ComboStoc: Combinatorial Stochasticity for Diffusion Generative Models
- URL: http://arxiv.org/abs/2405.13729v2
- Date: Fri, 24 May 2024 07:05:59 GMT
- Title: ComboStoc: Combinatorial Stochasticity for Diffusion Generative Models
- Authors: Rui Xu, Jiepeng Wang, Hao Pan, Yang Liu, Xin Tong, Shiqing Xin, Changhe Tu, Taku Komura, Wenping Wang,
- Abstract summary: We show that the space spanned by the combination of dimensions and attributes is insufficiently sampled by existing training scheme of diffusion generative models.
We present a simple fix to this problem by constructing processes that fully exploit the structures, hence the name ComboStoc.
- Score: 65.82630283336051
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: In this paper, we study an under-explored but important factor of diffusion generative models, i.e., the combinatorial complexity. Data samples are generally high-dimensional, and for various structured generation tasks, there are additional attributes which are combined to associate with data samples. We show that the space spanned by the combination of dimensions and attributes is insufficiently sampled by existing training scheme of diffusion generative models, causing degraded test time performance. We present a simple fix to this problem by constructing stochastic processes that fully exploit the combinatorial structures, hence the name ComboStoc. Using this simple strategy, we show that network training is significantly accelerated across diverse data modalities, including images and 3D structured shapes. Moreover, ComboStoc enables a new way of test time generation which uses insynchronized time steps for different dimensions and attributes, thus allowing for varying degrees of control over them.
Related papers
- IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generation [70.8833857249951]
IterComp is a novel framework that aggregates composition-aware model preferences from multiple models.
We propose an iterative feedback learning method to enhance compositionality in a closed-loop manner.
IterComp opens new research avenues in reward feedback learning for diffusion models and compositional generation.
arXiv Detail & Related papers (2024-10-09T17:59:13Z) - Flexible inference in heterogeneous and attributed multilayer networks [21.349513661012498]
We develop a probabilistic generative model to perform inference in multilayer networks with arbitrary types of information.
We demonstrate its ability to unveil a variety of patterns in a social support network among villagers in rural India.
arXiv Detail & Related papers (2024-05-31T15:21:59Z) - On the Trajectory Regularity of ODE-based Diffusion Sampling [79.17334230868693]
Diffusion-based generative models use differential equations to establish a smooth connection between a complex data distribution and a tractable prior distribution.
In this paper, we identify several intriguing trajectory properties in the ODE-based sampling process of diffusion models.
arXiv Detail & Related papers (2024-05-18T15:59:41Z) - T1: Scaling Diffusion Probabilistic Fields to High-Resolution on Unified
Visual Modalities [69.16656086708291]
Diffusion Probabilistic Field (DPF) models the distribution of continuous functions defined over metric spaces.
We propose a new model comprising of a view-wise sampling algorithm to focus on local structure learning.
The model can be scaled to generate high-resolution data while unifying multiple modalities.
arXiv Detail & Related papers (2023-05-24T03:32:03Z) - Latent Processes Identification From Multi-View Time Series [17.33428123777779]
We propose a novel framework that employs the contrastive learning technique to invert the data generative process for enhanced identifiability.
MuLTI integrates a permutation mechanism that merges corresponding overlapped variables by the establishment of an optimal transport formula.
arXiv Detail & Related papers (2023-05-14T14:21:58Z) - 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) - Structurally Diverse Sampling Reduces Spurious Correlations in Semantic
Parsing Datasets [51.095144091781734]
We propose a novel algorithm for sampling a structurally diverse set of instances from a labeled instance pool with structured outputs.
We show that our algorithm performs competitively with or better than prior algorithms in not only compositional template splits but also traditional IID splits.
In general, we find that diverse train sets lead to better generalization than random training sets of the same size in 9 out of 10 dataset-split pairs.
arXiv Detail & Related papers (2022-03-16T07:41:27Z) - Hierarchical Few-Shot Generative Models [18.216729811514718]
We study a latent variables approach that extends the Neural Statistician to a fully hierarchical approach with an attention-based point to set-level aggregation.
Our results show that the hierarchical formulation better captures the intrinsic variability within the sets in the small data regime.
arXiv Detail & Related papers (2021-10-23T19:19:39Z) - PIETS: Parallelised Irregularity Encoders for Forecasting with
Heterogeneous Time-Series [5.911865723926626]
Heterogeneity and irregularity of multi-source data sets present a significant challenge to time-series analysis.
In this work, we design a novel architecture, PIETS, to model heterogeneous time-series.
We show that PIETS is able to effectively model heterogeneous temporal data and outperforms other state-of-the-art approaches in the prediction task.
arXiv Detail & Related papers (2021-09-30T20:01:19Z) - Stacking VAE with Graph Neural Networks for Effective and Interpretable
Time Series Anomaly Detection [5.935707085640394]
We propose a stacking variational auto-encoder (VAE) model with graph neural networks for the effective and interpretable time-series anomaly detection.
We show that our proposed model outperforms the strong baselines on three public datasets with considerable improvements.
arXiv Detail & Related papers (2021-05-18T09:50:00Z)
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.