Relational program synthesis with numerical reasoning
Program synthesis approaches struggle to learn programs with numerical values. An especially difficult problem is learning continuous values over multiple examples, such as intervals. To overcome this limitation, we introduce an inductive logic programming approach which combines relational learning with numerical reasoning. Our approach, which we call NUMSYNTH, uses satisfiability modulo theories solvers to efficiently learn programs with numerical values. Our approach can identify numerical values in linear arithmetic fragments, such as real difference logic, and from infinite domains, such as real numbers or integers. Our experiments on four diverse domains, including game playing and program synthesis, show that our approach can (i) learn programs with numerical values from linear arithmetical reasoning, and (ii) outperform existing approaches in terms of predictive accuracies and learning times.
Code (1)
Tasks
Inductive logic programmingProgram SynthesisRelational ReasoningSimilar Papers 제목 키워드 기반
Generating Programmatic Referring Expressions via Program Synthesis
Incorporating symbolic reasoning into machine learning algorithms is a promising approach to improve performance on learning tasks that require logical reasoning. We study the problem of generating a programmatic variant…
Enumerative SearchLogical ReasoningProgram SynthesisOnce Upon an Input: Reasoning via Per-Instance Program Synthesis
Large language models (LLMs) excel at zero-shot inference but continue to struggle with complex, multi-step reasoning. Recent methods that augment LLMs with intermediate reasoning steps such as Chain of Thought (CoT) and…
Visual Question AnsweringMathematical ReasoningRelational ReasoningProgram SynthesisRelational decomposition for program synthesis
We introduce a novel approach to program synthesis that decomposes complex functional tasks into simpler relational synthesis sub-tasks. We demonstrate the effectiveness of our approach using an off-the-shelf inductive l…
Inductive logic programmingProgram SynthesisPix2Code: Learning to Compose Neural Visual Concepts as Programs
The challenge in learning abstract concepts from images in an unsupervised fashion lies in the required integration of visual perception and generalizable relational reasoning. Moreover, the unsupervised nature of this t…
Program SynthesisRelational ReasoningLLMs for Relational Reasoning: How Far are We?
Large language models (LLMs) have revolutionized many areas (e.g. natural language processing, software engineering, etc.) by achieving state-of-the-art performance on extensive downstream tasks. Aiming to achieve robust…
Common Sense ReasoningDecision MakingInductive logic programmingProgram induction+2