Timezone: »

 
Poster
Efficient Generation of Structured Objects with Constrained Adversarial Networks
Luca Di Liello · Pierfrancesco Ardino · Jacopo Gobbi · Paolo Morettin · Stefano Teso · Andrea Passerini

Wed Dec 09 09:00 AM -- 11:00 AM (PST) @ Poster Session 3 #944
in Poster Session 4 »

Generative Adversarial Networks (GANs) struggle to generate structured objects like molecules and game maps. The issue is that structured objects must satisfy hard requirements (e.g., molecules must be chemically valid) that are difficult to acquire from examples alone. As a remedy, we propose Constrained Adversarial Networks (CANs), an extension of GANs in which the constraints are embedded into the model during training. This is achieved by penalizing the generator proportionally to the mass it allocates to invalid structures. In contrast to other generative models, CANs support efficient inference of valid structures (with high probability) and allows to turn on and off the learned constraints at inference time. CANs handle arbitrary logical constraints and leverage knowledge compilation techniques to efficiently evaluate the disagreement between the model and the constraints. Our setup is further extended to hybrid logical-neural constraints for capturing very complex constraints, like graph reachability. An extensive empirical analysis shows that CANs efficiently generate valid structures that are both high-quality and novel.

Keywords: Causal Inference · Probabilistic Methods

Author Information

Luca Di Liello (University of Trento)
Pierfrancesco Ardino (University of Trento)
Jacopo Gobbi (University of Trento)
Paolo Morettin (University of Trento)
Stefano Teso (University of Trento)
Andrea Passerini (Università degli Studi di Trento)

More from the Same Authors