Disentangled Representation Learning with the Gromov-Monge Gap

• URL: http://arxiv.org/abs/2407.07829v2
• Date: Thu, 24 Oct 2024 16:49:16 GMT
• Title: Disentangled Representation Learning with the Gromov-Monge Gap
• Authors: Théo Uscidda, Luca Eyring, Karsten Roth, Fabian Theis, Zeynep Akata, Marco Cuturi,
• Abstract summary: Learning disentangled representations from unlabelled data is a fundamental challenge in machine learning. We introduce a novel approach to disentangled representation learning based on quadratic optimal transport. We demonstrate the effectiveness of our approach for quantifying disentanglement across four standard benchmarks.
• Score: 65.73194652234848
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Learning disentangled representations from unlabelled data is a fundamental challenge in machine learning. Solving it may unlock other problems, such as generalization, interpretability, or fairness. Although remarkably challenging to solve in theory, disentanglement is often achieved in practice through prior matching. Furthermore, recent works have shown that prior matching approaches can be enhanced by leveraging geometrical considerations, e.g., by learning representations that preserve geometric features of the data, such as distances or angles between points. However, matching the prior while preserving geometric features is challenging, as a mapping that fully preserves these features while aligning the data distribution with the prior does not exist in general. To address these challenges, we introduce a novel approach to disentangled representation learning based on quadratic optimal transport. We formulate the problem using Gromov-Monge maps that transport one distribution onto another with minimal distortion of predefined geometric features, preserving them as much as can be achieved. To compute such maps, we propose the Gromov-Monge-Gap (GMG), a regularizer quantifying whether a map moves a reference distribution with minimal geometry distortion. We demonstrate the effectiveness of our approach for disentanglement across four standard benchmarks, outperforming other methods leveraging geometric considerations.

Related papers

• Geometrically Aligned Transfer Encoder for Inductive Transfer in Regression Tasks [5.038936775643437]
  We propose a novel transfer technique based on differential geometry, namely the Geometrically Aligned Transfer (GATE) We find a proper diffeomorphism between pairs of tasks to ensure that every arbitrary point maps to a locally flat coordinate in the overlapping region, allowing the transfer of knowledge from the source to the target data. GATE outperforms conventional methods and exhibits stable behavior in both the latent space and extrapolation regions for various molecular graph datasets.
  arXiv  Detail & Related papers  (2023-10-10T07:11:25Z)
• Joint graph learning from Gaussian observations in the presence of hidden nodes [26.133725549667734]
  We propose a joint graph learning method that takes into account the presence of hidden (latent) variables. We exploit the structure resulting from the previous considerations to propose a convex optimization problem. We compare the proposed algorithm with different baselines and evaluate its performance over synthetic and real-world graphs.
  arXiv  Detail & Related papers  (2022-12-04T13:03:41Z)
• Unveiling the Sampling Density in Non-Uniform Geometric Graphs [69.93864101024639]
  We consider graphs as geometric graphs: nodes are randomly sampled from an underlying metric space, and any pair of nodes is connected if their distance is less than a specified neighborhood radius. In a social network communities can be modeled as densely sampled areas, and hubs as nodes with larger neighborhood radius. We develop methods to estimate the unknown sampling density in a self-supervised fashion.
  arXiv  Detail & Related papers  (2022-10-15T08:01:08Z)
• Geometry Contrastive Learning on Heterogeneous Graphs [50.58523799455101]
  This paper proposes a novel self-supervised learning method, termed as Geometry Contrastive Learning (GCL) GCL views a heterogeneous graph from Euclidean and hyperbolic perspective simultaneously, aiming to make a strong merger of the ability of modeling rich semantics and complex structures. Extensive experiments on four benchmarks data sets show that the proposed approach outperforms the strong baselines.
  arXiv  Detail & Related papers  (2022-06-25T03:54:53Z)
• Semi-supervised Dense Keypoints Using Unlabeled Multiview Images [22.449168666514677]
  This paper presents a new end-to-end semi-supervised framework to learn a dense keypoint detector using unlabeled multiview images. A key challenge lies in finding the exact correspondences between the dense keypoints in multiple views. We derive a new probabilistic epipolar constraint that encodes the two desired properties.
  arXiv  Detail & Related papers  (2021-09-20T04:57:57Z)
• Finding Geometric Models by Clustering in the Consensus Space [61.65661010039768]
  We propose a new algorithm for finding an unknown number of geometric models, e.g., homographies. We present a number of applications where the use of multiple geometric models improves accuracy. These include pose estimation from multiple generalized homographies; trajectory estimation of fast-moving objects.
  arXiv  Detail & Related papers  (2021-03-25T14:35:07Z)
• Making Affine Correspondences Work in Camera Geometry Computation [62.7633180470428]
  Local features provide region-to-region rather than point-to-point correspondences. We propose guidelines for effective use of region-to-region matches in the course of a full model estimation pipeline. Experiments show that affine solvers can achieve accuracy comparable to point-based solvers at faster run-times.
  arXiv  Detail & Related papers  (2020-07-20T12:07:48Z)
• Spatial Pyramid Based Graph Reasoning for Semantic Segmentation [67.47159595239798]
  We apply graph convolution into the semantic segmentation task and propose an improved Laplacian. The graph reasoning is directly performed in the original feature space organized as a spatial pyramid. We achieve comparable performance with advantages in computational and memory overhead.
  arXiv  Detail & Related papers  (2020-03-23T12:28:07Z)
• Learning Flat Latent Manifolds with VAEs [16.725880610265378]
  We propose an extension to the framework of variational auto-encoders, where the Euclidean metric is a proxy for the similarity between data points. We replace the compact prior typically used in variational auto-encoders with a recently presented, more expressive hierarchical one. We evaluate our method on a range of data-sets, including a video-tracking benchmark.
  arXiv  Detail & Related papers  (2020-02-12T09:54:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.