Utilizing long-range dependency, though extensively studied in homogeneous graphs, is rarely studied in large-scale heterogeneous information networks (HINs), whose main challenge is the high costs and the difficulty in utilizing effective information. To this end, we investigate the importance of different meta-paths and propose an automatic framework for utilizing long-range dependency in HINs, called Long-range Meta-path Search through Progressive Sampling (LMSPS). Specifically, to discover meta-paths for various datasets or tasks without prior, we develop a search space with all target-node-related meta-paths. With a progressive sampling algorithm, we dynamically shrink the search space with hop-independent time complexity, leading to a compact search space driven by the current HIN and task. Utilizing a sampling evaluation strategy as the guidance, we conduct a specialized and expressive meta-path selection. Extensive experiments on eight heterogeneous datasets demonstrate that LMSPS discovers effective long-range meta-paths and outperforms state-of-the-art models. Besides, it ranks top-1 on the leaderboards of ogbn-mag in Open Graph Benchmark.

翻译：利用长距离依赖关系，虽在同质图中已得到广泛研究，但在大规模异构信息网络（HIN）中却鲜有探索，其主要挑战在于高昂的代价以及难以有效利用信息。为此，我们研究了不同元路径的重要性，并提出了一种在HIN中利用长距离依赖关系的自动化框架，称为通过渐进采样的长距离元路径搜索（LMSPS）。具体而言，为了在无先验知识的情况下发现适用于各种数据集或任务的元路径，我们构建了一个包含所有目标节点相关元路径的搜索空间。通过渐进采样算法，我们动态缩小搜索空间，其时间复杂度与跳数无关，从而得到一个由当前HIN和任务驱动的紧凑搜索空间。以采样评估策略为指导，我们进行专业且富有表现力的元路径选择。在八个异构数据集上的大量实验表明，LMSPS能够发现有效的长距离元路径，并优于当前最先进的模型。此外，它在开放图基准测试（Open Graph Benchmark）的ogbn-mag排行榜上排名第一。