# Symbolic Snapshot Ensembles

arXiv: https://arxiv.org/abs/2510.24633 · HTML: https://mlsanity.com/paper/2510.24633/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 35 references that are in the map.
- First posted on arXiv 28 Oct 2025.

## Builds on (most cited first, 12 of 12)

- [Convolutional 2D Knowledge Graph Embeddings](https://mlsanity.com/paper/1707.01476/) (2017)
- [Snapshot Ensembles: Train 1, get M for free](https://mlsanity.com/paper/1704.00109/) (2017)
- [Learning Explanatory Rules from Noisy Data](https://mlsanity.com/paper/1711.04574/) (2017)
- [Inductive logic programming at 30: a new introduction](https://mlsanity.com/paper/2008.07912/) (2020)
- [Learning programs by learning from failures](https://mlsanity.com/paper/2005.02259/) (2020)
- [Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic Sparsity](https://mlsanity.com/paper/2106.14568/) (2021)
- [Checkpoint Ensembles: Ensemble Methods from a Single Training Process](https://mlsanity.com/paper/1710.03282/) (2017)
- [Horizontal and Vertical Ensemble with Deep Representation for Classification](https://mlsanity.com/paper/1306.2759/) (2013)
- [Inductive general game playing](https://mlsanity.com/paper/1906.09627/) (2019)
- [MotherNets: Rapid Deep Ensemble Learning](https://mlsanity.com/paper/1809.04270/) (2018)
- [Prune and Tune Ensembles: Low-Cost Ensemble Learning With Sparse Independent Subnetworks](https://mlsanity.com/paper/2202.11782/) (2022)
- [Explainable Models via Compression of Tree Ensembles](https://mlsanity.com/paper/2206.07904/) (2022)

## 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.