TMetaNet uses Dowker Zigzag Persistence features to adapt the learning rate of dynamic GNNs per snapshot, improving dynamic link prediction and noise robustness on six benchmarks.
Applications of Zigzag Persistence to Topological Data Analysis
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
The theory of zigzag persistence is a substantial extension of persistent homology, and its development has enabled the investigation of several unexplored avenues in the area of topological data analysis. In this paper, we discuss three applications of zigzag persistence: topological bootstrapping, parameter thresholding, and the comparison of witness complexes.
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
TMetaNet: Topological Meta-Learning Framework for Dynamic Link Prediction
TMetaNet uses Dowker Zigzag Persistence features to adapt the learning rate of dynamic GNNs per snapshot, improving dynamic link prediction and noise robustness on six benchmarks.