Deep Learning with Topological Signatures

Abstract

Inferring topological and geometrical information from data can offer an alternative perspective on machine learning problems. Methods from topological data analysis, e.g., persistent homology, enable us to obtain such information, typically in the form of summary representations of topological features. However, such topological signatures often come with an unusual structure (e.g., multisets of intervals) that is highly impractical for most machine learning techniques. While many strategies have been proposed to map these topological signatures into machine learning compatible representations, they suffer from being agnostic to the target learning task. In contrast, we propose a technique that enables us to input topological signatures to deep neural networks and learn a task-optimal representation during training. Our approach is realized as a novel input layer with favorable theoretical properties. Classification experiments on 2D object shapes and social network graphs demonstrate the versatility of the approach and, in case of the latter, we even outperform the state-of-the-art by a large margin.

References in corpus (2)

• Learning Convolutional Neural Networks for Graphs
• Persistence weighted Gaussian kernel for topological data analysis

Cited by in corpus (19)

• Graph Kernels: State-of-the-Art and Future Challenges
• Edit Distance and Persistence Diagrams Over Lattices
• Tracking collective cell motion by topological data analysis
• Tropical Sufficient Statistics for Persistent Homology
• Mixing autoencoder with classifier: conceptual data visualization
• Path homologies of deep feedforward networks
• Knowledge gaps in the early growth of semantic networks
• TopoTxR: A topology-guided deep convolutional network for breast parenchyma learning on DCE-MRIs
• Elder-Rule-Staircodes for Augmented Metric Spaces
• Vietoris-Rips Complexes of Regular Polygons
• Fuzzy c-Means Clustering for Persistence Diagrams
• NIPS - Not Even Wrong? A Systematic Review of Empirically Complete Demonstrations of Algorithmic Effectiveness in the Machine Learning and Artificial Intelligence Literature
• Markov-Lipschitz Deep Learning
• Image analysis for Alzheimer's disease prediction: Embracing pathological hallmarks for model architecture design
• Topological Information Retrieval with Dilation-Invariant Bottleneck Comparative Measures
• ATOL: Measure Vectorization for Automatic Topologically-Oriented Learning
• Topological Machine Learning for Mixed Numeric and Categorical Data
• Smart Vectorizations for Single and Multiparameter Persistence
• Shapley Homology: Topological Analysis of Sample Influence for Neural Networks