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

• Supervised Score-Based Modeling by Gradient Boosting [49.556736252628745]
  We propose a Supervised Score-based Model (SSM) which can be viewed as a gradient boosting algorithm combining score matching. We provide a theoretical analysis of learning and sampling for SSM to balance inference time and prediction accuracy. Our model outperforms existing models in both accuracy and inference time.
  arXiv  Detail & Related papers  (2024-11-02T07:06:53Z)
• 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)
• Private Gradient Estimation is Useful for Generative Modeling [25.777591229903596]
  We present a new private generative modeling approach where samples are generated via Hamiltonian dynamics with gradients of the private dataset estimated by a well-trained network. Our model is able to generate data with a resolution of 256x256.
  arXiv  Detail & Related papers  (2023-05-18T02:51:17Z)
• 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)
• 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)
• 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.