Topological Information Retrieval with Dilation-Invariant Bottleneck Comparative Measures
arXiv:2104.01672 · doi:10.1093/imaiai/iaad022
Abstract
Appropriately representing elements in a database so that queries may be accurately matched is a central task in information retrieval; recently, this has been achieved by embedding the graphical structure of the database into a manifold in a hierarchy-preserving manner using a variety of metrics. Persistent homology is a tool commonly used in topological data analysis that is able to rigorously characterize a database in terms of both its hierarchy and connectivity structure. Computing persistent homology on a variety of embedded datasets reveals that some commonly used embeddings fail to preserve the connectivity. We show that those embeddings which successfully retain the database topology coincide in persistent homology by introducing two dilation-invariant comparative measures to capture this effect: in particular, they address the issue of metric distortion on manifolds. We provide an algorithm for their computation that exhibits greatly reduced time complexity over existing methods. We use these measures to perform the first instance of topology-based information retrieval and demonstrate its increased performance over the standard bottleneck distance for persistent homology. We showcase our approach on databases of different data varieties including text, videos, and medical images.
arXiv comment29 pages, 10 figures, 4 tables
References in corpus (16)
- A roadmap for the computation of persistent homology
- Hierarchical structures of amorphous solids characterized by persistent homology
- MedMNIST Classification Decathlon: A Lightweight AutoML Benchmark for Medical Image Analysis
- Ripser: efficient computation of Vietoris-Rips persistence barcodes
- Deep Learning with Topological Signatures
- Predicting Clinical Outcomes in Glioblastoma: An Application of Topological and Functional Data Analysis
- Topology-Preserving Deep Image Segmentation
- Evasion Paths in Mobile Sensor Networks
- giotto-tda: A Topological Data Analysis Toolkit for Machine Learning and Data Exploration
- Continuous Hierarchical Representations with Poincaré Variational Auto-Encoders
- A Topology Layer for Machine Learning
- Keyphrase Generation for Scientific Document Retrieval
- Connectivity-Optimized Representation Learning via Persistent Homology
- Large Scale computation of Means and Clusters for Persistence Diagrams using Optimal Transport
- Approximating Persistent Homology for Large Datasets
- On the notion of weak isometry for finite metric spaces