Towards Optimal Transport with Global Invariances

Abstract

Many problems in machine learning involve calculating correspondences between sets of objects, such as point clouds or images. Discrete optimal transport provides a natural and successful approach to such tasks whenever the two sets of objects can be represented in the same space, or at least distances between them can be directly evaluated. Unfortunately neither requirement is likely to hold when object representations are learned from data. Indeed, automatically derived representations such as word embeddings are typically fixed only up to some global transformations, for example, reflection or rotation. As a result, pairwise distances across two such instances are ill-defined without specifying their relative transformation. In this work, we propose a general framework for optimal transport in the presence of latent global transformations. We cast the problem as a joint optimization over transport couplings and transformations chosen from a flexible class of invariances, propose algorithms to solve it, and show promising results in various tasks, including a popular unsupervised word translation benchmark.

arXiv commentAISTATS 2019

Cited by in corpus (19)

• Bilingual Lexicon Induction through Unsupervised Machine Translation
• The Unbalanced Gromov Wasserstein Distance: Conic Formulation and Relaxation
• Sliced Gromov-Wasserstein
• Generalized Spectral Clustering via Gromov-Wasserstein Learning
• Time Series Alignment with Global Invariances
• Personalised Federated Learning On Heterogeneous Feature Spaces
• Nonparametric two-sample hypothesis testing for low-rank random graphs of differing sizes
• Are Girls Neko or Shōjo? Cross-Lingual Alignment of Non-Isomorphic Embeddings with Iterative Normalization
• Making transport more robust and interpretable by moving data through a small number of anchor points
• Cross-Domain Imitation Learning via Optimal Transport
• Variational Wasserstein Barycenters for Geometric Clustering
• CO-Optimal Transport
• Unsupervised Hierarchy Matching with Optimal Transport over Hyperbolic Spaces
• Learning transport cost from subset correspondence
• Equitable and Optimal Transport with Multiple Agents
• Order Constraints in Optimal Transport
• Beyond Offline Mapping: Learning Cross Lingual Word Embeddings through Context Anchoring
• Using Optimal Transport as Alignment Objective for fine-tuning Multilingual Contextualized Embeddings
• Valid Two-Sample Graph Testing via Optimal Transport Procrustes and Multiscale Graph Correlation with Applications in Connectomics