Structure by Architecture: Structured Representations without Regularization

• URL: http://arxiv.org/abs/2006.07796v4
• Date: Thu, 15 Feb 2024 14:34:20 GMT
• Title: Structure by Architecture: Structured Representations without Regularization
• Authors: Felix Leeb, Guilia Lanzillotta, Yashas Annadani, Michel Besserve, Stefan Bauer, Bernhard Sch\"olkopf
• Abstract summary: We study the problem of self-supervised structured representation learning using autoencoders for downstream tasks such as generative modeling. We design a novel autoencoder architecture capable of learning a structured representation without the need for aggressive regularization. We demonstrate how these models learn a representation that improves results in a variety of downstream tasks including generation, disentanglement, and extrapolation.
• Score: 31.75200752252397
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We study the problem of self-supervised structured representation learning using autoencoders for downstream tasks such as generative modeling. Unlike most methods which rely on matching an arbitrary, relatively unstructured, prior distribution for sampling, we propose a sampling technique that relies solely on the independence of latent variables, thereby avoiding the trade-off between reconstruction quality and generative performance typically observed in VAEs. We design a novel autoencoder architecture capable of learning a structured representation without the need for aggressive regularization. Our structural decoders learn a hierarchy of latent variables, thereby ordering the information without any additional regularization or supervision. We demonstrate how these models learn a representation that improves results in a variety of downstream tasks including generation, disentanglement, and extrapolation using several challenging and natural image datasets.

Related papers

• Enhancing Representations through Heterogeneous Self-Supervised Learning [61.40674648939691]
  We propose Heterogeneous Self-Supervised Learning (HSSL), which enforces a base model to learn from an auxiliary head whose architecture is heterogeneous from the base model. The HSSL endows the base model with new characteristics in a representation learning way without structural changes. The HSSL is compatible with various self-supervised methods, achieving superior performances on various downstream tasks.
  arXiv  Detail & Related papers  (2023-10-08T10:44:05Z)
• Unbiased Learning of Deep Generative Models with Structured Discrete Representations [7.9057320008285945]
  We propose novel algorithms for learning structured variational autoencoders (SVAEs) We are the first to demonstrate the SVAE's ability to handle multimodal uncertainty when data is missing by incorporating discrete latent variables. Our memory-efficient implicit differentiation scheme makes the SVAE tractable to learn via gradient descent, while demonstrating robustness to incomplete optimization.
  arXiv  Detail & Related papers  (2023-06-14T03:59:21Z)
• Disentanglement via Latent Quantization [60.37109712033694]
  In this work, we construct an inductive bias towards encoding to and decoding from an organized latent space. We demonstrate the broad applicability of this approach by adding it to both basic data-re (vanilla autoencoder) and latent-reconstructing (InfoGAN) generative models.
  arXiv  Detail & Related papers  (2023-05-28T06:30:29Z)
• DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusion [66.21290235237808]
  We introduce an energy constrained diffusion model which encodes a batch of instances from a dataset into evolutionary states. We provide rigorous theory that implies closed-form optimal estimates for the pairwise diffusion strength among arbitrary instance pairs. Experiments highlight the wide applicability of our model as a general-purpose encoder backbone with superior performance in various tasks.
  arXiv  Detail & Related papers  (2023-01-23T15:18:54Z)
• Autoregressive Structured Prediction with Language Models [73.11519625765301]
  We describe an approach to model structures as sequences of actions in an autoregressive manner with PLMs. Our approach achieves the new state-of-the-art on all the structured prediction tasks we looked at.
  arXiv  Detail & Related papers  (2022-10-26T13:27:26Z)
• Understanding Dynamics of Nonlinear Representation Learning and Its Application [12.697842097171119]
  We study the dynamics of implicit nonlinear representation learning. We show that the data-architecture alignment condition is sufficient for the global convergence. We derive a new training framework, which satisfies the data-architecture alignment condition without assuming it.
  arXiv  Detail & Related papers  (2021-06-28T16:31:30Z)
• Redefining Neural Architecture Search of Heterogeneous Multi-Network Models by Characterizing Variation Operators and Model Components [71.03032589756434]
  We investigate the effect of different variation operators in a complex domain, that of multi-network heterogeneous neural models. We characterize both the variation operators, according to their effect on the complexity and performance of the model; and the models, relying on diverse metrics which estimate the quality of the different parts composing it.
  arXiv  Detail & Related papers  (2021-06-16T17:12:26Z)
• SetVAE: Learning Hierarchical Composition for Generative Modeling of Set-Structured Data [27.274328701618]
  We propose SetVAE, a hierarchical variational autoencoder for sets. Motivated by recent progress in set encoding, we build SetVAE upon attentive modules that first partition the set and project the partition back to the original cardinality. We demonstrate that our model generalizes to unseen set sizes and learns interesting subset relations without supervision.
  arXiv  Detail & Related papers  (2021-03-29T14:01:18Z)
• MOGAN: Morphologic-structure-aware Generative Learning from a Single Image [59.59698650663925]
  Recently proposed generative models complete training based on only one image. We introduce a MOrphologic-structure-aware Generative Adversarial Network named MOGAN that produces random samples with diverse appearances. Our approach focuses on internal features including the maintenance of rational structures and variation on appearance.
  arXiv  Detail & Related papers  (2021-03-04T12:45:23Z)
• Learning Structured Latent Factors from Dependent Data:A Generative Model Framework from Information-Theoretic Perspective [18.88255368184596]
  We present a novel framework for learning generative models with various underlying structures in the latent space. Our model provides a principled approach to learn a set of semantically meaningful latent factors that reflect various types of desired structures.
  arXiv  Detail & Related papers  (2020-07-21T06:59:29Z)

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.