GraphQNTK: Quantum Neural Tangent Kernel for Graph Data
Authors: Yehui Tang, Junchi Yan
NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We empirically show that our method achieves competitive performance on several graph classification benchmarks, and theoretical analysis is provided to demonstrate the superiority of our quantum algorithm. Source code is available at https://github.com/abel1231/graph QNTK. |
| Researcher Affiliation | Academia | Yehui Tang, Junchi Yan Department of Computer Science and Engineering Mo E Key Lab of Artificial Intelligence Shanghai Jiao Tong University {yehuitang, yanjunchi}@sjtu.edu.cn Junchi Yan is the correspondence author who is also with Shanghai AI Laboratory. |
| Pseudocode | No | The paper describes the proposed methods using mathematical formulations and prose but does not include any explicitly labeled pseudocode or algorithm blocks. |
| Open Source Code | Yes | Source code is available at https://github.com/abel1231/graph QNTK. |
| Open Datasets | Yes | All the datasets can be found in [38]. [38] Kristian Kersting, Nils M. Kriege, Christopher Morris, Petra Mutzel, and Marion Neumann. Benchmark data sets for graph kernels, 2016. URL http://graphkernels.cs.tu-dortmund.de. |
| Dataset Splits | Yes | We follow the same setting as [17, 67], and report the average test accuracy and its standard deviation over a 10-fold cross validation on each dataset. |
| Hardware Specification | Yes | All the experiments are performed on a workstation with a single machine with 1TB memory, one physical CPU with 28 cores Intel(R) Xeon(R) W-3175X CPU @ 3.10GHz, and a single GPU (Nvidia Quadro RTX 8000). |
| Software Dependencies | No | The paper does not provide specific software dependencies with version numbers (e.g., Python, PyTorch versions). |
| Experiment Setup | Yes | We apply different hyper-parameter settings to L {2, 4, 6, 8} and R {1, 2, 3} and select the model with the best averaged accuracy. We test the kernel regression using SVM classifier and the regularization parameter is determined using the search protocol which is the same as the [17]. |