Notice: This website is continuously updated as new conference proceedings and journal volumes are published. Consequently, the figures presented here may differ from those reported in our publications.
A brief overview of our methodology is provided on the Methods page, along with references to publications documenting our approach and links to the code and data used in each study.
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.
Digraph Inception Convolutional Networks
Authors: Zekun Tong, Yuxuan Liang, Changsheng Sun, Xinke Li, David Rosenblum, Andrew Lim
NeurIPS 2020 | Venue PDF | LLM Run Details | Input Tokens: 19,422 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 4,911 Total number of tokens produced by the LLM (including reasoning/thinking tokens) for this paper's analysis.
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We empirically show that Di GCN can encode more structural information from digraphs than GCNs and help achieve better performance when generalized to other models. Moreover, experiments on various benchmarks demonstrate its superiority against the state-of-the-art methods. We conduct extensive experiments to evaluate the effectiveness of our model. |
| Researcher Affiliation | Academia | 1Department of Industrial Systems Engineering and Management, National University of Singapore, Singapore 2Department of Computer Science, National University of Singapore, Singapore 3Department of Computer Science, George Mason University, VA, USA EMAIL EMAIL, EMAIL |
| Pseudocode | No | The paper does not contain a pseudocode block or a clearly labeled algorithm block. |
| Open Source Code | Yes | Our implement can be obtained at https://github.com/flyingtango/DiGCN. |
| Open Datasets | Yes | We use several digraph datasets including citation networks: CORA-ML [6] and CITESEER [33], and Amazon Co-purchase Networks: AM-PHOTO and AM-COMPUTER [34]. |
| Dataset Splits | Yes | For train/validation/test split, following the rules in GCN [19], we choose 20 labels per class for training set, 500 labels for validation set and rest for test set. |
| Hardware Specification | Yes | Figure 3(c) summarizes the results and shows that our model can handle about 10 million nodes in one GPU (11GB). |
| Software Dependencies | No | The paper mentions software components generally but does not provide specific version numbers for any of its software dependencies. |
| Experiment Setup | Yes | We train all models for a maximum of 1000 epochs and early stop if the validation accuracy does not increase for 200 consecutive epochs, then calculate mean test accuracy with STD in percent (%) averaged over 20 random dataset splits with random weight initialization. |