← Back to all news
arXiv Machine Learning By Jennifer Rozenblit, Chenguang Yang, Yuxin Liu, Yuzhou Chen, Yulia Gel

Graph Representation via Elements of Discrete Morse and Cobordism Theories

Read the original on arXiv Machine Learning →

The paper proposes using concepts from low‑dimensional topology—specifically Morse theory and cobordism—to enhance graph diffusion models, introducing the MG‑Diff pipeline. It provides theoretical guarantees that the Morse‑theoretic guidance remains stable under small perturbations when a positive decision‑gap exists. The authors demonstrate the approach on spatio‑temporal graph forecasting and graph regeneration, suggesting broader potential for topology in machine learning.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Aug 20

Learning Topological Features of $\widehat Z$-invariants

arXiv:2608. 18570v1 Announce Type: cross Abstract: Machine learning and data analysis techniques have recently emerged as powerful tools for identifying patterns and formulating conjectures in mathematical research, most notably in the field of low-dimensional topology.

By Brandon Robinson, Shimal Harichurn, Fabian Ruehle, Sergei Gukov, Rak-Kyeong Seong, Miranda C. N. Cheng
safety
More like this →
arXiv AI
Jun 9

Topological Neural Operators

arXiv:2606. 09806v1 Announce Type: cross Abstract: We introduce Topological Neural Operators (TNOs), a principled framework for operator learning on cell complexes that lifts neural operators (NOs) from functions on points and/or edges to topological domains.

By Lennart Bastian, Samuel Leventhal, Mustafa Hajij, Tolga Birdal
benchmarks
More like this →
Hugging Face Trending Papers
Sep 8

Topology-induced Operators Reveal Complementary Graph Representations without Training

The paper demonstrates that high‑quality graph embeddings can be produced without complex models or training by propagating random features through topological structures derived from random walks and anonymous walks. These training‑free embeddings capture node proximity and structural roles, respectively, and perform competitively on node, edge, and graph tasks while often requiring less computation. Combining the two embedding types further improves inference quality for some tasks.

rag
More like this →
arXiv Machine Learning
Sep 3

From topology learning to graph generation: A unifying perspective

The article reviews the problem of learning graph structures from data, noting that research has traditionally split into two paths: inferring the topology of a single graph from observations on it, and learning a generative distribution from multiple observed graphs to sample new ones. It proposes a unified framework that treats both as inverse problems of a common graph generation process, reviews key methods, and discusses their interrelations, strengths, and limitations. The review highlights opportunities for cross‑paradigm integration and outlines future research directions.

By Xiaowen Dong, Hoi-To Wai, Siheng Chen, Laura Toni, Dorina Thanou
More like this →