Differentiable Random Partition Models

• URL: http://arxiv.org/abs/2305.16841v2
• Date: Wed, 8 Nov 2023 23:22:23 GMT
• Title: Differentiable Random Partition Models
• Authors: Thomas M. Sutter, Alain Ryser, Joram Liebeskind, Julia E. Vogt
• Abstract summary: We propose a novel two-step method for inferring partitions, which allows its usage in variational inference tasks. Our method works by inferring the number of elements per subset and, second, by filling these subsets in a learned order. We highlight the versatility of our general-purpose approach on three different challenging experiments.
• Score: 15.51229558339278
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Partitioning a set of elements into an unknown number of mutually exclusive subsets is essential in many machine learning problems. However, assigning elements, such as samples in a dataset or neurons in a network layer, to an unknown and discrete number of subsets is inherently non-differentiable, prohibiting end-to-end gradient-based optimization of parameters. We overcome this limitation by proposing a novel two-step method for inferring partitions, which allows its usage in variational inference tasks. This new approach enables reparameterized gradients with respect to the parameters of the new random partition model. Our method works by inferring the number of elements per subset and, second, by filling these subsets in a learned order. We highlight the versatility of our general-purpose approach on three different challenging experiments: variational clustering, inference of shared and independent generative factors under weak supervision, and multitask learning.

Related papers

• Enhancing Neural Subset Selection: Integrating Background Information into Set Representations [53.15923939406772]
  We show that when the target value is conditioned on both the input set and subset, it is essential to incorporate an textitinvariant sufficient statistic of the superset into the subset of interest. This ensures that the output value remains invariant to permutations of the subset and its corresponding superset, enabling identification of the specific superset from which the subset originated.
  arXiv  Detail & Related papers  (2024-02-05T16:09:35Z)
• High-dimensional variable clustering based on maxima of a weakly dependent random process [1.1999555634662633]
  We propose a new class of models for variable clustering called Asymptotic Independent block (AI-block) models. This class of models is identifiable, meaning that there exists a maximal element with a partial order between partitions, allowing for statistical inference. We also present an algorithm depending on a tuning parameter that recovers the clusters of variables without specifying the number of clusters empha priori.
  arXiv  Detail & Related papers  (2023-02-02T08:24:26Z)
• Equivariance with Learned Canonicalization Functions [77.32483958400282]
  We show that learning a small neural network to perform canonicalization is better than using predefineds. Our experiments show that learning the canonicalization function is competitive with existing techniques for learning equivariant functions across many tasks.
  arXiv  Detail & Related papers  (2022-11-11T21:58:15Z)
• An Additive Instance-Wise Approach to Multi-class Model Interpretation [53.87578024052922]
  Interpretable machine learning offers insights into what factors drive a certain prediction of a black-box system. Existing methods mainly focus on selecting explanatory input features, which follow either locally additive or instance-wise approaches. This work exploits the strengths of both methods and proposes a global framework for learning local explanations simultaneously for multiple target classes.
  arXiv  Detail & Related papers  (2022-07-07T06:50:27Z)
• Quantile-based fuzzy clustering of multivariate time series in the frequency domain [2.610470075814367]
  fuzzy C-means and fuzzy C-medoids algorithms are proposed. The performance of the proposed approach is evaluated in a broad simulation study. Two specific applications involving air quality and financial databases illustrate the usefulness of our approach.
  arXiv  Detail & Related papers  (2021-09-08T15:38:33Z)
• DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution [136.7261709896713]
  We propose a data-driven approach that generates the appropriate convolution kernels to apply in response to the nature of the instances. The proposed method achieves promising results on both ScanetNetV2 and S3DIS. It also improves inference speed by more than 25% over the current state-of-the-art.
  arXiv  Detail & Related papers  (2020-11-26T14:56:57Z)
• Multi-task Supervised Learning via Cross-learning [102.64082402388192]
  We consider a problem known as multi-task learning, consisting of fitting a set of regression functions intended for solving different tasks. In our novel formulation, we couple the parameters of these functions, so that they learn in their task specific domains while staying close to each other. This facilitates cross-fertilization in which data collected across different domains help improving the learning performance at each other task.
  arXiv  Detail & Related papers  (2020-10-24T21:35:57Z)
• Mixture Representation Learning with Coupled Autoencoders [1.589915930948668]
  We propose an unsupervised variational framework using multiple interacting networks called cpl-mixVAE. In this framework, the mixture representation of each network is regularized by imposing a consensus constraint on the discrete factor. We use the proposed method to jointly uncover discrete and continuous factors of variability describing gene expression in a single-cell transcriptomic dataset.
  arXiv  Detail & Related papers  (2020-07-20T04:12:04Z)
• Multi-view Orthonormalized Partial Least Squares: Regularizations and Deep Extensions [8.846165479467324]
  We establish a family of subspace-based learning method for multi-view learning using the least squares as the fundamental basis. We propose a unified multi-view learning framework to learn a classifier over a common latent space shared by all views.
  arXiv  Detail & Related papers  (2020-07-09T19:00:39Z)
• Differentiable Unsupervised Feature Selection based on a Gated Laplacian [7.970954821067042]
  We propose a differentiable loss function that combines the Laplacian score, which favors low-frequency features, with a gating mechanism for feature selection. We mathematically motivate the proposed approach and demonstrate that in the high noise regime, it is crucial to compute the Laplacian on the gated inputs, rather than on the full feature set.
  arXiv  Detail & Related papers  (2020-07-09T11:58:16Z)
• Set Based Stochastic Subsampling [85.5331107565578]
  We propose a set-based two-stage end-to-end neural subsampling model that is jointly optimized with an textitarbitrary downstream task network. We show that it outperforms the relevant baselines under low subsampling rates on a variety of tasks including image classification, image reconstruction, function reconstruction and few-shot classification.
  arXiv  Detail & Related papers  (2020-06-25T07:36:47Z)

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.