Diffusion Transport Alignment

• URL: http://arxiv.org/abs/2206.07305v1
• Date: Wed, 15 Jun 2022 05:25:06 GMT
• Title: Diffusion Transport Alignment
• Authors: Andres F. Duque, Guy Wolf, Kevin R. Moon
• Abstract summary: Many existing data integration methods assume a known one-to-one correspondence between domains of the entire dataset. We propose a semi-supervised manifold alignment method that exploits prior correspondence knowledge between only a few points to align the domains. We empirically demonstrate that DTA outperforms other methods in aligning multimodal data in this semisupervised setting.
• Score: 10.949343817897455
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The integration of multimodal data presents a challenge in cases when the study of a given phenomena by different instruments or conditions generates distinct but related domains. Many existing data integration methods assume a known one-to-one correspondence between domains of the entire dataset, which may be unrealistic. Furthermore, existing manifold alignment methods are not suited for cases where the data contains domain-specific regions, i.e., there is not a counterpart for a certain portion of the data in the other domain. We propose Diffusion Transport Alignment (DTA), a semi-supervised manifold alignment method that exploits prior correspondence knowledge between only a few points to align the domains. By building a diffusion process, DTA finds a transportation plan between data measured from two heterogeneous domains with different feature spaces, which by assumption, share a similar geometrical structure coming from the same underlying data generating process. DTA can also compute a partial alignment in a data-driven fashion, resulting in accurate alignments when some data are measured in only one domain. We empirically demonstrate that DTA outperforms other methods in aligning multimodal data in this semisupervised setting. We also empirically show that the alignment obtained by DTA can improve the performance of machine learning tasks, such as domain adaptation, inter-domain feature mapping, and exploratory data analysis, while outperforming competing methods.

Related papers

• Graph Integration for Diffusion-Based Manifold Alignment [0.0]
  Multimodal data integration can enrich information content compared to single-source data. Manifold alignment is a form of data integration that seeks a shared, underlying low-dimensional representation of multiple data sources. In this paper, we introduce two semi-supervised manifold alignment methods.
  arXiv  Detail & Related papers  (2024-10-30T12:43:44Z)
• Compositional Semantic Mix for Domain Adaptation in Point Cloud Segmentation [65.78246406460305]
  compositional semantic mixing represents the first unsupervised domain adaptation technique for point cloud segmentation. We present a two-branch symmetric network architecture capable of concurrently processing point clouds from a source domain (e.g. synthetic) and point clouds from a target domain (e.g. real-world)
  arXiv  Detail & Related papers  (2023-08-28T14:43:36Z)
• SALUDA: Surface-based Automotive Lidar Unsupervised Domain Adaptation [62.889835139583965]
  We introduce an unsupervised auxiliary task of learning an implicit underlying surface representation simultaneously on source and target data. As both domains share the same latent representation, the model is forced to accommodate discrepancies between the two sources of data. Our experiments demonstrate that our method achieves a better performance than the current state of the art, both in real-to-real and synthetic-to-real scenarios.
  arXiv  Detail & Related papers  (2023-04-06T17:36:23Z)
• Manifold Alignment with Label Information [9.742277703732187]
  MALI (Manifold alignment with label information) learns a correspondence between two distinct domains. We show that MALI outperforms the current state-of-the-art manifold alignment methods across multiple datasets.
  arXiv  Detail & Related papers  (2022-10-23T16:32:29Z)
• Unsupervised Manifold Alignment with Joint Multidimensional Scaling [4.683612295430957]
  We introduce Joint Multidimensional Scaling, which maps datasets from two different domains to a common low-dimensional Euclidean space. Our approach integrates Multidimensional Scaling (MDS) and Wasserstein Procrustes analysis into a joint optimization problem. We demonstrate the effectiveness of our approach in several applications, including joint visualization of two datasets, unsupervised heterogeneous domain adaptation, graph matching, and protein structure alignment.
  arXiv  Detail & Related papers  (2022-07-06T21:02:42Z)
• Instrumental Variable-Driven Domain Generalization with Unobserved Confounders [53.735614014067394]
  Domain generalization (DG) aims to learn from multiple source domains a model that can generalize well on unseen target domains. We propose an instrumental variable-driven DG method (IV-DG) by removing the bias of the unobserved confounders with two-stage learning. In the first stage, it learns the conditional distribution of the input features of one domain given input features of another domain. In the second stage, it estimates the relationship by predicting labels with the learned conditional distribution.
  arXiv  Detail & Related papers  (2021-10-04T13:32:57Z)
• Vector-Decomposed Disentanglement for Domain-Invariant Object Detection [75.64299762397268]
  We try to disentangle domain-invariant representations from domain-specific representations. In the experiment, we evaluate our method on the single- and compound-target case.
  arXiv  Detail & Related papers  (2021-08-15T07:58:59Z)
• Manifold Partition Discriminant Analysis [42.11470531267327]
  We propose a novel algorithm for supervised dimensionality reduction named Manifold Partition Discriminant Analysis (MPDA) It aims to find a linear embedding space where the within-class similarity is achieved along the direction that is consistent with the local variation of the data manifold. MPDA explicitly parameterizes the connections of tangent spaces and represents the data manifold in a piecewise manner.
  arXiv  Detail & Related papers  (2020-11-23T16:33:23Z)
• Learning to Combine: Knowledge Aggregation for Multi-Source Domain Adaptation [56.694330303488435]
  We propose a Learning to Combine for Multi-Source Domain Adaptation (LtC-MSDA) framework. In the nutshell, a knowledge graph is constructed on the prototypes of various domains to realize the information propagation among semantically adjacent representations. Our approach outperforms existing methods with a remarkable margin.
  arXiv  Detail & Related papers  (2020-07-17T07:52:44Z)
• Unified Multi-Domain Learning and Data Imputation using Adversarial Autoencoder [5.933303832684138]
  We present a novel framework that can combine multi-domain learning (MDL), data imputation (DI) and multi-task learning (MTL) The core of our method is an adversarial autoencoder that can: (1) learn to produce domain-invariant embeddings to reduce the difference between domains; (2) learn the data distribution for each domain and correctly perform data imputation on missing data.
  arXiv  Detail & Related papers  (2020-03-15T19:55:07Z)
• Multi-source Domain Adaptation for Visual Sentiment Classification [92.53780541232773]
  We propose a novel multi-source domain adaptation (MDA) method, termed Multi-source Sentiment Generative Adversarial Network (MSGAN) To handle data from multiple source domains, MSGAN learns to find a unified sentiment latent space where data from both the source and target domains share a similar distribution. Extensive experiments conducted on four benchmark datasets demonstrate that MSGAN significantly outperforms the state-of-the-art MDA approaches for visual sentiment classification.
  arXiv  Detail & Related papers  (2020-01-12T08:37:42Z)

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.