One-Shot Induction of Generalized Logical Concepts via Human Guidance

TL;DR

This paper introduces a new method for learning generalized logical concepts from a single example by combining a novel distance measure and human advice, improving efficiency and sample-efficiency in concept learning.

Contribution

It proposes a semantic distance measure and human advice integration to enhance one-shot logical concept learning, with theoretical guarantees and empirical validation.

Findings

The distance measure improves search efficiency.

Human advice increases sample-efficiency.

The approach outperforms traditional learners on diverse tasks.

Abstract

We consider the problem of learning generalized first-order representations of concepts from a single example. To address this challenging problem, we augment an inductive logic programming learner with two novel algorithmic contributions. First, we define a distance measure between candidate concept representations that improves the efficiency of search for target concept and generalization. Second, we leverage richer human inputs in the form of advice to improve the sample-efficiency of learning. We prove that the proposed distance measure is semantically valid and use that to derive a PAC bound. Our experimental analysis on diverse concept learning tasks demonstrates both the effectiveness and efficiency of the proposed approach over a first-order concept learner using only examples.