Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
Graph OOD Detection via Plug-and-Play Energy-based Evaluation and Propagation
Authors: Yunxia Zhang, Mingchen Sun, Yutong Zhang, Funing Yang, Ying Wang
IJCAI 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments on benchmark datasets demonstrate the superiority of our method. |
| Researcher Affiliation | Academia | Yunxia Zhang1 , Mingchen Sun 1 , Yutong Zhang 1,2 , Funing Yang1,2 and Ying Wang1,2 1 College of Computer Science and Technology, Jilin University, China 2 Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, China EMAIL, EMAIL |
| Pseudocode | No | The paper describes the methodology using prose and mathematical equations but does not include any explicitly labeled 'Pseudocode' or 'Algorithm' blocks. |
| Open Source Code | No | The paper does not contain any explicit statement about releasing code for the described methodology, nor does it provide a link to a code repository. |
| Open Datasets | Yes | We utilize three classic node classification datasets for evaluating the effectiveness of our framework, including citation networks [Kipf and Welling, 2017] (i.e., Cora, Citeseer), and academic network [Tang et al., 2008] (i.e., Coauthor-CS). |
| Dataset Splits | Yes | Dataset OOD classes ID size OOD size train-ID val-ID test-ID train-OOD val-OOD test-OOD Cora 0, 1, 2, 3 904 1804 6.64% 18.47% 34.96% 4.43% 18.46% 37.92% Citeseer 0, 1, 2 1805 1522 9.97% 9.97% 80.06% 9.99% 9.99% 80.03% Coauthor-CS 0, 1, 2, 3, 4 13290 5043 10.00% 10.00% 80.00% 9.99% 9.99% 80.01% Table 1: Data partitions. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running its experiments. It only mentions using PyTorch Geometric. |
| Software Dependencies | No | All experiments are done with Py Torch Geometric. The paper mentions the software library used (PyTorch Geometric) but does not specify its version number, nor any other key software dependencies with versions. |
| Experiment Setup | Yes | We utilize a 2-layer GCN with 64 hidden units as the backbone encoder for EPGNN. The dropout probability is 0.7, and the learning rate is 0.01. We set the regularization weight decay coefficient a = 0.9 and the time factor coefficient b = 0.01. For the Cora dataset, the balance parameter for the joint alignment regularization and the temperature coefficient in the energy function is set to β = 1 and T = 3, respectively. For Citeseer, these parameters are β = 0.5 and T = 2, and for Coauthor-CS, they are β = 5 and T = 3. ... During the training process, we set the maximum number of iterations to 2000, and we use early stopping when AUROC+Acc doesn t improve within 200 iterations. |