Unsupervised Learning of Neurosymbolic Encoders
arXiv:2107.13132
Abstract
We present a framework for the unsupervised learning of neurosymbolic encoders, which are encoders obtained by composing neural networks with symbolic programs from a domain-specific language. Our framework naturally incorporates symbolic expert knowledge into the learning process, which leads to more interpretable and factorized latent representations compared to fully neural encoders. We integrate modern program synthesis techniques with the variational autoencoding (VAE) framework, in order to learn a neurosymbolic encoder in conjunction with a standard decoder. The programmatic descriptions from our encoders can benefit many analysis workflows, such as in behavior modeling where interpreting agent actions and movements is important. We evaluate our method on learning latent representations for real-world trajectory data from animal biology and sports analytics. We show that our approach offers significantly better separation of meaningful categories than standard VAEs and leads to practical gains on downstream analysis tasks, such as for behavior classification.
References in corpus (17)
- Adam: A Method for Stochastic Optimization
- Auto-Encoding Variational Bayes
- UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
- Natural Scales in Geographical Patterns
- InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
- NVAE: A Deep Hierarchical Variational Autoencoder
- Composing graphical models with neural networks for structured representations and fast inference
- Fast Decoding in Sequence Models using Discrete Latent Variables
- Programmatically Interpretable Reinforcement Learning
- Disentangled Sequential Autoencoder
- Learning Disentangled Joint Continuous and Discrete Representations
- Discrete Variational Autoencoders
- The Multi-Agent Behavior Dataset: Mouse Dyadic Social Interactions
- Towards Synthesizing Complex Programs from Input-Output Examples
- A Survey on Neural Network Interpretability
- Selecting Representative Examples for Program Synthesis
- Learning Task-General Representations with Generative Neuro-Symbolic Modeling