From abstract items to latent spaces to observed data and back: Compositional Variational Auto-Encoder - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2020

From abstract items to latent spaces to observed data and back: Compositional Variational Auto-Encoder

Victor Berger
Michèle Sebag
  • Function : Author
  • PersonId : 836537

Abstract

Conditional Generative Models are now acknowledged an essential tool in Machine Learning. This paper focuses on their control. While many approaches aim at disentangling the data through the coordinate-wise control of their latent representations, another direction is explored in this paper. The proposed CompVAE handles data with a natural multi-ensemblist structure (i.e. that can naturally be decomposed into elements). Derived from Bayesian variational principles, CompVAE learns a latent representation leveraging both observational and symbolic information. A first contribution of the approach is that this latent representation supports a compositional generative model, amenable to multi-ensemblist operations (addition or subtraction of elements in the composition). This compositional ability is enabled by the invariance and generality of the whole framework w.r.t. respectively, the order and number of the elements. The second contribution of the paper is a proof of concept on synthetic 1D and 2D problems, demonstrating the efficiency of the proposed approach.
Fichier principal
Vignette du fichier
main.pdf (952.41 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-02431955 , version 1 (21-01-2020)

Identifiers

Cite

Victor Berger, Michèle Sebag. From abstract items to latent spaces to observed data and back: Compositional Variational Auto-Encoder. ECML PKDD 2019 - European Conference on Machine learning and knowledge discovery in databases, Sep 2019, Würzburg, Germany. pp.274-289, ⟨10.1007/978-3-030-46150-8_17⟩. ⟨hal-02431955⟩
110 View
134 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More