mlsanityData to 13 Oct 2026

Symbolic Snapshot Ensembles

arXiv 2510.24633 ↗First posted 28 Oct 2025cs.LG cs.LOcited by 0

Not on the map. Why?

Abstract (arXiv)

Inductive logic programming (ILP) is a form of logical machine learning. Most ILP algorithms learn a single hypothesis from a single training run. Ensemble methods train an ILP algorithm multiple times to learn multiple hypotheses. In this paper, we train an ILP algorithm only once and save intermediate hypotheses. We then combine the hypotheses using a minimum description length weighting scheme. Our experiments on multiple benchmarks, including game playing and visual reasoning, show that our approach improves predictive accuracy by 4% with less than 1% computational overhead.

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 12 of its 35 references that are in the map. First posted on arXiv 28 Oct 2025.

Builds on

12 of 35 references.

References · 12

  1. 2017Convolutional 2D Knowledge Graph Embeddingscited by 729
  2. 2017Snapshot Ensembles: Train 1, get M for freecited by 350
  3. 2017Learning Explanatory Rules from Noisy Datacited by 210
  4. 2020Inductive logic programming at 30: a new introductioncited by 85
  5. 2020Learning programs by learning from failurescited by 73
  6. 2021Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic Sparsitycited by 44
  7. 2017Checkpoint Ensembles: Ensemble Methods from a Single Training Processcited by 24
  8. 2013Horizontal and Vertical Ensemble with Deep Representation for Classificationcited by 22
  9. 2019Inductive general game playingcited by 18
  10. 2018MotherNets: Rapid Deep Ensemble Learningcited by 14
  11. 2022Prune and Tune Ensembles: Low-Cost Ensemble Learning With Sparse Independent Subnetworkscited by 13
  12. 2022Explainable Models via Compression of Tree Ensemblescited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Honey, I shrunk the hypothesis space (through logical preprocessing)
  2. 2025Efficient rule induction by ignoring pointless rules
  3. 2024Program Synthesis using Inductive Logic Programming for the Abstraction and Reasoning Corpus
  4. 2025Hypothesis Generation via LLM-Automated Language Bias for ILP
  5. 2025Symmetry breaking for inductive logic programming
  6. 2025Abductive Logical Rule Induction by Bridging Inductive Logic Programming and Multimodal Large Language Models
  7. 2025Bridging Logic Programming and Deep Learning for Explainability through ILASP ↗
  8. 2025Satisfiability Modulo Theory Meets Inductive Logic Programming