Intervening to learn and compose disentangled representations

• URL: http://arxiv.org/abs/2507.04754v1
• Date: Mon, 07 Jul 2025 08:30:27 GMT
• Title: Intervening to learn and compose disentangled representations
• Authors: Alex Markham, Jeri A. Chang, Isaac Hirsch, Liam Solus, Bryon Aragam,
• Abstract summary: We propose a new approach to training arbitrarily expressive generative models that simultaneously learn disentangled latent structure.<n>This is accomplished by adding a simple decoder-only module to the head of an existing decoder block that can be arbitrarily complex.<n>Inspired by the notion of intervention in causal graphical models, our module selectively modifies its architecture during training, allowing it to learn a compact joint model over different contexts.
• Score: 8.452837716541705
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: In designing generative models, it is commonly believed that in order to learn useful latent structure, we face a fundamental tension between expressivity and structure. In this paper we challenge this view by proposing a new approach to training arbitrarily expressive generative models that simultaneously learn disentangled latent structure. This is accomplished by adding a simple decoder-only module to the head of an existing decoder block that can be arbitrarily complex. The module learns to process concept information by implicitly inverting linear representations from an encoder. Inspired by the notion of intervention in causal graphical models, our module selectively modifies its architecture during training, allowing it to learn a compact joint model over different contexts. We show how adding this module leads to disentangled representations that can be composed for out-of-distribution generation. To further validate our proposed approach, we prove a new identifiability result that extends existing work on identifying structured representations in nonlinear models.

Related papers

• Growing Transformers: Modular Composition and Layer-wise Expansion on a Frozen Substrate [0.0]
  This paper explores an alternative, constructive approach to model development, built upon the foundation of non-trainable, deterministic input embeddings.<n>We show that specialist models trained on disparate datasets can be merged into a single, more capable Mixture-of-Experts model.<n>We introduce a layer-wise constructive training methodology, where a deep Transformer is "grown" by progressively stacking and training one layer at a time.
  arXiv  Detail & Related papers  (2025-07-08T20:01:15Z)
• Mining Frequent Structures in Conceptual Models [2.625701175074974]
  We propose a general approach to the problem of discovering frequent structures in conceptual models.<n>We implement our approach by focusing on two widely-used conceptual modeling languages.<n>This tool can be used to identify both effective and ineffective modeling practices.
  arXiv  Detail & Related papers  (2024-06-11T10:24:02Z)
• A Recursive Bateson-Inspired Model for the Generation of Semantic Formal Concepts from Spatial Sensory Data [77.34726150561087]
  This paper presents a new symbolic-only method for the generation of hierarchical concept structures from complex sensory data. The approach is based on Bateson's notion of difference as the key to the genesis of an idea or a concept. The model is able to produce fairly rich yet human-readable conceptual representations without training.
  arXiv  Detail & Related papers  (2023-07-16T15:59:13Z)
• A Deep Unrolling Model with Hybrid Optimization Structure for Hyperspectral Image Deconvolution [50.13564338607482]
  We propose a novel optimization framework for the hyperspectral deconvolution problem, called DeepMix.<n>It consists of three distinct modules, namely, a data consistency module, a module that enforces the effect of the handcrafted regularizers, and a denoising module.<n>This work proposes a context aware denoising module designed to sustain the advancements achieved by the cooperative efforts of the other modules.
  arXiv  Detail & Related papers  (2023-06-10T08:25:16Z)
• 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)
• Modular Deep Learning [120.36599591042908]
  Transfer learning has recently become the dominant paradigm of machine learning. It remains unclear how to develop models that specialise towards multiple tasks without incurring negative interference. Modular deep learning has emerged as a promising solution to these challenges.
  arXiv  Detail & Related papers  (2023-02-22T18:11:25Z)
• Internal Representations of Vision Models Through the Lens of Frames on Data Manifolds [8.67467876089153]
  We present a new approach to studying such representations inspired by the idea of a frame on the tangent bundle of a manifold. Our construction, which we call a neural frame, is formed by assembling a set of vectors representing specific types of perturbations of a data point. Using neural frames, we make observations about the way that models process, layer-by-layer, specific modes of variation within a small neighborhood of a datapoint.
  arXiv  Detail & Related papers  (2022-11-19T01:48:19Z)
• Dynamic Latent Separation for Deep Learning [67.62190501599176]
  A core problem in machine learning is to learn expressive latent variables for model prediction on complex data. Here, we develop an approach that improves expressiveness, provides partial interpretation, and is not restricted to specific applications.
  arXiv  Detail & Related papers  (2022-10-07T17:56:53Z)
• S2RMs: Spatially Structured Recurrent Modules [105.0377129434636]
  We take a step towards exploiting dynamic structure that are capable of simultaneously exploiting both modular andtemporal structures. We find our models to be robust to the number of available views and better capable of generalization to novel tasks without additional training.
  arXiv  Detail & Related papers  (2020-07-13T17:44:30Z)
• Structure by Architecture: Structured Representations without Regularization [31.75200752252397]
  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.
  arXiv  Detail & Related papers  (2020-06-14T04:37:08Z)

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.