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 2307.08430cs.AI
收藏

大规模异构图上的长程元路径搜索

Long-range Meta-path Search on Large-scale Heterogeneous Graphs

School of Computer Science, Huazhong University of Science and Technology(华中科技大学计算机学院);Hopcroft Center on Computing Science, Huazhong University of Science and Technology(华中科技大学霍普克罗夫特计算科学中心)

Chao Li, Zijie Guo, Qiuting He, Hao Xu, Kun He

AI总结:

针对大规模异构图中长程依赖利用不足及过平滑问题,提出渐进采样长程元路径搜索框架LMSPS,动态缩小搜索空间并选择有效元路径,在多个数据集上超越现有方法。

摘要:

利用长程依赖(一种在同质图中被广泛研究的概念)在异构图中仍未得到充分探索,尤其是在大规模异构图上,这带来了两个重大挑战:在存在异质性的情况下降低计算成本同时最大化有效信息利用,以及克服图神经网络中的过平滑问题。为解决这一空白,我们研究了不同元路径的重要性,并引入了一个用于在异构图上利用长程依赖的自动框架,称为通过渐进采样的长程元路径搜索(LMSPS)。具体而言,我们构建了一个包含与目标节点类型相关的所有元路径的搜索空间。通过采用渐进采样算法,LMSPS 以与跳数无关的时间复杂度动态缩小搜索空间。通过采样评估策略,LMSPS 进行专门且有效的元路径选择,从而仅使用有效的元路径进行重新训练,从而降低成本和过平滑问题。跨多个异构数据集的广泛实验验证了 LMSPS 在发现有效长程元路径方面的能力,超越了最先进的方法。我们的代码可在 https://github.com/JHL-HUST/LMSPS 获取。

英文摘要:

Utilizing long-range dependency, a concept extensively studied in homogeneous graphs, remains underexplored in heterogeneous graphs, especially on large ones, posing two significant challenges: Reducing computational costs while maximizing effective information utilization in the presence of heterogeneity, and overcoming the over-smoothing issue in graph neural networks. To address this gap, we investigate the importance of different meta-paths and introduce an automatic framework for utilizing long-range dependency on heterogeneous graphs, denoted as Long-range Meta-path Search through Progressive Sampling (LMSPS). Specifically, we develop a search space with all meta-paths related to the target node type. By employing a progressive sampling algorithm, LMSPS dynamically shrinks the search space with hop-independent time complexity. Through a sampling evaluation strategy, LMSPS conducts a specialized and effective meta-path selection, leading to retraining with only effective meta-paths, thus mitigating costs and over-smoothing. Extensive experiments across diverse heterogeneous datasets validate LMSPS's capability in discovering effective long-range meta-paths, surpassing state-of-the-art methods. Our code is available at https://github.com/JHL-HUST/LMSPS.

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。

↑