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.
Hierarchical Multi-Marginal Optimal Transport for Network Alignment
Authors: Zhichen Zeng, Boxin Du, Si Zhang, Yinglong Xia, Zhining Liu, Hanghang Tong
AAAI 2024 | Venue PDF | LLM Run Details | Input Tokens: 19,100 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 4,627 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 | Extensive experiments and analysis show that our proposed HOT achieves significant improvements over the state-of-the-art in both effectiveness and scalability. |
| Researcher Affiliation | Collaboration | Zhichen Zeng1, Boxin Du2, Si Zhang3, Yinglong Xia3, Zhining Liu1, Hanghang Tong1 1University of Illinois Urbana-Champaign 2Amazon 3Meta |
| Pseudocode | No | The paper has an 'Optimization Algorithm' section detailing iterative calculations (e.g., Eq. 8-13), but it does not present these as a formal 'Pseudocode' or 'Algorithm' block/figure. |
| Open Source Code | Yes | 1Code and datasets are available at https://github.com/ zhichenz98/HOT-AAAI24 |
| Open Datasets | Yes | 1Code and datasets are available at https://github.com/ zhichenz98/HOT-AAAI24 |
| Dataset Splits | Yes | To mitigate the effect of data split, we randomly split the datatsets into 10 folds, using 1 fold (i.e., 10%) for training and the rest 9 folds for testing. We report the mean and standard deviation of the alignment results with different training/test splits. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., CPU/GPU models, memory) used for running the experiments. It only generally refers to 'GPU' in a related work context without linking it to their own experimental setup. |
| Software Dependencies | No | The paper does not provide specific software dependencies with version numbers. |
| Experiment Setup | Yes | In our experiments, we adopt a consistent parameter setting with λ=10 3, α=0.5, and β =0.15. For number of clusters, we set M = n 50 for all datasets. |