We propose a heterogeneous graph mamba network (HGMN) as the first
exploration in leveraging the selective state space models (SSSMs) for
heterogeneous graph learning. Compared with the literature, our HGMN overcomes
two major challenges: (i) capturing long-range dependencies among heterogeneous
nodes and (ii) adapting SSSMs to heterogeneous graph data. Our key contribution
is a general graph architecture that can solve heterogeneous nodes in
real-world scenarios, followed an efficient flow. Methodologically, we
introduce a two-level efficient tokenization approach that first captures
long-range dependencies within identical node types, and subsequently across
all node types. Empirically, we conduct comparisons between our framework and
19 state-of-the-art methods on the heterogeneous benchmarks. The extensive
comparisons demonstrate that our framework outperforms other methods in both
the accuracy and efficiency dimensions.

我们提出了一种异构图曼巴网络 (HGMN)，它是利用选择性状态空间模型 (SSSMs) 进行异构图学习的首次探索。相比文献，我们的 HGMN 克服了两个主要挑战：(i) 捕捉异构节点之间的长程依赖和 (ii) 将 SSSMs 针对异构图数据进行适应。我们的主要贡献是提出了一个通用的图结构，可以解决现实场景中的异构节点，并进行高效的流程。在方法上，我们引入了一种两级高效的标记化方法，首先在相同节点类型内捕捉长程依赖，然后在所有节点类型之间进行捕捉。在实证方面，我们在异构基准测试上将我们的框架与其他 19 个最先进的方法进行了比较。广泛的比较表明，我们的框架在准确性和效率维度上表现优于其他方法。