Towards Probabilistic Inductive Logic Programming with Neurosymbolic Inference and Relaxation
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909320271101952 |
|---|---|
| author | Hillerstrom, Fieke Burghouts, Gertjan |
| author_facet | Hillerstrom, Fieke Burghouts, Gertjan |
| contents | Many inductive logic programming (ILP) methods are incapable of learning programs from probabilistic background knowledge, e.g. coming from sensory data or neural networks with probabilities. We propose Propper, which handles flawed and probabilistic background knowledge by extending ILP with a combination of neurosymbolic inference, a continuous criterion for hypothesis selection (BCE) and a relaxation of the hypothesis constrainer (NoisyCombo). For relational patterns in noisy images, Propper can learn programs from as few as 8 examples. It outperforms binary ILP and statistical models such as a Graph Neural Network. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_11367 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Towards Probabilistic Inductive Logic Programming with Neurosymbolic Inference and Relaxation Hillerstrom, Fieke Burghouts, Gertjan Artificial Intelligence Machine Learning Many inductive logic programming (ILP) methods are incapable of learning programs from probabilistic background knowledge, e.g. coming from sensory data or neural networks with probabilities. We propose Propper, which handles flawed and probabilistic background knowledge by extending ILP with a combination of neurosymbolic inference, a continuous criterion for hypothesis selection (BCE) and a relaxation of the hypothesis constrainer (NoisyCombo). For relational patterns in noisy images, Propper can learn programs from as few as 8 examples. It outperforms binary ILP and statistical models such as a Graph Neural Network. |
| title | Towards Probabilistic Inductive Logic Programming with Neurosymbolic Inference and Relaxation |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2408.11367 |