Neural Production Systems

by   Anirudh Goyal, et al.

Visual environments are structured, consisting of distinct objects or entities. These entities have properties – both visible and latent – that determine the manner in which they interact with one another. To partition images into entities, deep-learning researchers have proposed structural inductive biases such as slot-based architectures. To model interactions among entities, equivariant graph neural nets (GNNs) are used, but these are not particularly well suited to the task for two reasons. First, GNNs do not predispose interactions to be sparse, as relationships among independent entities are likely to be. Second, GNNs do not factorize knowledge about interactions in an entity-conditional manner. As an alternative, we take inspiration from cognitive science and resurrect a classic approach, production systems, which consist of a set of rule templates that are applied by binding placeholder variables in the rules to specific entities. Rules are scored on their match to entities, and the best fitting rules are applied to update entity properties. In a series of experiments, we demonstrate that this architecture achieves a flexible, dynamic flow of control and serves to factorize entity-specific and rule-based information. This disentangling of knowledge achieves robust future-state prediction in rich visual environments, outperforming state-of-the-art methods using GNNs, and allows for the extrapolation from simple (few object) environments to more complex environments.


page 6

page 7

page 13

page 16

page 18


Medical Entity Disambiguation Using Graph Neural Networks

Medical knowledge bases (KBs), distilled from biomedical literature and ...

Explore Entity Embedding Effectiveness in Entity Retrieval

This paper explores entity embedding effectiveness in ad-hoc entity retr...

TeKo: Text-Rich Graph Neural Networks with External Knowledge

Graph Neural Networks (GNNs) have gained great popularity in tackling va...

Inductive Entity Representations from Text via Link Prediction

We present a method for learning representations of entities, that uses ...

Coordination Among Neural Modules Through a Shared Global Workspace

Deep learning has seen a movement away from representing examples with a...

SOS Rules for Equivalences of Reaction Systems

Reaction Systems (RSs) are a successful computational framework inspired...

Business Entity Matching with Siamese Graph Convolutional Networks

Data integration has been studied extensively for decades and approached...