Yangyang Li, Tianyong Hao, Chaoqun Fei, Huanjiang Liu, Tinglve Zhou
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Introduces a novel and computationally efficient curvature flow based on effective resistance from circuit theory, establishing a new paradigm for geometric graph structure evolution. • Formulates the dynamic evolution equation of RCF, elucidates its mechanisms for manifold enhancement and noise suppression, and highlights its differentiability and compatibility with deep learning frameworks. • Proposes an efficient Dynamic Graph Structure Learning method based on RCF. Extensive experiments on deep metric learning, manifold learning and graph structure learning tasks demonstrate that DGSL-RCF consistently improves representation quality and downstream performance with low runtime cost.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2601.08149")
get_code_for_paper("2601.08149")
have("2601.08149")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2601.08149.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2601.08149)
Connect an agent — have() is free.