Towards Universal Neural Likelihood Inference
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910010739523584 |
|---|---|
| author | Brahmavar, Shreyas Bhat Li, Yang Liu, Qiyang Srivastava, Shashank Oliva, Junier |
| author_facet | Brahmavar, Shreyas Bhat Li, Yang Liu, Qiyang Srivastava, Shashank Oliva, Junier |
| contents | We introduce universal neural likelihood inference (UNLI): enabling a single model to provide data-grounded, conditional likelihood predictions for arbitrary targets given any collection of observed features, across diverse domains and tasks. To achieve UNLI over heterogeneous tabular data, we develop the Arbitrary Set-based Permutation-Invariant Reasoning Engine (ASPIRE) model. Our design addresses critical gaps in existing approaches to merge semantic-understanding capabilities and generalised numerical feature reasoning within a zero-shot capable framework. Trained on over 1,400 real diverse datasets spanning various domains, ASPIRE achieves 15\% higher F1 scores and 85\% lower RMSE than existing tabular foundation models in zero-shot and few-shot settings. Lastly, this work introduces open-world active feature acquisition, where we leverage the UNLI capabilities of ASPIRE to adeptly determine next feature-values to observe to improve inference time prediction accuracies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_09100 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Universal Neural Likelihood Inference Brahmavar, Shreyas Bhat Li, Yang Liu, Qiyang Srivastava, Shashank Oliva, Junier Machine Learning Artificial Intelligence We introduce universal neural likelihood inference (UNLI): enabling a single model to provide data-grounded, conditional likelihood predictions for arbitrary targets given any collection of observed features, across diverse domains and tasks. To achieve UNLI over heterogeneous tabular data, we develop the Arbitrary Set-based Permutation-Invariant Reasoning Engine (ASPIRE) model. Our design addresses critical gaps in existing approaches to merge semantic-understanding capabilities and generalised numerical feature reasoning within a zero-shot capable framework. Trained on over 1,400 real diverse datasets spanning various domains, ASPIRE achieves 15\% higher F1 scores and 85\% lower RMSE than existing tabular foundation models in zero-shot and few-shot settings. Lastly, this work introduces open-world active feature acquisition, where we leverage the UNLI capabilities of ASPIRE to adeptly determine next feature-values to observe to improve inference time prediction accuracies. |
| title | Towards Universal Neural Likelihood Inference |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2508.09100 |