Skews in the Phenomenon Space Hinder Generalization in Text-to-Image Generation

• URL: http://arxiv.org/abs/2403.16394v2
• Date: Fri, 25 Oct 2024 13:56:36 GMT
• Title: Skews in the Phenomenon Space Hinder Generalization in Text-to-Image Generation
• Authors: Yingshan Chang, Yasi Zhang, Zhiyuan Fang, Yingnian Wu, Yonatan Bisk, Feng Gao,
• Abstract summary: We introduce statistical metrics that quantify both the linguistic and visual skew of a dataset for relational learning. We show that systematically controlled metrics are strongly predictive of generalization performance. This work informs an important direction towards quality-enhancing the data diversity or balance to scaling up the absolute size.
• Score: 59.138470433237615
• License:
• Abstract: The literature on text-to-image generation is plagued by issues of faithfully composing entities with relations. But there lacks a formal understanding of how entity-relation compositions can be effectively learned. Moreover, the underlying phenomenon space that meaningfully reflects the problem structure is not well-defined, leading to an arms race for larger quantities of data in the hope that generalization emerges out of large-scale pretraining. We hypothesize that the underlying phenomenological coverage has not been proportionally scaled up, leading to a skew of the presented phenomenon which harms generalization. We introduce statistical metrics that quantify both the linguistic and visual skew of a dataset for relational learning, and show that generalization failures of text-to-image generation are a direct result of incomplete or unbalanced phenomenological coverage. We first perform experiments in a synthetic domain and demonstrate that systematically controlled metrics are strongly predictive of generalization performance. Then we move to natural images and show that simple distribution perturbations in light of our theories boost generalization without enlarging the absolute data size. This work informs an important direction towards quality-enhancing the data diversity or balance orthogonal to scaling up the absolute size. Our discussions point out important open questions on 1) Evaluation of generated entity-relation compositions, and 2) Better models for reasoning with abstract relations.

Related papers

• Representations as Language: An Information-Theoretic Framework for Interpretability [7.2129390689756185]
  Large scale neural models show impressive performance across a wide array of linguistic tasks. Despite this they remain, largely, black-boxes, inducing vector-representations of their input that prove difficult to interpret. We introduce a novel approach to interpretability that looks at the mapping a model learns from sentences to representations as a kind of language in its own right.
  arXiv  Detail & Related papers  (2024-06-04T16:14:00Z)
• Neural Causal Abstractions [63.21695740637627]
  We develop a new family of causal abstractions by clustering variables and their domains. We show that such abstractions are learnable in practical settings through Neural Causal Models. Our experiments support the theory and illustrate how to scale causal inferences to high-dimensional settings involving image data.
  arXiv  Detail & Related papers  (2024-01-05T02:00:27Z)
• On the Complexity of Bayesian Generalization [141.21610899086392]
  We consider concept generalization at a large scale in the diverse and natural visual spectrum. We study two modes when the problem space scales up, and the $complexity$ of concepts becomes diverse.
  arXiv  Detail & Related papers  (2022-11-20T17:21:37Z)
• Beyond spectral gap: The role of the topology in decentralized learning [58.48291921602417]
  In data-parallel optimization of machine learning models, workers collaborate to improve their estimates of the model. This paper aims to paint an accurate picture of sparsely-connected distributed optimization when workers share the same data distribution. Our theory matches empirical observations in deep learning, and accurately describes the relative merits of different graph topologies.
  arXiv  Detail & Related papers  (2022-06-07T08:19:06Z)
• Rate-Distortion Theoretic Generalization Bounds for Stochastic Learning Algorithms [12.020634332110147]
  We prove novel generalization bounds through the lens of rate-distortion theory. Our results bring a more unified perspective on generalization and open up several future research directions.
  arXiv  Detail & Related papers  (2022-03-04T18:12:31Z)
• Generalizable Information Theoretic Causal Representation [37.54158138447033]
  We propose to learn causal representation from observational data by regularizing the learning procedure with mutual information measures according to our hypothetical causal graph. The optimization involves a counterfactual loss, based on which we deduce a theoretical guarantee that the causality-inspired learning is with reduced sample complexity and better generalization ability.
  arXiv  Detail & Related papers  (2022-02-17T00:38:35Z)
• Uniform Convergence, Adversarial Spheres and a Simple Remedy [40.44709296304123]
  Previous work has cast doubt on the general framework of uniform convergence and its ability to explain generalization in neural networks. We provide an extensive theoretical investigation of the previously studied data setting through the lens of infinitely-wide models. We prove that the Neural Tangent Kernel (NTK) also suffers from the same phenomenon and we uncover its origin.
  arXiv  Detail & Related papers  (2021-05-07T20:23:01Z)
• Supercharging Imbalanced Data Learning With Energy-based Contrastive Representation Transfer [72.5190560787569]
  In computer vision, learning from long tailed datasets is a recurring theme, especially for natural image datasets. Our proposal posits a meta-distributional scenario, where the data generating mechanism is invariant across the label-conditional feature distributions. This allows us to leverage a causal data inflation procedure to enlarge the representation of minority classes.
  arXiv  Detail & Related papers  (2020-11-25T00:13:11Z)
• Hyperbolic Graph Embedding with Enhanced Semi-Implicit Variational Inference [48.63194907060615]
  We build off of semi-implicit graph variational auto-encoders to capture higher-order statistics in a low-dimensional graph latent representation. We incorporate hyperbolic geometry in the latent space through a Poincare embedding to efficiently represent graphs exhibiting hierarchical structure.
  arXiv  Detail & Related papers  (2020-10-31T05:48:34Z)

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.