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 Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The Shift Toward Open and Reproducible AI Research," Under Review, 2026. doi: 10.48550/arXiv.2606.16974..
Descent Steps of a Relation-Aware Energy Produce Heterogeneous Graph Neural Networks
Authors: Hongjoon Ahn, Yongyi Yang, Quan Gan, Taesup Moon, David P Wipf
NeurIPS 2022 | Venue PDF | LLM Run Details | Input Tokens: 18,048 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 3,413 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 | Experimental results on 8 heterogeneous graph benchmarks demonstrate that our proposed method can achieve competitive node classification accuracy. |
| Researcher Affiliation | Collaboration | Hongjoon Ahn1 , Yongyi Yang2 , Quan Gan 3, Taesup Moon 1 and David Wipf 3 1 ECE/IPAI/ASRI/INMC, Seoul National University, 2 University of Michigan, 3 Amazon Web Services |
| Pseudocode | Yes | Algorithm 1 HALO algorithm |
| Open Source Code | Yes | The source code of our algorithm is available at https://github.com/hongjoon0805/HALO. |
| Open Datasets | Yes | HGB contains 4 node classification datasets, which is our focus herein. These include: DBLP, IMDB, ACM, and Freebase. The knowledge graph benchmarking proposed in [29] is composed of 4 datasets: AIFB, MUTAG, BGS, AM. |
| Dataset Splits | No | For the details on the hyperparameters and other experimental settings, please see the Supplementary Materials. |
| Hardware Specification | No | The paper states: “Did you include the total amount of compute and the type of resources used (e.g., type of GPUs, internal cluster, or cloud provider)? [Yes] Please see Supplementary Materials.” This information is not provided in the main paper. |
| Software Dependencies | No | All models and experiments were implemented using Py Torch [25] and the Deep Graph Library (DGL) [32]. |
| Experiment Setup | No | For the details on the hyperparameters and other experimental settings, please see the Supplementary Materials. |