Constrained Generation of Semantically Valid Graphs via Regularizing Variational Autoencoders
This work addresses the problem of ensuring semantic validity in graph generation for domains like chemistry and biology, representing an incremental improvement over prior generative models.
The paper tackles the challenge of generating semantically valid graphs, such as molecules and protein networks, by proposing a regularization framework for variational autoencoders that incorporates constraints into the decoder's output distribution. Experimental results show a significantly higher likelihood of sampling valid graphs compared to existing methods.
Deep generative models have achieved remarkable success in various data domains, including images, time series, and natural languages. There remain, however, substantial challenges for combinatorial structures, including graphs. One of the key challenges lies in the difficulty of ensuring semantic validity in context. For examples, in molecular graphs, the number of bonding-electron pairs must not exceed the valence of an atom; whereas in protein interaction networks, two proteins may be connected only when they belong to the same or correlated gene ontology terms. These constraints are not easy to be incorporated into a generative model. In this work, we propose a regularization framework for variational autoencoders as a step toward semantic validity. We focus on the matrix representation of graphs and formulate penalty terms that regularize the output distribution of the decoder to encourage the satisfaction of validity constraints. Experimental results confirm a much higher likelihood of sampling valid graphs in our approach, compared with others reported in the literature.