← Search

Astrit Tola

2 accepted papers

2026

TopoFormer: Topology Meets Attention for Graph Learning

ICLR 2026poster

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 token…

Cited by 0SourceScholar
2025

TopER: Topological Embeddings in Graph Representation Learning

NeurIPS 2025poster

Graph embeddings play a critical role in graph representation learning, allowing machine learning models to explore and interpret graph-structured data. However, existing methods often rely on opaque, high-dimensional embeddings, limiting interpretability and practical visualization. In this work,…

Cited by 0SourceScholar