KDLGT: A Linear Graph Transformer Framework via Kernel Decomposition Approach

Authors: Yi Wu, Yanyang Xu, Wenhao Zhu, Guojie Song, Zhouchen Lin, Liang Wang, Shaoguo Liu

IJCAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments on both real-world and synthetic datasets indicate that KDLGT not only achieves state-of-the-art performance on various datasets but also reaches an acceleration ratio of approximately 10 on graphs of certain sizes.
Researcher Affiliation Collaboration Yi Wu1 , Yanyang Xu2 , Wenhao Zhu3 , Guojie Song3 , Zhouchen Lin3,4,5 , Liang Wang6 , Shaoguo Liu6 1 Academy for Advanced Interdisciplinary Studies, Peking University 2 School of Software and Microelectronics, Peking University 3 National Key Lab of General AI, School of Intelligence Science and Technology, Peking University 4 Institute for Artificial Intelligence, Peking University 5 Peng Cheng Laboratory 6 Alibaba Group, Beijing, China wuyi aais@pku.edu.cn , xuyanyang@stu.pku.edu.cn , {wenhaozhu, gjsong, zlin}@pku.edu.cn , {liangbo.wl, shaoguo.lsg}@alibaba-inc.com
Pseudocode No The paper describes methods using mathematical formulations but does not include any explicitly labeled pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any links to source code or explicitly state that the code is available or will be made public.
Open Datasets Yes The benchmarking-GNN [Dwivedi et al., 2020] (ZINC), OGB [Hu et al., 2020] (OGBG-MOLHIV) and TUD [Morris et al., 2020] (MUTAG, COX2 MD, PROTEINS, NCI1) are all popular graph-level benchmark datasets... The Cora, Citeseer and Pub Med [Yang et al., 2016] are popular citation datasets... Last FM-Asia [Rozemberczki and Sarkar, 2020] is a social network...
Dataset Splits Yes In the experiments, for the datasets without public splits, we use random split with the ratio of training/validation/test sets being 7/1.5/1.5.
Hardware Specification Yes All models are trained and evaluated on 3 NVIDIA RTX 3090 GPUs for the fairness of efficiency comparison.
Software Dependencies No The paper mentions 'Our models are implemented in Py Torch' but does not provide specific version numbers for PyTorch or any other software dependencies.
Experiment Setup Yes We use Adam [Kingma and Ba, 2015] as the optimizer and set hyperparameter ϵ to 1e-7 and (β1, β2) to (0.99, 0.999), respectively. Besides, the initial learning rate is set to 1e-4 with a linear decay learning rate scheduler. The training and inference batch sizes are both set to 128.