Unsupervised Learning of Neurosymbolic Encoders
This work addresses the need for more interpretable and factorized latent representations in domains like behavior modeling, though it is incremental as it builds upon existing VAE and program synthesis techniques.
The paper tackles the problem of learning interpretable latent representations by introducing a framework for unsupervised learning of neurosymbolic encoders, which combine neural networks with symbolic programs. The result shows significantly better separation of meaningful categories on real-world trajectory data, leading to practical gains in downstream tasks like behavior classification.
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.