperforms state-of-the-art baselines across six benchmark datasets.
Researcher Affiliation Academia 1College of Intelligence and Computing, Tianjin University, Tianjin, China 2Yazhou Bay Innovation Institute, Hainan Tropical Ocean University, China EMAIL
Pseudocode No The paper describes the methodology using prose and mathematical formulations in Section 4, but does not include any explicit pseudocode or algorithm blocks.
Open Source Code No The paper does not contain any explicit statements about releasing open-source code, nor does it provide a link to a code repository.
Open Datasets Yes To evaluate our model, we use six widely recognized benchmark datasets commonly employed in graph anomaly detection. These datasets are categorized into two types: citation network datasets and social network datasets [Liu et al., 2021; Zheng et al., 2021]. The citation network datasets include Cora, Citeseer, ACM, and Pubmed, while the social network datasets consist of Blog Catalog and Flickr.
Dataset Splits No The paper mentions anomaly ratios for each dataset in Table 1 and states that anomaly injection methods from [Ding et al., 2019; Liu et al., 2021] were used. However, it does not provide specific training/test/validation splits (percentages or counts) for the datasets.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory, or specific cloud/cluster configurations) used for running the experiments.
Software Dependencies No The paper mentions using the Adam optimizer but does not provide specific version numbers for any key software components, libraries, or frameworks used in the implementation.
Experiment Setup Yes In this study, we set the subgraph size to 4. The GNN encoder and the attribute decoder each consist of two layers of GNN, while the structure decoder uses a single-layer GCN. The hidden layer embedding dimension is fixed to 64. We optimize the model using the Adam optimizer, with a batch size of 300 across all datasets. For the Cora, Citeseer, Pubmed, and ACM datasets, the learning rate is set to 0.001, whereas for Blog Catalog, the learning rate is 0.003, and for Flickr, it is 5e-4. The model is trained for a total of 300 epochs.