AI 中文总结
该研究提出TopoFormer框架，通过核心模块Topo-Scan将图拓扑结构编码为注意力友好序列，结合Transformer实现图表示学习，在相关基准上达到SOTA性能，开辟了拓扑与注意力融合的图学习新方向。
AI 中文摘要
我们提出TopoFormer，这是一种轻量且可扩展的图表示学习框架，可将拓扑结构编码为适合注意力机制处理的序列。该方法的核心是Topo-Scan，这是一种新型模块，通过对节点或边的滤波进行切片，将图分解为短而有序的拓扑标记序列。这些序列捕捉从局部 motif 到全局组织的多尺度结构模式，经Transformer处理后生成具有强表达能力的图级嵌入。与传统持久同伦流程不同，Topo-Scan可并行化，避免了代价高昂的图计算，且能与标准深度学习架构无缝集成。我们为拓扑编码的稳定性提供了理论保证，并在图分类和分子性质预测基准上展示了SOTA性能。结果表明，TopoFormer在匹配或超越强大GNN及基于拓扑的基线的同时，还具备可预测且高效的计算特性。该研究为将拓扑归纳偏置融入注意力框架的并行化、统一化图表示学习方法开辟了新路径。
英文摘要
We introduce Topoformer, a lightweight and scalable framework for graph representation learning that encodes topological structure into attention-friendly sequences. At the core of our method is Topo-Scan, a novel module that decomposes a graph into a short, ordered sequence of topological tokens by slicing over node or edge filtrations. These sequences capture multi-scale structural patterns, from local motifs to global organization, and are processed by a Transformer to produce expressive graph-level embeddings. Unlike traditional persistent homology pipelines, Topo-Scan is parallelizable, avoids costly diagram computations, and integrates seamlessly with standard deep learning architectures. We provide theoretical guarantees on the stability of our topological encodings and demonstrate state-of-the-art performance across graph classification and molecular property prediction benchmarks. Our results show that Topoformer matches or exceeds strong GNN and topology-based baselines while offering predictable and efficient compute. This work opens a new path for parallelizable and unifying approaches to graph representation learning that integrate topological inductive biases into attention frameworks.
Comments26 pages, 5 figures
Journal refICLR 2026
