arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2305.00724cs.LG
收藏

使用局部拓扑轮廓(Local Topological Profile)强化图分类的结构基线

Strengthening structural baselines for graph classification using Local Topological Profile

AGH University of Science and Technology(AGH科技大学)

Jakub Adamczyk, Wojciech Czech

AI总结:

本研究分析图分类结构基线LDP,基于公平评估框架提出融合额外中心性与局部顶点描述符的LTP基线,在9个基准中4个达SOTA,优化了计算效率,可胜过GIN等现代模型并提供开源实现。

摘要:

我们对拓扑图描述符局部度轮廓(Local Degree Profile, LDP)展开分析,该描述符是图分类领域广泛使用的结构基线。我们的研究围绕近期提出的公平评估框架开展模型评估,该框架为图分类定义了严格的模型选择与评估流程,可确保结果的可复现性与可比性。基于所得洞察,我们提出一种名为局部拓扑轮廓(Local Topological Profile, LTP)的新型基线算法,它通过引入额外的中心性度量与局部顶点描述符对LDP进行扩展。在所有使用的数据集上,该新方法的结果均优于或非常接近最新的图神经网络(GNN),具体而言,在9个基准数据集中有4个取得了当前最优结果。我们还考量了基于LDP的特征提取与模型构建的计算层面,提出了影响执行速度与可扩展性的实用改进方案,这使得处理现代大规模数据集成为可能,并拓展了图表示学习中所用基准的范围。作为研究成果,我们得到的LTP是一种易于理解、快速且可扩展,同时仍具备鲁棒性的基线,能够胜过现代图分类模型,例如图同构网络(Graph Isomorphism Network, GIN)。我们在GitHub(https://github.com/j-adamczyk/LTP)上提供了开源实现。

英文摘要:

We present the analysis of the topological graph descriptor Local Degree Profile (LDP), which forms a widely used structural baseline for graph classification. Our study focuses on model evaluation in the context of the recently developed fair evaluation framework, which defines rigorous routines for model selection and evaluation for graph classification, ensuring reproducibility and comparability of the results. Based on the obtained insights, we propose a new baseline algorithm called Local Topological Profile (LTP), which extends LDP by using additional centrality measures and local vertex descriptors. The new approach provides the results outperforming or very close to the latest GNNs for all datasets used. Specifically, state-of-the-art results were obtained for 4 out of 9 benchmark datasets. We also consider computational aspects of LDP-based feature extraction and model construction to propose practical improvements affecting execution speed and scalability. This allows for handling modern, large datasets and extends the portfolio of benchmarks used in graph representation learning. As the outcome of our work, we obtained LTP as a simple to understand, fast and scalable, still robust baseline, capable of outcompeting modern graph classification models such as Graph Isomorphism Network (GIN). We provide open-source implementation at \href{https://github.com/j-adamczyk/LTP}{GitHub}.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑