Goal-directed Generation of Discrete Structures with Conditional
Generative Models
- URL: http://arxiv.org/abs/2010.02311v2
- Date: Fri, 23 Oct 2020 11:15:31 GMT
- Title: Goal-directed Generation of Discrete Structures with Conditional
Generative Models
- Authors: Amina Mollaysa, Brooks Paige, Alexandros Kalousis
- Abstract summary: 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.
- Score: 85.51463588099556
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Despite recent advances, goal-directed generation of structured discrete data
remains challenging. For problems such as program synthesis (generating source
code) and materials design (generating molecules), finding examples which
satisfy desired constraints or exhibit desired properties is difficult. In
practice, expensive heuristic search or reinforcement learning algorithms are
often employed. In this paper we investigate the use of conditional generative
models which directly attack this inverse problem, by modeling the distribution
of discrete structures given properties of interest. Unfortunately, maximum
likelihood training of such models often fails with the samples from the
generative model inadequately respecting the input properties. To address this,
we introduce a novel approach to directly optimize a reinforcement learning
objective, maximizing an expected reward. We avoid high-variance score-function
estimators that would otherwise be required by sampling from an approximation
to the normalized rewards, allowing simple Monte Carlo estimation of model
gradients. 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. In both cases, we find improvements over maximum
likelihood estimation and other baselines.
Related papers
- Towards Learning Stochastic Population Models by Gradient Descent [0.0]
We show that simultaneous estimation of parameters and structure poses major challenges for optimization procedures.
We demonstrate accurate estimation of models but find that enforcing the inference of parsimonious, interpretable models drastically increases the difficulty.
arXiv Detail & Related papers (2024-04-10T14:38:58Z) - ChiroDiff: Modelling chirographic data with Diffusion Models [132.5223191478268]
We introduce a powerful model-class namely "Denoising Diffusion Probabilistic Models" or DDPMs for chirographic data.
Our model named "ChiroDiff", being non-autoregressive, learns to capture holistic concepts and therefore remains resilient to higher temporal sampling rate.
arXiv Detail & Related papers (2023-04-07T15:17:48Z) - Training Discrete Deep Generative Models via Gapped Straight-Through
Estimator [72.71398034617607]
We propose a Gapped Straight-Through ( GST) estimator to reduce the variance without incurring resampling overhead.
This estimator is inspired by the essential properties of Straight-Through Gumbel-Softmax.
Experiments demonstrate that the proposed GST estimator enjoys better performance compared to strong baselines on two discrete deep generative modeling tasks.
arXiv Detail & Related papers (2022-06-15T01:46:05Z) - Score-Based Generative Models for Molecule Generation [0.8808021343665321]
We train a Transformer-based score function on representations of 1.5 million samples from the ZINC dataset.
We use the Moses benchmarking framework to evaluate the generated samples on a suite of metrics.
arXiv Detail & Related papers (2022-03-07T13:46:02Z) - 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) - Evaluating State-of-the-Art Classification Models Against Bayes
Optimality [106.50867011164584]
We show that we can compute the exact Bayes error of generative models learned using normalizing flows.
We use our approach to conduct a thorough investigation of state-of-the-art classification models.
arXiv Detail & Related papers (2021-06-07T06:21:20Z) - Anomaly Detection of Time Series with Smoothness-Inducing Sequential
Variational Auto-Encoder [59.69303945834122]
We present a Smoothness-Inducing Sequential Variational Auto-Encoder (SISVAE) model for robust estimation and anomaly detection of time series.
Our model parameterizes mean and variance for each time-stamp with flexible neural networks.
We show the effectiveness of our model on both synthetic datasets and public real-world benchmarks.
arXiv Detail & Related papers (2021-02-02T06:15:15Z) - Learning Consistent Deep Generative Models from Sparse Data via
Prediction Constraints [16.48824312904122]
We develop a new framework for learning variational autoencoders and other deep generative models.
We show that these two contributions -- prediction constraints and consistency constraints -- lead to promising image classification performance.
arXiv Detail & Related papers (2020-12-12T04:18:50Z) - Maximum Entropy Model Rollouts: Fast Model Based Policy Optimization
without Compounding Errors [10.906666680425754]
We propose a Dyna-style model-based reinforcement learning algorithm, which we called Maximum Entropy Model Rollouts (MEMR)
To eliminate the compounding errors, we only use our model to generate single-step rollouts.
arXiv Detail & Related papers (2020-06-08T21:38:15Z) - Improving Molecular Design by Stochastic Iterative Target Augmentation [38.44457632751997]
Generative models in molecular design tend to be richly parameterized, data-hungry neural models.
We propose a surprisingly effective self-training approach for iteratively creating additional molecular targets.
Our approach outperforms the previous state-of-the-art in conditional molecular design by over 10% in absolute gain.
arXiv Detail & Related papers (2020-02-11T22:40:04Z)
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.