Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.24633 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915583259312128 |
|---|---|
| author | Liu, Mingyue Cropper, Andrew |
| author_facet | Liu, Mingyue Cropper, Andrew |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_24633 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Symbolic Snapshot Ensembles Liu, Mingyue Cropper, Andrew Machine Learning Logic in Computer Science 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. |
| title | Symbolic Snapshot Ensembles |
| topic | Machine Learning Logic in Computer Science |
| url | https://arxiv.org/abs/2510.24633 |