Relational Neural Markov Random Fields

Yuqiao Chen, Sriraam Natarajan, Nicholas Ruozzi
Proceedings of The 25th International Conference on Artificial Intelligence and Statistics, PMLR 151:8260-8269, 2022.

Abstract

Statistical Relational Learning (SRL) models have attracted significant attention due to their ability to model complex data while handling uncertainty. However, most of these models have been restricted to discrete domains owing to the complexity of inference in continuous domains. In this work, we introduce Relational Neural Markov Random Fields (RN-MRFs) that allow handling of complex relational hybrid domains, i.e., those that include discrete and continuous quantities, and we propose a maximum pseudolikelihood estimation-based learning algorithm with importance sampling for training the neural potential parameters. The key advantage of our approach is that it makes minimal data distributional assumptions and can seamlessly embed human knowledge through potentials or relational rules. Our empirical evaluations across diverse domains, such as image processing and relational object mapping, demonstrate its practical utility.

Cite this Paper

BibTeX
@InProceedings{pmlr-v151-chen22f, title = { Relational Neural Markov Random Fields }, author = {Chen, Yuqiao and Natarajan, Sriraam and Ruozzi, Nicholas}, booktitle = {Proceedings of The 25th International Conference on Artificial Intelligence and Statistics}, pages = {8260--8269}, year = {2022}, editor = {Camps-Valls, Gustau and Ruiz, Francisco J. R. and Valera, Isabel}, volume = {151}, series = {Proceedings of Machine Learning Research}, month = {28--30 Mar}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v151/chen22f/chen22f.pdf}, url = {https://proceedings.mlr.press/v151/chen22f.html}, abstract = { Statistical Relational Learning (SRL) models have attracted significant attention due to their ability to model complex data while handling uncertainty. However, most of these models have been restricted to discrete domains owing to the complexity of inference in continuous domains. In this work, we introduce Relational Neural Markov Random Fields (RN-MRFs) that allow handling of complex relational hybrid domains, i.e., those that include discrete and continuous quantities, and we propose a maximum pseudolikelihood estimation-based learning algorithm with importance sampling for training the neural potential parameters. The key advantage of our approach is that it makes minimal data distributional assumptions and can seamlessly embed human knowledge through potentials or relational rules. Our empirical evaluations across diverse domains, such as image processing and relational object mapping, demonstrate its practical utility. } }
Endnote
%0 Conference Paper %T Relational Neural Markov Random Fields %A Yuqiao Chen %A Sriraam Natarajan %A Nicholas Ruozzi %B Proceedings of The 25th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2022 %E Gustau Camps-Valls %E Francisco J. R. Ruiz %E Isabel Valera %F pmlr-v151-chen22f %I PMLR %P 8260--8269 %U https://proceedings.mlr.press/v151/chen22f.html %V 151 %X Statistical Relational Learning (SRL) models have attracted significant attention due to their ability to model complex data while handling uncertainty. However, most of these models have been restricted to discrete domains owing to the complexity of inference in continuous domains. In this work, we introduce Relational Neural Markov Random Fields (RN-MRFs) that allow handling of complex relational hybrid domains, i.e., those that include discrete and continuous quantities, and we propose a maximum pseudolikelihood estimation-based learning algorithm with importance sampling for training the neural potential parameters. The key advantage of our approach is that it makes minimal data distributional assumptions and can seamlessly embed human knowledge through potentials or relational rules. Our empirical evaluations across diverse domains, such as image processing and relational object mapping, demonstrate its practical utility.
APA
Chen, Y., Natarajan, S. & Ruozzi, N.. (2022). Relational Neural Markov Random Fields . Proceedings of The 25th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 151:8260-8269 Available from https://proceedings.mlr.press/v151/chen22f.html.

Related Material