mlsanityData to 7 Oct 2026

Predicate Invention by Learning From Failures

arXiv 2104.14426 ↗First posted 29 Apr 2021cs.AIcited by 9

Not on the map. Why?

Abstract (arXiv)

Discovering novel high-level concepts is one of the most important steps needed for human-level AI. In inductive logic programming (ILP), discovering novel high-level concepts is known as predicate invention (PI). Although seen as crucial since the founding of ILP, PI is notoriously difficult and most ILP systems do not support it. In this paper, we introduce POPPI, an ILP system that formulates the PI problem as an answer set programming problem. Our experiments show that (i) PI can drastically improve learning performance when useful, (ii) PI is not too costly when unnecessary, and (iii) POPPI can substantially outperform existing ILP systems.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 11 of its 45 references that are in the map. First posted on arXiv 29 Apr 2021.

Builds on

11 of 45 references.

References · 11

  1. 2017Learning Explanatory Rules from Noisy Datacited by 210
  2. 2017Multi-shot ASP solving with clingocited by 115
  3. 2020Learning programs by learning from failurescited by 73
  4. 2020Turning 30: New Ideas in Inductive Logic Programmingcited by 42
  5. 2019Making sense of sensory inputcited by 29
  6. 2020Randomised Gaussian Process Upper Confidence Bound for Bayesian Optimisationcited by 22
  7. 2019Logical reduction of metarulescited by 19
  8. 2019Learning Relational Representations with Auto-encoding Logic Programscited by 13
  9. 2017Best-Effort Inductive Logic Programming via Fine-grained Cost-based Hypothesis Generationcited by 11
  10. 2019Playgol: learning programs through playcited by 8
  11. 2016Clustering-Based Relational Unsupervised Representation Learning with an Explicit Distributed Representationcited by 3

Built on by

Cited by year

Citing papers per year: 2021: 3; 2022: 3; 2023: 0; 2024: 2; 2025: 1.

9 papers.

  1. 2022CrossBeam: Learning to Search in Bottom-Up Program Synthesiscited by 18
  2. 2021Learning Higher-Order Programs without Meta-Interpretive Learningcited by 14
  3. 2022Learning logic programs by combining programscited by 7
  4. 2024EXPIL: Explanatory Predicate Invention for Learning in Gamescited by 5
  5. 2022Learning programs with magic valuescited by 2
  6. 2025Predicate Renaming via Large Language Modelscited by 2
  7. 2021Learning logic programs through divide, constrain, and conquercited by 1
  8. 2024Learning logic programs by finding minimal unsatisfiable subprogramscited by 1
  9. 2021Parallel Constraint-Driven Inductive Logic Programmingcited by 0