Multi-objective Deep Data Generation with Correlated Property Control
- URL: http://arxiv.org/abs/2210.01796v1
- Date: Sat, 1 Oct 2022 00:35:45 GMT
- Title: Multi-objective Deep Data Generation with Correlated Property Control
- Authors: Shiyu Wang, Xiaojie Guo, Xuanyang Lin, Bo Pan, Yuanqi Du, Yinkai Wang,
Yanfang Ye, Ashley Ann Petersen, Austin Leitgeb, Saleh AlKhalifa, Kevin
Minbiole, Bill Wuest, Amarda Shehu, Liang Zhao
- Abstract summary: We propose a novel deep generative framework that recovers semantics and the correlation of properties through disentangled latent vectors.
Our generative model preserves properties of interest while handling correlation and conflicts of properties under a multi-objective optimization framework.
- Score: 23.99970130388449
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Developing deep generative models has been an emerging field due to the
ability to model and generate complex data for various purposes, such as image
synthesis and molecular design. However, the advancement of deep generative
models is limited by challenges to generate objects that possess multiple
desired properties: 1) the existence of complex correlation among real-world
properties is common but hard to identify; 2) controlling individual property
enforces an implicit partially control of its correlated properties, which is
difficult to model; 3) controlling multiple properties under various manners
simultaneously is hard and under-explored. We address these challenges by
proposing a novel deep generative framework that recovers semantics and the
correlation of properties through disentangled latent vectors. The correlation
is handled via an explainable mask pooling layer, and properties are precisely
retained by generated objects via the mutual dependence between latent vectors
and properties. Our generative model preserves properties of interest while
handling correlation and conflicts of properties under a multi-objective
optimization framework. The experiments demonstrate our model's superior
performance in generating data with desired properties.
Related papers
- Deep Causal Generative Models with Property Control [11.604321459670315]
We propose a novel deep generative framework called the Correlation-aware Causal Variational Auto-encoder (C2VAE)
C2VAE simultaneously recovers the correlation and causal relationships between properties using disentangled latent vectors.
arXiv Detail & Related papers (2024-05-25T13:07:27Z) - Controllable Data Generation Via Iterative Data-Property Mutual Mappings [13.282793266390316]
We propose a framework to enhance VAE-based data generators with property controllability and ensure disentanglement.
The proposed framework is implemented on four VAE-based controllable generators to evaluate its performance on property error, disentanglement, generation quality, and training time.
arXiv Detail & Related papers (2023-10-11T17:34:56Z) - Heterogeneous Entity Matching with Complex Attribute Associations using
BERT and Neural Networks [0.7252027234425334]
We introduce a novel entity matching model, dubbed Entity Matching Model for Capturing Complex Attribute Relationships(EMM-CCAR)
Specifically, this model transforms the matching task into a sequence matching problem to mitigate the impact of varying data formats.
In comparison with the DER-SSM and Ditto approaches, our model improvements of approximately 4% and 1% in F1 scores, respectively.
arXiv Detail & Related papers (2023-09-20T03:49:57Z) - A Pareto-optimal compositional energy-based model for sampling and
optimization of protein sequences [55.25331349436895]
Deep generative models have emerged as a popular machine learning-based approach for inverse problems in the life sciences.
These problems often require sampling new designs that satisfy multiple properties of interest in addition to learning the data distribution.
arXiv Detail & Related papers (2022-10-19T19:04:45Z) - Learning Conditional Invariance through Cycle Consistency [60.85059977904014]
We propose a novel approach to identify meaningful and independent factors of variation in a dataset.
Our method involves two separate latent subspaces for the target property and the remaining input information.
We demonstrate on synthetic and molecular data that our approach identifies more meaningful factors which lead to sparser and more interpretable models.
arXiv Detail & Related papers (2021-11-25T17:33:12Z) - Controllable Dialogue Generation with Disentangled Multi-grained Style
Specification and Attribute Consistency Reward [47.96949534259019]
We propose a controllable dialogue generation model to steer response generation under multi-attribute constraints.
We categorize the commonly used control attributes into global and local ones, which possess different granularities of effects on response generation.
Our model can significantly outperform competitive baselines in terms of response quality, content diversity and controllability.
arXiv Detail & Related papers (2021-09-14T14:29:38Z) - Model-agnostic multi-objective approach for the evolutionary discovery
of mathematical models [55.41644538483948]
In modern data science, it is more interesting to understand the properties of the model, which parts could be replaced to obtain better results.
We use multi-objective evolutionary optimization for composite data-driven model learning to obtain the algorithm's desired properties.
arXiv Detail & Related papers (2021-07-07T11:17:09Z) - Neural Production Systems [90.75211413357577]
Visual environments are structured, consisting of distinct objects or entities.
To partition images into entities, deep-learning researchers have proposed structural inductive biases.
We take inspiration from cognitive science and resurrect a classic approach, which consists of a set of rule templates.
This architecture achieves a flexible, dynamic flow of control and serves to factorize entity-specific and rule-based information.
arXiv Detail & Related papers (2021-03-02T18:53:20Z) - Polymer Informatics with Multi-Task Learning [0.06524460254566902]
We show the potency of multi-task learning approaches that exploit inherent correlations effectively.
Data pertaining to 36 different properties of over $13, 000$ polymers are coalesced and supplied to deep-learning multi-task architectures.
The multi-task approach is accurate, efficient, scalable, and amenable to transfer learning as more data on the same or different properties become available.
arXiv Detail & Related papers (2020-10-28T18:28:12Z) - Goal-directed Generation of Discrete Structures with Conditional
Generative Models [85.51463588099556]
We introduce a novel approach to directly optimize a reinforcement learning objective, maximizing an expected reward.
We test our methodology on two tasks: generating molecules with user-defined properties and identifying short python expressions which evaluate to a given target value.
arXiv Detail & Related papers (2020-10-05T20:03:13Z)
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.