ZeroC: A Neuro-Symbolic Model for Zero-shot Concept Recognition and Acquisition at Inference Time

TL;DR

ZeroC is a neuro-symbolic model that enables zero-shot recognition and acquisition of novel concepts by representing them as graphs and using energy-based models for inference, improving generalization at inference time.

Contribution

ZeroC introduces a novel neuro-symbolic architecture that maps symbolic graph structures to energy-based models, allowing zero-shot concept recognition and acquisition during inference.

Findings

ZeroC successfully recognizes and acquires new concepts in a grid-world dataset.

The model demonstrates effective zero-shot classification and detection across domains.

ZeroC's architecture enables inference-time composition of novel concepts.

Abstract

Humans have the remarkable ability to recognize and acquire novel visual concepts in a zero-shot manner. Given a high-level, symbolic description of a novel concept in terms of previously learned visual concepts and their relations, humans can recognize novel concepts without seeing any examples. Moreover, they can acquire new concepts by parsing and communicating symbolic structures using learned visual concepts and relations. Endowing these capabilities in machines is pivotal in improving their generalization capability at inference time. In this work, we introduce Zero-shot Concept Recognition and Acquisition (ZeroC), a neuro-symbolic architecture that can recognize and acquire novel concepts in a zero-shot way. ZeroC represents concepts as graphs of constituent concept models (as nodes) and their relations (as edges). To allow inference time composition, we employ energy-based models (EBMs) to model concepts and relations. We design ZeroC architecture so that it allows a one-to-one mapping between a symbolic graph structure of a concept and its corresponding EBM, which for the first time, allows acquiring new concepts, communicating its graph structure, and applying it to classification and detection tasks (even across domains) at inference time. We introduce algorithms for learning and inference with ZeroC. We evaluate ZeroC on a challenging grid-world dataset which is designed to probe zero-shot concept recognition and acquisition, and demonstrate its capability.