提出GRAMA模型，让图神经网络更好捕捉长距离依赖。
GRAMA: Adaptive Graph Autoregressive Moving Average Models
- 基于可学习ARMA框架，动态调整图数据传播方式。
- 在14个数据集上优于基线模型，表现接近顶尖方法。
- 适合需要长程建模的图学习任务，如社交网络分析。
图状态空间模型（SSMs）近期被引入以增强图神经网络（GNNs）对长程交互的建模能力。尽管取得成功，现有方法或牺牲置换等变性，或仅关注成对交互而非序列建模。本文基于自回归移动平均（ARMA）与SSM之间的联系，提出GRAMA——一种基于可学习ARMA框架的图自适应方法，解决了上述限制。通过将静态图数据转换为序列形式，GRAMA利用ARMA框架优势，同时保持置换等变性。此外，引入选择性注意力机制，实现对ARMA系数的动态学习，提升长程信息传播效率。我们还建立了GRAMA与选择性SSMs之间的理论联系，揭示其捕捉长程依赖的能力。在14个合成与真实世界数据集上的大量实验表明，GRAMA始终优于基线模型，且性能媲美当前最优方法。
原文摘要 · Abstract (English)
Graph State Space Models (SSMs) have recently been introduced to enhance Graph Neural Networks (GNNs) in modeling long-range interactions. Despite their success, existing methods either compromise on permutation equivariance or limit their focus to pairwise interactions rather than sequences. Building on the connection between Autoregressive Moving Average (ARMA) and SSM, in this paper, we introduce GRAMA, a Graph Adaptive method based on a learnable Autoregressive Moving Average (ARMA) framework that addresses these limitations. By transforming from static to sequential graph data, GRAMA leverages the strengths of the ARMA framework, while preserving permutation equivariance. Moreover, GRAMA incorporates a selective attention mechanism for dynamic learning of ARMA coefficients, enabling efficient and flexible long-range information propagation. We also establish theoretical connections between GRAMA and Selective SSMs, providing insights into its ability to capture long-range dependencies. Extensive experiments on 14 synthetic and real-world datasets demonstrate that GRAMA consistently outperforms backbone models and performs competitively with state-of-the-art methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。